Locking Devices in Robotics

Locking devices are widely used in robotics, for instance to lock springs and joints or to reconfigure robots. This review article classifies the locking devices currently described in the literature and performs a comparative study. Designers can therefore better determine which locking device best matches the needs of their application. The locking devices are divided into three main categories based on different locking principles: 1) mechanical locking, 2) friction-based locking, and 3) singularity locking. Different locking devices in each category can be passive or active. Based on an extensive literature survey, this article summarizes the findings by comparing different locking devices on a set of properties of an ideal locking device.

Why Singularities Can Ruin Your Day

What do robots have in common with black holes? They both have singularities! we find out what singularities are, why they can cause havoc for roboticists and how to overcome them.

robot-axis

If you are interested in science, the word "singularity" probably makes you think of a black hole. Black holes are pretty popular right now, since the LIGO lab in America proved the existence of gravitational waves. Right at the center of a black hole, physicists theorize that there is a "gravitational singularity”. This means that the force of gravity gets so big, it goes to infinity. Robotic singularities use exactly the same concept as black holes. But, wait! Let's back up for a second. What are robotic singularities? How can they possibly be anything like black holes?

My Robot's

Imagine this. You want to use your robot to paint a line using a spray painting gun. To paint a perfect line, the robot needs to move at a constant velocity. If the robot changes velocity, some parts of the line will have more paint than others. This won't look very good. If the robot slows down too much, we'll get an unsightly blob of paint. Obviously, it's important that the robot moves along the line at a constant velocity. Robots are precise. Usually they can handle this without a problem. However, if there are any kinematic singularities in the line, the paint job could be ruined.
.

Singularities Tend to Infinity (whether you want them to or not!)

Remember I said that the gravity at the center of a black hole "goes to infinity?" This means that the gravitational force gets stronger and stronger the closer you get to the center. At the center of the black hole the gravitational force is theoretically infinite. This might not actually be true (nobody knows), but it's basically a property of math. Mathematics can easily handle the concept of infinity. The real world can't.
Lots of mathematical equations tend to infinity. As this physicist explains, theoretically you should create a singularity in your bathtub every time you pull the plug. The basic equation for the spiraling water says that the closer you get to the center of the plughole, the faster the water spins. According to the equation, the water should be moving infinitely fast right at the center. In reality that's not what happens. Physical systems cannot move infinitely fast (as far as we know).
Robot singularities happen because robots are controlled by math (which is okay with infinity), but are made of real, physical moving parts (which isn't). If an equation commands one robot joint to "rotate 180 degrees at infinite angular velocity”, the robot joint will say "I don't' think so!”.
robot-singularity

What Are Robot Singularities?

Singularities are caused by the inverse kinematics of the robot. When placed at a singularity, there may be an infinite number of ways for the kinematics to achieve the same tip position of the robot. If the optimal solution is not chosen, assuming there is one, the robot joints could be commanded to move in an impossible way. Infinite velocity is not the only type of singularity that causes problems and certain types of singularities can be more problematic than others. Some robots can be put in such a bad position that they need to be turned off, moved and restarted manually.

The 3 Types of Robot Singularities

Thankfully, industrial robots are not as problematic as the Stewart Platform. 6-axis industrial robots only suffer from three types of singularities. However, these singularities can still cause havoc.
The American National Standard for Industrial Robots and Robot Systems defines singularities as “a condition caused by the collinear alignment of two or more robot axes resulting in unpredictable robot motion and velocities”. Therefore, the three types of singularities are defined by which joint alignments cause the problem:

Wrist Singularities - These happen when two of the robot's wrist axes (joints 4 and 6) line up with each other. This can cause these joints to try and spin 180 degrees instantaneously.
Shoulder Singularities - These happen when the center of the robot's wrist aligns with the axis of joint 1. It causes joints 1 and 4 to try and spin 180 degrees instantaneously. A subset of this is an Alignment Singularity, where the first and last joints of the robot (joints 1 and 6) line up with each other.
Elbow Singularities - These happen when the center of the robot's wrist lies on the same plane as joints 2 and 3. Elbow singularities look like the robot has "reached too far", causing the elbow to lock in position.

How To Avoid Singularities

Manufacturers program their robots so that singularities don't break the robot. However, in the past this just meant that if one joint was commanded to move too fast, the robot stopped completely with an error message. This was not a very elegant solution.
These days, many robot manufacturers are improving their singularity avoidance. When the wrist joint was commanded "to infinity", this caused the software to reduce the velocity of the tip. The robot slowed down when it reached the middle of the line. When it passed the singularity, it was able to continue doing the rest of the line at the correct velocity. The paint job still would have been ruined, but the robot nevertheless functions correctly and doesn't get stuck.

How Programmers Avoid Singularities

Singularity avoidance has been a developing topic for many years. Various solutions have been proposed and some are starting to make their way into industrial robots. For an introduction to the basics, the ETS Control and Robotics Lab cites a good academic paper which explains the mathematics behind robot singularities and gives examples using an industrial robot.
The more axes that a robot has, the more possibilities for singularities. This is because there are more axes which can line up with each other.

How Technicians Avoid Singularities

Robot technicians have come up with many ingenious ways to avoid singularities over the years. Singularities usually occur when the robot's links are lined up straight and/or when a joint approaches zero degrees. As a result, technicians started to add small angles to the tooling to reduce the chance that the robot moves into a singularity.
This technique is still a good way to avoid singularities. Mounting a spray painting gun at a very slight angle (5-15 degrees) can sometimes ensure that a robot avoids singularities completely. Not always, but it's a cheap solution and easy to try.
Finally, another good technique is to move the task into a part of the workspace where there are no singularities. This is not always possible, but can be very effective.

What is the difference between Robotics and Mechatronics? Also, how does Mechanical and Automation Engineering differ from Mechanical Engineering?

