Abstract | ||
---|---|---|
We consider the problem of planning motions in observations space, based on learned models of the dynamics that associate to each action a diffeomorphism of the observations domain. For an arbitrary set of diffeomorphisms, this problem must be formulated as a generic search problem. We adapt established algorithms of the graph search family. In this scenario, node expansion is very costly, as each node in the graph is associated to an uncertain diffeomorphism and corresponding predicted observations. We describe several improvements that ameliorate performance: the introduction of better image similarities to use as heuristics; a method to reduce the number of expanded nodes by preliminarily identifying redundant plans; and a method to pre-compute composite actions that make the search efficient in all directions. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1109/ICRA.2013.6630973 | 2013 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) |
Keywords | Field | DocType |
graph theory,mobile robots,planning,uncertainty,visual servoing,learning artificial intelligence,path planning,motion planning,feature extraction | Motion planning,Graph theory,Any-angle path planning,Mathematical optimization,Feature extraction,Fringe search,Heuristics,Search problem,Mathematics,Diffeomorphism | Conference |
Volume | Issue | ISSN |
2013 | 1 | 1050-4729 |
Citations | PageRank | References |
5 | 0.42 | 6 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Andrea Censi | 1 | 551 | 39.63 |
Adam Nilsson | 2 | 5 | 0.42 |
Richard M. Murray | 3 | 12322 | 1223.70 |