Name
Abstract | ||
|---|---|---|
The control of light-weight compliant robot arms is cumbersome due to the fact that their Coriolis forces are large, and the forces exerted by the relatively weak actuators may change in time as the result of external (e.g. tempera- ture) influences. We describe and analyse the behaviour of a light-weight robot arm, the SoftArm robot. It is found that the hysteretic force-position relationship of the arm can be explained from its structure. This knowledge is used in the construction of a neural-network-based controller. Experi- ments show that the network is able to control the robot arm accurately after a training session of only a few minutes. feedback algorithms. As is shown in this paper, it is possible to use a standard PID controller in a feedback loop to con- trol the joint values of the robot towards their desired values. The resulting precision, however, is rather poor; the desired trajectory is only coarsely followed (lagging and hysteresis problems), and the error in joint position is up to 10. The algorithms that can be used for controlling industrial non- compliant robots are not usable to control compliant robots due to the complex, highly non-linear dynamics of the latter. It has been shown that neural networks can be well ap- |
Year | DOI | Venue |
|---|---|---|
1996 | 10.1007/s004220050308 | Biological Cybernetics |
Keywords | Field | DocType |
Training Session,Coriolis Force,Compliant Robot | Robot control,Control theory,Robotic arm,Simulation,Control theory,Snake-arm robot,Artificial intelligence,Robot,Mathematics,Robotics,Arm solution,Actuator | Journal |
Volume | Issue | ISSN |
75 | 5 | 0340-1200 |
Citations | PageRank | References |
17 | 2.37 | 2 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| P. Patrick Van Der Smagt | 1 | 274 | 35.19 |
| F. Groen | 2 | 17 | 2.37 |
| K. Schulten | 3 | 17 | 2.37 |