A. Mechatronics
The word mechatronics was invented by the Japanese engineer Ko Kikuchi in 1969. It is a combination of the terms 'mechanical' ("mecha" for mechanisms, i.e., machines that 'move') and 'electronics'. The word reflects the basic nature of this field, to integrate electrical and mechanical systems in a single device. Mechatronics is said to be the junction where concepts from mechanical engineering, electrical engineering, and computer science are merged to design, build and operate products.
The leading scholarly publication on mechatronics is IEEE/ASME Transactions on Mechatronics.
A1. Definitions of Mechatronics
Here are several definitions of mechatronics:
(1) The incorporation of electronics into mechanisms
(2) The integration of mechanical engineering with electronics and intelligent computer control
(3) The use of a synergistic integration of mechanics, electronics, and computer technology to produce enhanced products or systems
(4) The application of complex decision making to the operation of physical systems
(5) The addition of intelligence to a mechanical design or replacing mechanical designs with an intelligent electronic solution
(6) The synergistic combination of mechanical engineering, electronic engineering, and software engineering
[Note: some of these definitions use derivatives of
Synergy, which is observed when "two or more discrete influences or agents acting together create an effect greater than that predicted by knowing only the separate effects of the individual agents. Often the prediction is the sum of the effects each influence is able to create independently."]
A2. Mechatronics and Robotics
A robot is a good example of a mechatronic system. Most robots integrate software, electronics, and mechanical designs in a synergistic manner (meaning that the separate parts act together in such a way that the combined effect is stronger than the sum of the separate effects of each one of the components). Other examples of mechatronics are the digital thermostat and the anti-lock brake system. Both were originally designed as mechanical systems and have been improved later by their integration with electronic controls and digital computing elements.
Robotics is considered a subset of mechatronics, since almost all robots are mechatronic but not all mechatronic systems are robots. Many classes on mechatronics in university curricula include the design and construction of robots or robotic elements as examples. Some mechatronics programs and mechatronics courses are essentially all about robotics.
A3. Mechatronics in academia
In spite of earlier projections that estimated large growth in the number of engineering departments labeled formally Mechatronics Engineering, the actual number of such programs continues to be small. Most of the academic activity in mechatronics occurs in departments of mechanical, electrical, and computer engineering.
B. Mechanical and Automation Engineering
Programs labeled Mechanical and Automation Engineering are more popular in Chinese speaking regions than elsewhere
Like Mechatronics Engineering, the combination Mechanical and Automation Engineering is an example of an inter-disciplinary field that integrates mechanical systems with electronics, control, and computer technologies. In Mechanical and Automation Engineering, there is, in addition to mechanical system design and analysis, a focus on process control, networking, and computer interface and software. Some examples of courses in Mechanical and Automation Engineering are mechanics and materials, thermal fluids, dynamics and control, electronics, robotics, design and manufacturing.

How Robotic Cell Entry Works

The use of industrial robots is becoming more prevalent every year. According to the Robotic Industry Association, 34,606 robots were added to facilities across North America in 2016. With these new robots being added to facilities, it is important to keep safety standards and easy to manage procedures at the forefront when designing robot systems. As a robotic integrator, our job is building robot systems that meet and exceed safety standards. This is accomplished through consistency in developing and using proven safety features.

Safety Fencing for Robot Cells

A safety fence around the robot is used to ensure that operators are protected from coming into contact with the robot while it is moving. The fencing must surround any area the robot can reach and be at a height of at least 5 feet from the walking surface. The operator, at times though, must enter the robot cell for maintenance or other production needs. So all safety fences have to have at least one entry gate.

Entry Gates

Entry gates pose a problem because they allow access to the area where the robot is moving. So every entry to the cell must contain an access controls system, such as an safety interlock switch. A safety interlock switch tells the robot that an operator is entering and signals the robot to stop moving. The entry gates we install on robot cells at Motion Controls Robotics consist of a locking gate switch and a yellow, “Request Access” push button. They feature a locking solenoid and an internal release to prevent an operator from becoming trapped inside the robot cell. This type of switch is both TUV certified and RIA compliant.

How the Safety Interlock Switch on the Gate Works

Below are the steps the operator must take to enter and then leave the robot cell
interlock switch

Operator pushes the yellow, “Request Access” push button
Push button begins to flash while the robot comes to a safe stopping point
Push button stops flashing, remaining lit, as the operator hears the gate switch solenoid release unlocking the gate latch
It’s now safe for the operator to enter
Operator uses the handle on the gate to open the door and enter the cell (If required, the gate handle has a lock-out clasp)
Operator finishes their task inside the cell
Verifying that no one else is inside the robot cell, the operator exits closing the gate fully
Operator presses the “Request Access” push button again – the solenoid locks into place
Robot smoothly starts from the point at which it stopped when the operator first pushed the “Request Access” push button

Watch video to see this process in action

Why is having an safety interlock switch setup important?
The entry gate setup that Motion Controls Robotics uses serves two purposes.

Keeping the operators protected and safe – The way our gate entrance procedure works provides a safe and functional way of entering the robot cell. The process described above predicts issues that could occur and keeps the operator safe when entering the cell.
Making sure that stop time for the robot is minimized – By using a locking gate switch with the “Request Access” push button it allows the operator to stop the system at a controlled stopping point to avoid resetting delays and costing valuable time. By doing this we can avoid interrupting the robot’s cycle and allow the operator to enter and exit the protected area safely. The operator should always use this sequence and never try to just open the door during normal operation.

Benefits of Interlock Switches

Configurable to fit our customer’s specific needs
Durable, one piece metal case
Configuration can include an E-Stop
Can be hard-wired to a safety relay or controlled with AS-I Safe Fieldbus
Quick connect cables

If Motion Controls Robotics designs and integrates your robotic system, you can be assured that we are using safety interlock switches that can exceed your safety needs and keep your operators safe.

XXX . XXX Choosing a Motor: DC, Stepper, Or Servo

How to choose a motor for your robot

Electric motors are used to “actuate” something in your robot: its wheels, legs, tracks, arms, fingers, sensor turrets, or weapon systems. There are literally dozens of types of electric motors (and many more if you count gasoline and other fueled engines), but for amateur robotics, the choice comes down to these three:

In a continuous DC motor, application of power causes the shaft to rotate continually. The shaft stops only when the power is removed, of if the motor is stalled because it can no longer drive the load attached to it.
In a stepping motor, applying power causes the shaft to rotate a few degrees, then stop. Continuous rotation of the shaft requires that the power be pulsed to the motor. As with continuous DC motors, there are sub-types of stepping motors. Permanent magnet steppers are the ones you’ll likely encounter, and they are also the easiest to use.
A special “subset” of continuous motors is the servo motor, which in typical cases combines a continuous DC motor with a “feedback loop” to ensure accurate positioning. There are many, many types of servo motors; a common form is the kind used in model and hobby radio-controlled cars and planes.

With three common motor types for amateur robots to pick from — DC, stepper, and servo — it can be hard to know which one is best. The answer is not simple, because each motor type has its own pros and cons.

