Continuous Arvand: Motion Planning with Monte Carlo Random Walks
نویسندگان
چکیده
Sampling-based approaches such as Probabilistic Roadmaps and Rapidly-exploring Random Trees are very popular in motion planning. Monte Carlo Random Walks (MRW) are a quite different sampling method. They were implemented in the Arvand family of planners, which have been successful in classical planning with its discrete state spaces and actions. The work described here develops an MRW approach for domains with continuous state and action spaces, as encountered in motion planning. Several new algorithms based on MRW are introduced, implemented in the Continuous Arvand system, and compared with existing motion planning approaches in the Open Motion Planning Li-
منابع مشابه
Arvand: the Art of Random Walks
Arvand is a stochastic planner that uses Monte Carlo random walks (MRW) planning to balance exploration and exploitation in heuristic search. Herein, we focus on the latest developments of Arvand submitted to IPC’11: smart restarts, the online parameter learning system, and the integration of Arvand and the postprocessing system Aras.
متن کاملMonte-Carlo Exploration for Deterministic Planning
Search methods based on Monte-Carlo simulation have recently led to breakthrough performance improvements in difficult game-playing domains such as Go and General Game Playing. Monte-Carlo Random Walk (MRW) planning applies MonteCarlo ideas to deterministic classical planning. In the forward chaining planner ARVAND, MonteCarlo random walks are used to explore the local neighborhood of a search ...
متن کاملA Theoretical Framework for Studying Random Walk Planning
Random walks are a relatively new component used in several state of the art satisficing planners. Empirical results have been mixed: while the approach clearly outperforms more systematic search methods such as weighted A* on many planning domains, it fails in many others. So far, the explanations for these empirical results have been somewhat ad hoc. This paper proposes a formal framework for...
متن کاملA Local Monte Carlo Tree Search Approach in Deterministic Planning
Much recent work in satisficing planning has aimed at striking a balance between coverage solving as many problems as possible and plan quality. Current planners achieve near perfect coverage on the latest IPC benchmarks. It is therefore natural to investigate their scaling behavior on more difficult instances. Among state of the art planners, LAMA (Richter, Helmert, and Westphal 2008) is able ...
متن کاملBalancing Exploration and Exploitation in Classical Planning
Successful heuristic search planners for satisficing planning like FF or LAMA are usually based on one or more best first search techniques. Recent research has led to planners like Arvand, Roamer or Probe, where novel techniques like Monte-Carlo Random Walks extend the traditional exploitation-focused best first search by an exploration component. The UCT algorithm balances these contradictory...
متن کامل