DocumentCode :
2572446
Title :
Adaptive path planning for flexible manufacturing
Author :
Chen, Pang C.
Author_Institution :
Sandia Nat. Labs., Albuquerque, NM, USA
fYear :
1994
fDate :
10-12 Oct 1994
Firstpage :
17
Lastpage :
23
Abstract :
Path planning needs to be fast to facilitate real-time robot programming. Unfortunately, current planning techniques are still too slow to be effective, as they often require several minutes, if not hours of computation. To overcome this difficulty, the author presents an adaptive algorithm that uses past experience to speed up future performance. It is a learning algorithm suitable for automating flexible manufacturing in incrementally-changing environments. The algorithm allows the robot to adapt to its environment by having two manipulation schemes. For minor environmental change, the author uses an object-attached experience abstraction scheme to increase the flexibility of the learned experience; for major environmental change, the author uses an on-demand experience repair scheme to retain those experiences that remain valid and useful. Using this algorithm, one can effectively reduce the overall robot planning time by re-using the computation result for one task to plan a path for another
Keywords :
flexible manufacturing systems; industrial robots; path planning; robot programming; adaptive path planning; earned experience; flexible manufacturing; incrementally-changing environments; object-attached experience abstraction scheme; on-demand experience repair scheme; real-time robot programming; Adaptive algorithm; Computer aided manufacturing; Flexible manufacturing systems; Laboratories; Manufacturing automation; Mobile robots; Path planning; Robot programming; Robotics and automation; Technology planning;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Integrated Manufacturing and Automation Technology, 1994., Proceedings of the Fourth International Conference on
Conference_Location :
Troy, NY
Print_ISBN :
0-8186-6510-6
Type :
conf
DOI :
10.1109/CIMAT.1994.389099
Filename :
389099
Link To Document :
بازگشت