Motor Type	Pros	Cons
Continuous DC	Wide selection available, both new and used.- Easy to control via computer with relays or electronic switches. With gearbox, larger DC motors can power a 200 pound robot.	Requires gear reduction to provide torques needed for most robotic applications. Poor standards in sizing and mounting arrangements.
Stepper	Does not require gear reduction to power at low speeds. Low cost when purchased on the surplus market. Dynamic braking effect achieved by leaving coils of stepper motor energized (motor will not turn, but will lock in place).	Poor performance under varying loads. Not great for robot locomotion over uneven surfaces. Consumes high current. Needs special driving circuit to provide stepping rotation.
R/C servo*	Least expensive non-surplus source for gear motors. Can be used for precise angular control, or for continuous rotation (the latter requires modification). Available in several standard sizes, with standard mounting holes.	Requires modification for continuous rotation. Requires special driving circuit. Though more powerful servos are available, practical weight limit for powering a robot is about 10 pounds.

* The discussion is limited here to radio control (R/C) servo motors; there are other types of servo motors, but most are mondo expensive.
Bear in mind that all motors are available in different sizes.

Small motors are engineered for applications where compactness is valued over torque. While there are small high-torque motors, these tend to be expensive because they use rare earth magnets, high efficiency bearings, and other features that add to their cost.
Large motors may produce more torque, but also require higher currents. High current motors require larger capacity batteries, and bigger control circuits that won’t overheat and burn out under the load. Therefore, match the size of the motor with the rest of the robot. Don’t overload a small robot with a large motor when big size isn’t important.
When decided on the size of the motor, compare available torque after any gear reduction. Gear reduction always increases torque. The increase in torque is proportional to the amount of gear reduction: if the reduction is 3:1, the torque is increased by about three times (but not quite, because of frictional losses).

XXX . XXX 4%zero Industrial Robots and Robot System Safety

I. Introduction

Industrial robots are programmable multifunctional mechanical devices designed to move material, parts, tools, or specialized devices through variable programmed motions to perform a variety of tasks. An industrial robot system includes not only industrial robots but also any devices and/or sensors required for the robot to perform its tasks as well as sequencing or monitoring communication interfaces.
Robots are generally used to perform unsafe, hazardous, highly repetitive, and unpleasant tasks. They have many different functions such as material handling, assembly, arc welding, resistance welding, machine tool load and unload functions, painting, spraying, etc. Most robots are set up for an operation by the teach-and-repeat technique. In this mode, a trained operator (programmer) typically uses a portable control device (a teach pendant) to teach a robot its task manually. Robot speeds during these programming sessions are slow.
This instruction includes safety considerations necessary to operate the robot properly and use it automatically in conjunction with other peripheral equipment. This instruction applies to fixed industrial robots and robot systems only.

Accidents: Past Studies
1. Studies in Sweden and Japan indicate that many robot accidents do not occur under normal operating conditions but, instead during programming, program touch-up or refinement, maintenance, repair, testing, setup, or adjustment. During many of these operations the operator, programmer, or corrective maintenance worker may temporarily be within the robot's working envelope where unintended operations could result in injuries.
2. Typical accidents have included the following:
  - A robot's arm functioned erratically during a programming sequence and struck the operator.
  - A materials handling robot operator entered a robot's work envelope during operations and was pinned between the back end of the robot and a safety pole.
  - A fellow employee accidentally tripped the power switch while a maintenance worker was servicing an assembly robot. The robot's arm struck the maintenance worker's hand.
Robot Safeguarding
1. The proper selection of an effective robotic safeguarding system should be based upon a hazard analysis of the robot system's use, programming, and maintenance operations. Among the factors to be considered are the tasks a robot will be programmed to perform, start-up and command or programming procedures, environmental conditions, location and installation requirements, possible human errors, scheduled and unscheduled maintenance, possible robot and system malfunctions, normal mode of operation, and all personnel functions and duties.
2. An effective safeguarding system protects not only operators but also engineers, programmers, maintenance personnel, and any others who work on or with robot systems and could be exposed to hazards associated with a robot's operation. A combination of safeguarding methods may be used. Redundancy and backup systems are especially recommended, particularly if a robot or robot system is operating in hazardous conditions or handling hazardous materials. The safeguarding devices employed should not themselves constitute or act as a hazard or curtail necessary vision or viewing by attending human operators.

II. Types and Classification of Robots

Industrial robots are available commercially in a wide range of sizes, shapes, and configurations. They are designed and fabricated with different design configurations and a different number of axes or degrees of freedom. These factors of a robot's design influence its working envelope (the volume of working or reaching space). Diagrams of the different robot design configurations are shown in Figure IV: 4-1.

