TY - GEN
T1 - Improved roadmap connection via local learning for sampling based planners
AU - Ekenna, Chinwe
AU - Uwacu, Diane
AU - Thomas, Shawna
AU - Amato, Nancy M.
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/12/11
Y1 - 2015/12/11
N2 - Probabilistic Roadmap Methods (PRMs) solve the motion planing problem by constructing a roadmap (or graph) that models the motion space when feasible local motions exist. PRMs and variants contain several phases during roadmap generation i.e., sampling, connection, and query. Some work has been done to apply machine learning to the connection phase to decide which variant to employ, but it uses a global learning approach that is inefficient in heterogeneous situations. We present an algorithm that instead uses local learning: it only considers the performance history in the vicinity of the current connection attempt and uses this information to select good candidates for connection. It thus removes any need to explicitly partition the environment which is burdensome and typically difficult to do. Our results show that our method learns and adapts in heterogeneous environments, including a KUKA youBot with a fixed and mobile base. It finds solution paths faster for single and multi-query scenarios and builds roadmaps with better coverage and connectivity given a fixed amount of time in a wide variety of input problems. In all cases, our method outperforms the previous adaptive connection method and is comparable or better than the best individual method.
AB - Probabilistic Roadmap Methods (PRMs) solve the motion planing problem by constructing a roadmap (or graph) that models the motion space when feasible local motions exist. PRMs and variants contain several phases during roadmap generation i.e., sampling, connection, and query. Some work has been done to apply machine learning to the connection phase to decide which variant to employ, but it uses a global learning approach that is inefficient in heterogeneous situations. We present an algorithm that instead uses local learning: it only considers the performance history in the vicinity of the current connection attempt and uses this information to select good candidates for connection. It thus removes any need to explicitly partition the environment which is burdensome and typically difficult to do. Our results show that our method learns and adapts in heterogeneous environments, including a KUKA youBot with a fixed and mobile base. It finds solution paths faster for single and multi-query scenarios and builds roadmaps with better coverage and connectivity given a fixed amount of time in a wide variety of input problems. In all cases, our method outperforms the previous adaptive connection method and is comparable or better than the best individual method.
UR - http://www.scopus.com/inward/record.url?scp=84958156767&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84958156767&partnerID=8YFLogxK
U2 - 10.1109/IROS.2015.7353825
DO - 10.1109/IROS.2015.7353825
M3 - Conference contribution
AN - SCOPUS:84958156767
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 3227
EP - 3234
BT - IROS Hamburg 2015 - Conference Digest
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2015
Y2 - 28 September 2015 through 2 October 2015
ER -