Adaptive path planning: Algorithm and analysis
To address the need for a fast path planner, we present a learning algorithm that improves path planning by using past experience to enhance future performance. The algorithm relies on an existing path planner to provide solutions difficult tasks. From these solutions, an evolving sparse work of useful robot configurations is learned to support faster planning. More generally, the algorithm provides a framework in which a slow but effective planner may be improved both cost-wise and capability-wise by a faster but less effective planner coupled with experience. We analyze algorithm by formalizing the concept of improvability and deriving conditions under which a planner can be improved within the framework. The analysis is based on two stochastic models, one pessimistic (on task complexity), the other randomized (on experience utility). Using these models, we derive quantitative bounds to predict the learning behavior. We use these estimation tools to characterize the situations in which the algorithm is useful and to provide bounds on the training time. In particular, we show how to predict the maximum achievable speedup. Additionally, our analysis techniques are elementary and should be useful for studying other types of probabilistic learning as well.
- Research Organization:
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE, Washington, DC (United States); Institute of Electrical and Electronics Engineers, Inc., New York, NY (United States)
- DOE Contract Number:
- AC04-94AL85000
- OSTI ID:
- 36797
- Report Number(s):
- SAND-95-0241C; CONF-9505193-3; ON: DE95008549
- Resource Relation:
- Conference: 1995 international conference on robotics and automation, Nagoya (Japan), 21-27 May 1995; Other Information: PBD: [1995]
- Country of Publication:
- United States
- Language:
- English
Similar Records
Adaptive path planning: Algorithm and analysis
Improving path planning with learning