Figure IV:4-1. Robot Arm Design Configurations

Servo and Nonservo
All industrial robots are either servo or nonservo controlled. Servo robots are controlled through the use of sensors that continually monitor the robot's axes and associated components for position and velocity. This feedback is compared to pretaught information which has been programmed and stored in the robot's memory. Nonservo robots do not have the feedback capability, and their axes are controlled through a system of mechanical stops and limit switches.
Type of Path Generated. Industrial robots can be programmed from a distance to perform their required and preprogrammed operations with different types of paths generated through different control techniques. The three different types of paths generated are Point-to-Point Path, Controlled Path, and Continuous Path.
1. Point-to-Point Path. Robots programmed and controlled in this manner are programmed to move from one discrete point to another within the robot's working envelope. In the automatic mode of operation, the exact path taken by the robot will vary slightly due to variations in velocity, joint geometries, and point spatial locations. This difference in paths is difficult to predict and therefore can create a potential safety hazard to personnel and equipment.
2. Controlled Path. The path or mode of movement ensures that the end of the robot's arm will follow a predictable (controlled) path and orientation as the robot travels from point to point. The coordinate transformations required for this hardware management are calculated by the robot's control system computer. Observations that result from this type of programming are less likely to present a hazard to personnel and equipment.
3. Continuous Path. A robot whose path is controlled by storing a large number or close succession of spatial points in memory during a teaching sequence is a continuous path controlled robot. During this time, and while the robot is being moved, the coordinate points in space of each axis are continually monitored on a fixed time base, e.g., 60 or more times per second, and placed into the control system's computer memory. When the robot is placed in the automatic mode of operation, the program is replayed from memory and a duplicate path is generated.
Robot Components. Industrial robots have four major components: the mechanical unit, power source, control system, and tooling (Figure IV: 4-2).
1. Mechanical Unit. The robot's manipulative arm is the mechanical unit. This mechanical unit is also comprised of a fabricated structural frame with provisions for supporting mechanical linkage and joints, guides, actuators (linear or rotary), control valves, and sensors. The physical dimensions, design, and weight-carrying ability depend on application requirements.
  Figure IV:4-2. Industrial Robots: Major Components
2. Power Sources
  1. Energy is provided to various robot actuators and their controllers as pneumatic, hydraulic, or electrical power. The robot's drives are usually mechanical combinations powered by these types of energy, and the selection is usually based upon application requirements. For example, pneumatic power (low-pressure air) is used generally for low weight carrying robots.
  2. Hydraulic power transmission (high-pressure oil) is usually used for medium to high force or weight applications, or where smoother motion control can be achieved than with pneumatics. Consideration should be given to potential hazards of fires from leaks if petroleum-based oils are used.
  3. Electrically powered robots are the most prevalent in industry. Either AC or DC electrical power is used to supply energy to electromechanical motor-driven actuating mechanisms and their respective control systems. Motion control is much better, and in an emergency an electrically powered robot can be stopped or powered down more safely and faster than those with either pneumatic or hydraulic power.
Control Systems
1. Either auxiliary computers or embedded microprocessors are used for practically all control of industrial robots today. These perform all of the required computational functions as well as interface with and control associated sensors, grippers, tooling, and other associated peripheral equipment. The control system performs the necessary sequencing and memory functions for on-line sensing, branching, and integration of other equipment. Programming of the controllers can be done on-line or at remote off-line control stations with electronic data transfer of programs by cassette, floppy disc, or telephone modem.
2. Self-diagnostic capability for troubleshooting and maintenance greatly reduces robot system downtime. Some robot controllers have sufficient capacity, in terms of computational ability, memory capacity, and input-output capability to serve also as system controllers and handle many other machines and processes. Programming of robot controllers and systems has not been standardized by the robotics industry; therefore, the manufacturers use their own proprietary programming languages which require special training of personnel.
Robot Programming By Teaching Methods. A program consists of individual command steps which state either the position or function to be performed, along with other informational data such as speed, dwell or delay times, sample input device, activate output device, execute, etc.
When establishing a robot program, it is necessary to establish a physical or geometrical relationship between the robot and other equipment or work to be serviced by the robot. To establish these coordinate points precisely within the robot's working envelope, it is necessary to control the robot manually and physically teach the coordinate points. To do this as well as determine other functional programming information, three different teaching or programming techniques are used: lead-through, walk-through, and off-line.
1. Lead-Through Programming or Teaching. This method of teaching uses a proprietary teach pendant (the robot's control is placed in a "teach" mode), which allows trained personnel physically to lead the robot through the desired sequence of events by activating the appropriate pendant button or switch. Position data and functional information are "taught" to the robot, and a new program is written (Figure IV:4-3). The teach pendant can be the sole source by which a program is established, or it may be used in conjunction with an additional programming console and/or the robot's controller. When using this technique of teaching or programming, the person performing the teach function can be within the robot's working envelope, with operational safeguarding devices deactivated or inoperative.
  
  Figure IV:4-3. Robot Lead-Through Programming or Teaching
2. Walk-Through Programming or Teaching. A person doing the teaching has physical contact with the robot arm and actually gains control and walks the robot's arm through the desired positions within the working envelope (Figure IV:4-4).
  
  Figure IV:4-4. Walk-Through Programming or Teaching
  
  During this time, the robot's controller is scanning and storing coordinate values on a fixed time basis. When the robot is later placed in the automatic mode of operation, these values and other functional information are replayed and the program run as it was taught. With the walk-through method of programming, the person doing the teaching is in a potentially hazardous position because the operational safeguarding devices are deactivated or inoperative.
  Off-Line Programming. The programming establishing the required sequence of functional and required positional steps is written on a remote computer console (Figure IV:4-5). Since the console is distant from the robot and its controller, the written program has to be transferred to the robot's controller and precise positional data established to achieve the actual coordinate information for the robot and other equipment. The program can be transferred directly or by cassette or floppy discs. After the program has been completely transferred to the robot's controller, either the lead-through or walk-through technique can be used for obtaining actual positional coordinate information for the robot's axes.
  
  Figure IV:4-5. Off-Line Programming or Teaching
  
  When programming robots with any of the three techniques discussed above, it is generally required that the program be verified and slight modifications in positional information made. This procedure is called program touch-up and is normally carried out in the teach mode of operation. The teacher manually leads or walks the robot through the programmed steps. Again, there are potential hazards if safeguarding devices are deactivated or inoperative.
3. Degrees of Freedom. Regardless of the configuration of a robot, movement along each axis will result in either a rotational or a translational movement. The number of axes of movement (degrees of freedom) and their arrangement, along with their sequence of operation and structure, will permit movement of the robot to any point within its envelope. Robots have three arm movements (up-down, in-out, side-to-side). In addition, they can have as many as three additional wrist movements on the end of the robot's arm: yaw (side to side), pitch (up and down), and rotational (clockwise and counterclockwise).

III. Hazards

The operational characteristics of robots can be significantly different from other machines and equipment. Robots are capable of high-energy (fast or powerful) movements through a large volume of space even beyond the base dimensions of the robot (see Figure IV:4-6). The pattern and initiation of movement of the robot is predictable if the item being "worked" and the environment are held constant. Any change to the object being worked (i.e., a physical model change) or the environment can affect the programmed movements.

Figure IV:4-6. A Robot's Work Envelope

Some maintenance and programming personnel may be required to be within the restricted envelope while power is available to actuators. The restricted envelope of the robot can overlap a portion of the restricted envelope of other robots or work zones of other industrial machines and related equipment. Thus, a worker can be hit by one robot while working on another, trapped between them or peripheral equipment, or hit by flying objects released by the gripper.
A robot with two or more resident programs can find the current operating program erroneously calling another existing program with different operating parameters such as velocity, acceleration, or deceleration, or position within the robot's restricted envelope. The occurrence of this might not be predictable by maintenance or programming personnel working with the robot. A component malfunction could also cause an unpredictable movement and/or robot arm velocity.
Additional hazards can also result from the malfunction of, or errors in, interfacing or programming of other process or peripheral equipment. The operating changes with the process being performed or the breakdown of conveyors, clamping mechanisms, or process sensors could cause the robot to react in a different manner.

Types of Accidents. Robotic incidents can be grouped into four categories: a robotic arm or controlled tool causes the accident, places an individual in a risk circumstance, an accessory of the robot's mechanical parts fails, or the power supplies to the robot are uncontrolled.
1. Impact or Collision Accidents. Unpredicted movements, component malfunctions, or unpredicted program changes related to the robot's arm or peripheral equipment can result in contact accidents.
2. Crushing and Trapping Accidents. A worker's limb or other body part can be trapped between a robot's arm and other peripheral equipment, or the individual may be physically driven into and crushed by other peripheral equipment.
3. Mechanical Part Accidents. The breakdown of the robot's drive components, tooling or end-effector, peripheral equipment, or its power source is a mechanical accident. The release of parts, failure of gripper mechanism, or the failure of end-effector power tools (e.g., grinding wheels, buffing wheels, deburring tools, power screwdrivers, and nut runners) are a few types of mechanical failures.
4. Other Accidents. Other accidents can result from working with robots. Equipment that supplies robot power and control represents potential electrical and pressurized fluid hazards. Ruptured hydraulic lines could create dangerous high-pressure cutting streams or whipping hose hazards. Environmental accidents from arc flash, metal spatter, dust, electromagnetic, or radio-frequency interference can also occur. In addition, equipment and power cables on the floor present tripping hazards.
Sources of Hazards. The expected hazards of machine to humans can be expected with several additional variations, as follows.
1. Human Errors. Inherent prior programming, interfacing activated peripheral equipment, or connecting live input-output sensors to the microprocessor or a peripheral can cause dangerous, unpredicted movement or action by the robot from human error. The incorrect activation of the "teach pendant" or control panel is a frequent human error. The greatest problem, however, is over familiarity with the robot's redundant motions so that an individual places himself in a hazardous position while programming the robot or performing maintenance on it.
2. Control Errors. Intrinsic faults within the control system of the robot, errors in software, electromagnetic interference, and radio frequency interference are control errors. In addition, these errors can occur due to faults in the hydraulic, pneumatic, or electrical subcontrols associated with the robot or robot system.
3. Unauthorized Access. Entry into a robot's safeguarded area is hazardous because the person involved may not be familiar with the safeguards in place or their activation status.
4. Mechanical Failures. Operating programs may not account for cumulative mechanical part failure, and faulty or unexpected operation may occur.
5. Environmental Sources. Electromagnetic or radio-frequency interference (transient signals) should be considered to exert an undesirable influence on robotic operation and increase the potential for injury to any person working in the area. Solutions to environmental hazards should be documented prior to equipment start-up.
6. Power Systems. Pneumatic, hydraulic, or electrical power sources that have malfunctioning control or transmission elements in the robot power system can disrupt electrical signals to the control and/or power-supply lines. Fire risks are increased by electrical overloads or by use of flammable hydraulic oil. Electrical shock and release of stored energy from accumulating devices also can be hazardous to personnel.
7. Improper Installation. The design, requirements, and layout of equipment, utilities, and facilities of a robot or robot system, if inadequately done, can lead to inherent hazards.

Investigation Guidelines

Manufactured, Remanufactured, and Rebuilt Robots
1. All robots should meet minimum design requirements to ensure safe operation by the user. Consideration needs to be given to a number of factors in designing and building the robots to industry standards. If older or obsolete robots are rebuilt or remanufactured, they should be upgraded to conform to current industry standards.
2. Every robot should be designed, manufactured, remanufactured, or rebuilt with safe design and manufacturing considerations. Improper design and manufacture can result in hazards to personnel if minimum industry standards are not conformed to on mechanical components, controls, methods of operation, and other required information necessary to insure safe and proper operating procedures. To ensure that robots are designed, manufactured, remanufactured, and rebuilt to ensure safe operation, it is recommended that they comply with Section 4 of the ANSI/RIA R15.06-1992 standard for Manufacturing, Remanufacture, and Rebuild of Robots.
Installation
1. A robot or robot system should be installed by the users in accordance with the manufacturer's recommendations and in conformance to acceptable industry standards. Temporary safeguarding devices and practices should be used to minimize the hazards associated with the installation of new equipment. The facilities, peripheral equipment, and operating conditions which should be considered are:
  - Installation specifications;
  - Physical facilities;
  - Electrical facilities;
  - Action of peripheral equipment integrated with the robot;
  - Identification requirements;
  - Control and emergency stop requirements; and
  - Special robot operating procedures or conditions.
2. To ensure safe operating practices and safe installation of robots and robot systems, it is recommended that the minimum requirements of Section 5 of the ANSI/RIA R15.06-1992, Installation of Robots and Robot Systems be followed. In addition, OSHA's Lockout/Tagout standards (29 CFR 1910.147 and 1910.333) must be followed for servicing and maintenance.

For the planning stage, installation, and subsequent operation of a robot or robot system, one should consider the following.

Risk Assessment. At each stage of development of the robot and robot system a risk assessment should be performed. There are different system and personnel safeguarding requirements at each stage. The appropriate level of safeguarding determined by the risk assessment should be applied. In addition, the risk assessments for each stage of development should be documented for future reference.
Safeguarding Devices. Personnel should be safeguarded from hazards associated with the restricted envelope (space) through the use of one or more safeguarding devices:
- Mechanical limiting devices;
- Nonmechanical limiting devices;
- Presence-sensing safeguarding devices;
- Fixed barriers (which prevent contact with moving parts); and
- Interlocked barrier guards.
Awareness Devices. Typical awareness devices include chain or rope barriers with supporting stanchions or flashing lights, signs, whistles, and horns. They are usually used in conjunction with other safeguarding devices.
Safeguarding the Teacher. Special consideration must be given to the teacher or person who is programming the robot. During the teach mode of operation, the person performing the teaching has control of the robot and associated equipment and should be familiar with the operations to be programmed, system interfacing, and control functions of the robot and other equipment. When systems are large and complex, it can be easy to activate improper functions or sequence functions improperly. Since the person doing the training can be within the robot's restricted envelope, such mistakes can result in accidents. Mistakes in programming can result in unintended movement or actions with similar results. For this reason, a restricted speed of 250 mm/§ or 10 in/§ should be placed on any part of the robot during training to minimize potential injuries to teaching personnel.
Several other safeguards are suggested in the ANSI/RIA R15.06-1992 standard to reduce the hazards associated with teaching a robotic system.
Operator Safeguards. The system operator should be protected from all hazards during operations performed by the robot. When the robot is operating automatically, all safeguarding devices should be activated, and at no time should any part of the operator's body be within the robot's safeguarded area.
For additional operator safeguarding suggestions, see the ANSI/RIA R15.06-1992 standard, Section 6.6.
Attended Continuous Operation. When a person is permitted to be in or near the robots restricted envelope to evaluate or check the robots motion or other operations, all continuous operation safeguards must be in force. During this operation, the robot should be at slow speed, and the operator would have the robot in the teach mode and be fully in control of all operations.
Other safeguarding requirements are suggested in the ANSI/RIA R15.06-1992 standard, Section 6.7.
Maintenance and Repair Personnel. Safeguarding maintenance and repair personnel is very difficult because their job functions are so varied. Troubleshooting faults or problems with the robot, controller, tooling, or other associated equipment is just part of their job. Program touchup is another of their jobs as is scheduled maintenance, and adjustments of tooling, gages, recalibration, and many other types of functions.
While maintenance and repair is being performed, the robot should be placed in the manual or teach mode, and the maintenance personnel perform their work within the safeguarded area and within the robots restricted envelope. Additional hazards are present during this mode of operation because the robot system safeguards are not operative.
To protect maintenance and repair personnel, safeguarding techniques and procedures as stated in the ANSI/RIA R15.06-1992 standard, Section 6.8, are recommended.
Maintenance. Maintenance should occur during the regular and periodic inspection program for a robot or robot system. An inspection program should include, but not be limited to, the recommendations of the robot manufacturer and manufacturer of other associated robot system equipment such as conveyor mechanisms, parts feeders, tooling, gages, sensors, and the like.
These recommended inspection and maintenance programs are essential for minimizing the hazards from component malfunction, breakage, and unpredicted movements or actions by the robot or other system equipment. To ensure proper maintenance, it is recommended that periodic maintenance and inspections be documented along with the identity of personnel performing these tasks.
Safety Training. Personnel who program, operate, maintain, or repair robots or robot systems should receive adequate safety training, and they should be able to demonstrate their competence to perform their jobs safely. Employers can refer to OSHA's publication 2254 (Revised), "Training Requirements in OSHA Standards and Training Guidelines."
General Requirements. To ensure minimum safe operating practices and safeguards for robots and robot systems covered by this instruction, the following sections of the ANSI/RIA R15.06-1992 must also be considered:
- Section 6 - Safeguarding Personnel;
- Section 7 - Maintenance of Robots and Robot Systems;
- Section 8 - Testing and Start-up of Robots and Robot Systems; and
- Section 9 - Safety Training of Personnel.
Robots or robotic systems must comply with the following regulations: Occupational Safety and Health Administration, OSHA 29 CFR 1910.333, Selection and Use of Work Practices, and OSHA 29 CFR 1910.147, The Control of Hazardous Energy (Lockout/Tagout).

A____Z robotics

Actuator: A power mechanism used to effect motion of the robot; a device that converts electrical, hydraulic, or pneumatic energy into robot motion.
Application Program: The set of instructions that defines the specific intended tasks of robots and robot systems. This program may be originated and modified by the robot user.
Attended Continuous Operation: The time when robots are performing (production) tasks at a speed no greater than slow speed through attended program execution.
Attended Program Verification: The time when a person within the restricted envelope (space) verifies the robot's programmed tasks at programmed speed.
Automatic Mode: The robot state in which automatic operation can be initiated.
Automatic Operation: The time during which robots are performing programmed tasks through unattended program execution.
Awareness Barrier: Physical and/or visual means that warns a person of an approaching or present hazard.
Awareness Signal: A device that warns a person of an approaching or present hazard by means of audible sound or visible light.
Axis: The line about which a rotating body (such as a tool) turns.
Barrier: A physical means of separating persons from the restricted envelope (space).
Control Device: Any piece of control hardware providing a means for human intervention in the control of a robot or robot system, such as an emergency-stop button, a start button, or a selector switch.
Control Program: The inherent set of control instructions that defines the capabilities, actions and responses of the robot system. This program is usually not intended to be modified by the user.
Coordinated Straight Line Motion: Control wherein the axes of the robot arrive at their respective end points simultaneously, giving a smooth appearance to the motion. Control wherein the motions of the axes are such that the Tool Center Point (TCP) moves along a prespecified type of path (line, circle, etc.)
Device: Any piece of control hardware such as an emergency-stop button, selector switch, control pendant, relay, solenoid valve, sensor, etc.
Drive Power: The energy source or sources for the robot actuators.
Emergency Stop: The operation of a circuit using hardware-based components that overrides all other robot controls, removes drive power from the robot actuators, and causes all moving parts to stop.
Enabling Device: A manually operated device that permits motion when continuously activated. Releasing the device stops robot motion and motion of associated equipment that may present a hazard.
End-effector: An accessory device or tool specifically designed for attachment to the robot wrist or tool mounting plate to enable the robot to perform its intended task. (Examples may include gripper, spot-weld gun, arc-weld gun, spray- paint gun, or any other application tools.)
Energy Source: Any electrical, mechanical, hydraulic, pneumatic, chemical, thermal, or other source.
Envelope (Space), Maximum: The volume of space encompassing the maximum designed movements of all robot parts including the end-effector, workpiece, and attachments.
Restricted Envelope (Space): That portion of the maximum envelope to which a robot is restricted by limiting devices. The maximum distance that the robot can travel after the limiting device is actuated defines the boundaries of the restricted envelope (space) of the robot.
Note:: The safeguarding interlocking logic and robot program may redefine the restricted envelope (space) as the robot performs its application program. (See Appendix D of the ANSI/RIA R15.06-1992 Specification).
Operating Envelope (Space): That portion of the restricted envelope (space) that is actually used by the robot while performing its programmed motions.
Hazard: A situation that is likely to cause physical harm.
Hazardous Motion: Any motion that is likely to cause personal physical harm.
Industrial Equipment: Physical apparatus used to perform industrial tasks, such as welders, conveyors, machine tools, fork trucks, turn tables, positioning tables, or robots.
Industrial Robot: A reprogrammable, multifunctional manipulator designed to move material, parts, tools, or specialized devices through variable programmed motions for the performance of a variety of tasks.
Industrial Robot System: A system that includes industrial robots, the end-effectors, and the devices and sensors required for the robots to be taught or programmed, or for the robots to perform the intended automatic operations, as well as the communication interfaces required for interlocking, sequencing, or monitoring the robots.
Interlock: An arrangement whereby the operation of one control or mechanism brings about or prevents the operation of another.
Joint Motion: A method for coordinating the movement of the joints such that all joints arrive at the desired location simultaneously.
Limiting Device: A device that restricts the maximum envelope (space) by stopping or causing to stop all robot motion and is independent of the control program and the application programs.
Maintenance: The act of keeping the robots and robot systems in their proper operating condition.
Mobile Robot: A self-propelled and self-contained robot that is capable of moving over a mechanically unconstrained course.
Muting: The deactivation of a presence-sensing safeguarding device during a portion of the robot cycle.
Operator: The person designated to start, monitor, and stop the intended productive operation of a robot or robot system. An operator may also interface with a robot for productive purposes.
Pendant: Any portable control device, including teach pendants, that permits an operator to control the robot from within the restricted envelope (space) of the robot.
Presence-Sensing Safeguarding Device: A device designed, constructed, and installed to create a sensing field or area to detect an intrusion into the field or area by personnel, robots, or other objects.
Program
Rebuild: To restore the robot to the original specifications of the manufacturer, to the extent possible.
Remanufacture: To upgrade or modify robots to the revised specifications of the manufacturer and applicable industry standards.
Repair: To restore robots and robot systems to operating condition after damage, malfunction, or wear.
Robot Manufacturer: A company or business involved in either the design, fabrication, or sale of robots, robot tooling, robotic peripheral equipment or controls, and associated process ancillary equipment.
Robot System Integrator: A company or business who either directly or through a subcontractor will assume responsibility for the design, fabrication, and integration of the required robot, robotic peripheral equipment, and other required ancillary equipment for a particular robotic application.
Safeguard: A barrier guard, device, or safety procedure designed for the protection of personnel.
Safety Procedure: An instruction designed for the protection of personnel.
Sensor: A device that responds to physical stimuli (such as heat, light, sound, pressure, magnetism, motion, etc.) and transmits the resulting signal or data for providing a measurement, operating a control, or both.
Service: To adjust, repair, maintain, and make fit for use.
Single Point of Control: The ability to operate the robot such that initiation or robot motion from one source of control is possible only from that source and cannot be overridden from another source.
Slow Speed Control: A mode of robot motion control where the velocity of the robot is limited to allow persons sufficient time either to withdraw the hazardous motion or stop the robot.
Start-up: Routine application of drive power to the robot or robot system.
Start-up, Initial: Initial drive power application to the robot or robot system after one of the following events:
Teach: The generation and storage of a series of positional data points effected by moving the robot arm through a path of intended motions.
Teach Mode: The control state that allows the generation and storage of positional data points effected by moving the robot arm through a path of intended motions.
Teacher: A person who provides the robot with a specific set of instructions to perform a task.
Tool Center Point (TCP): The origin of the tool coordinate system.
User: A company, business, or person who uses robots and who contracts, hires, or is responsible for the personnel associated with robot operation.

Service robots are machines that extend human capabilities.
Automatic guided-vehicle systems are advanced material-handling or conveying systems that involve a driverless vehicle which follows a guide-path.
Undersea and space robots include in addition to the manipulator or tool that actually accomplishes a task, the vehicles or platforms that transport the tools to the site. These vehicles are called remotely operated vehicles (ROV's) or autonomous undersea vehicles (AUV's); the feature that distinguishes them is, respectively, the presence or absence of an electronics tether that connects the vehicle and surface control station.
Automatic storage and retrieval systems are storage racks linked through automatically controlled conveyors and an automatic storage and retrieval machine or machines that ride on floor-mounted guide rails and power-driven wheels.
Automatic conveyor and shuttle systems are comprised of various types of conveying systems linked together with various shuttle mechanisms for the prime purpose of conveying materials or parts to prepositioned and predetermined locations automatically.
Tele operators are robotic devices comprised of sensors and actuators for mobility and/or manipulation and are controlled remotely by a human operator.
Mobile robots are freely moving automatic programmable industrial robots.
Prosthetic robots are programmable manipulators or devices for missing human limbs.
Numerically controlled machine tools are operated by a series of coded instructions comprised of numbers, letters of the alphabet, and other symbols. These are translated into pulses of electrical current or other output signals that activate motors and other devices to run the machine.

A Year of Growth

Trick among robot builderss of the Trade

Few things are more satisfying that building your own project from design to implementation. As you gain experience doing so, you find that you start developing a bag of tools and tricks for building things. This month, I would like to share with you some of the things that I have found very useful for building robots.

Connectors

Almost everyone at one point or another has ended up directly wiring one sub-system to another. Usually, a few wires are soldered into place, or wire wrapped between boards. Of course, when you are building and debugging something as complex as a robot, there always ends up being times when you really need to disconnect those sub-systems, and you end up having to unsolder or unwrap a bunch of connections.

The obvious, but often overlooked, solution to this problem is to handle inter-connections using standard connectors between boards. Standard connectors, especially those with interlocking tabs, are extremely useful, time saving, and prevent you from doing something really nasty like wiring up Vcc and GND backwards. I am sure most of us can relate to burning up some critical part by a bonehead mistake like plugging a wire in backwards. Connectors are especially useful if you are publishing your design for others to use. Connectors give a well defined interface between your design and other components. In my opinion, it makes for a more complete project.
There are many types of connectors available. Buying connectors surplus is usually a hit and miss ordeal. Often times, you can't get them in matching pairs. Or, if you can, you usually are stuck with 17pins, when you really only wanted 10. There are times when buying retail parts is worth the expense. This is one of those. The ability to buy matching parts is a nice feature.

Connectors in use on a CPU board.

I would like to expand on a type that many of the SRS members have been using with great success. The connectors are made by Molex/Waldom, are called the K.K. series, and are available from several sources. I usually order from Digikey, but Mouser and Newark also carry these. Looking in the catalog can be a little confusing. It isn't obvious exactly what you need to order from the long list of parts. I will explain what the different parts are, and what you need to order.

Crimp Pin, Terminal Housing, and "Center Header"

The connectors come in three basic parts. "Center Headers" are the pins that you will solder onto your PCB. Terminal Housings are the connector part that attach to the headers. Last but not least are the crimp pins that make the electrical connection.
The metal parts are available in tin or gold plating. I have been using the tin plated parts (which are cheaper) with no problems at all. If you would prefer, you can order the gold ones. Gold is more durable, but is also much more expensive ( over twice as much!) All of the part numbers I will describe are the tin plated versions.

You want to order .100" Center Headers. These will fit the industry standard .100" spacing of most PCB parts. For example, the BotBoard power and communication connectors are all on .100" (or 100 mil) centers. The other option is a .156", which is commonly used for higher power applications. I like to use the 'Straight Friction Lock Headers', which have a locking mechanism that requires a substantial force to disconnect. You can see the friction lock mechanism in the side view picture to the left. Friction Lock Headers also only allow the connector to be attached in one direction. This helps prevent reversing the polarity on your connections. There are also polarizing ribs available on the terminal housings.

As with many parts, connectors are cheaper in quantity. If you plan to tinker over the next couple of years, I would recommend that you consider investing a few bucks on a supply of connectors. Most commonly used in my toolbox are 2pin, 3pin, 4pin, and 6pin connectors. You may have needs for other sizes (they come up to 12 pins), but I find a supply of these sizes works well. I usually purchase 10 of each. The next part of the connector assembly is the terminal housing. For each size of Center Header, there is a matching terminal housing. I typically use the 'Center Crimp Terminal Housing with Locking Ramp and Polarizing Ribs'. This means the locking ramp interconnects with the Center Header to hold it securely, and the polarizing ribs help prevent a misconnection. The Polarizing Rib isn't critical, but I like it.

The final part are the crimp terminals. These crimp onto the ends of the wires, and then snap into place in the terminal housing. You will need one crimp terminal for each pin. I usually get a few extra, because you are bound to break some, or pull a wire out now and then. I usually buy in lots of 100, since the pins are cheaper that way.
Now, for an example from the Digikey catalog. Everything you need for assembling a 4 pin connector is shown below:

Quantity	Digi-key Part #	Description	Price
1	WM4202-ND	4 pin Center Header Tin Plating	.48
1	WM2002-ND	4 pin Terminal Housing with Locking Ramp	.29
10	WM2200-ND	Crimp Terminals for .100" Housings	1.05

By checking out the catalog, you can figure out how to order the rest.
One last thing to consider is the crimping tool. I have a whole bunch of different crimp tools from various sources. I also ended up with the 'real' crimping tool for the above connector parts. If you are planning on sticking with these connectors, I highly recommend getting the $13.75 Waldom hand crimp tool. The crimp terminals fit correctly, and the crimp is always tight and electrically secure. 'Other' crimp tools work, sometimes, but nothing like the original.
Connectors, as with any of the parts we order, can be expensive. However, I justify the expense to myself by understanding that the cost of one blown processor or motor driver can make the connectors worth the trouble. They also save quite a bit of time when building the robot, since taking the sub-systems apart is quite easy. Proper connectors can make the difference between a working project and a not-so-working project.

Switches

It still amazes me to see the number of robots and projects that use the power connector as the on/off switch. I admit that most of my first robots were initialized by trying to plug the battery onto the controller board using a two pin connector. It took a few toasted HC11's to realize the beauty of the power switch.

Slide, Toggle, and Pushbutton switches

Switches come in many styles. Three basic switch styles that are commonly used as power switches are the slide, toggle, and pushbutton. My personal preference is to be able to determine the state of the switch by looking at it. Therefore, I usually try to use toggle switches. You can see the state of a slide switch, but they require either a PCB mount, or a square hole in a panel, which is a pain to deal with. Pushbutton switches also have their uses if you have space constraints, but you can't easily determine is current state just by looking at it.In addition to the power switch, I will often put a small, low power LED on the robot somewhere that also acts as visual verification that the power switch is on. Try to put this on the computer board if possible. Use a relatively high valued resistor if you are concerned with power consumption.

Most toggle switches mount in a small round hole which can be made with drill motor and bit. Your switch should be wired to your power source, so that when the switch is off, all power to the system is shut down. Many parts, especially motor drivers, have a nasty problem where feedback through various ground paths can cause them to engage. The last thing you want is for your motors to turn on at an unexpected time. Switching the power from the positive lead from your power source is a good way to ensure that this doesn't happen.

XXX . XXX 4%zero null Robot Vision

Next time a robot calls you a "feeble human," just ask it to pick out the one tangerine in a pile of assorted fruits by sight alone. Who's feeble now? | Credit: iStock/Thinkstock

You've probably seen -- or maybe even built -- robots that use sensors as a means of gathering information about the environment they're in. These robots can detect objects in their path and route around them (or sometimes plow right through them). But these basic robots aren't "seeing" anything -- they're sensing an obstacle rather than identifying it. As it turns out, teaching robots to see in a way that's similar to what we do naturally is tough.
Let's imagine a quick scenario: You're searching for a particular object amongst a clutter of other stuff. For me, it's nearly always my master remote control for my man-cave entertainment system. But I've accumulated so many whozits and whatsits (not to mention gadgets and gizmos) that it can take me a while to find the remote. Fortunately, I can distinguish between objects by sight pretty efficiently, no matter what orientation they might be in.
That's quite a trick, as it turns out. I can recognize my remote whether it's face up, face down, upside down or partially covered by my latest copy of Ukulele International. But imagine teaching that same skill to a robot. Suddenly this completely natural ability we humans possess becomes a head-scratchingly difficult problem.
Over at MIT, graduate student Jared Glover is exploring a new way to teach robots how to see. Glover's method uses an old statistical approach called the Bingham distribution. Working with former MIT student (and current Google employee) Sanja Popovic, Glover designed an algorithm that helps robots identify objects through a probabilistic approach.
Here's how it works -- first, you have to teach the robot about objects, like my remote control. You build a virtual model of the remote control, like a grid outline. The robot knows the proportions of the remote control, what its edges look like and how parts of it are flat and other parts are curved. Then, you show the robot a scene of clutter (like my coffee table).
The robot starts to look for objects that match the model it has learned. It compares surfaces, edges, corners and other distinguishing features of the model against the objects on the table. If an object matches the model at a high enough degree of certainty, the robot identifies that object as the one you were looking for.
This is different from other models that use high-resolution data imagery and complicated algorithms for robot vision. And the best thing about it is it seems to work! Glover and Popovic's algorithm successfully identified more objects more frequently than the leading methodologies used in the field of robotics right now.
Of course, teaching a robot to see is still a really arduous task. We can't just hold up a representative object -- like my remote control -- and expect the robot to identify all remote controls based off that one example. But every step forward brings us closer to a world where robots can navigate through and interact with environments similar to the way we do.

Robotic Assembly Plant

++++++++++++++++++++++++

GO LOOK IMPORTANTBOOK

Jumat, 09 Februari 2018

electronic locking robotics and How to choose a motor for your robot and robot system safety AMNIMARJESLOW GOVERNMENT 91220017 XI XA PIN PING HUNG CHOP LJBUSAF 2002 x2020 LOCKING CENTRAL ROBOTICS ELECTRONIC 0202