Utilizing Reinforcement Learning to Continuously Improve a Primitive-Based Motion Planner
- Georgia Institute of Technology, Atlanta, GA (United States)
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
We report in this paper describes how the performance of motion primitive-based planning algorithms can be improved using reinforcement learning. Specifically, we describe and evaluate a framework that autonomously improves the performance of a primitive-based motion planner. The improvement process consists of three phases: exploration, extraction, and reward updates. This process can be iterated continuously to provide successive improvement. The exploration step generates new trajectories, and the extraction step identifies new primitives from these trajectories. These primitives are then used to update rewards for continued exploration. This framework required novel shaping rewards, development of a primitive extraction algorithm, and modification of the Hybrid A* algorithm. The framework is tested on a navigation task using a nonlinear F-16 model. The framework autonomously added 91 motion primitives to the primitive library and reduced average path cost by 21.6 seconds, or 35.75% of the original cost. The learned primitives are applied to an obstacle field navigation task, which was not used in training, and reduced path cost by 16.3 seconds, or 24.1%. Additionally, two heuristics for the modified Hybrid A* algorithm are designed to improve effective branching factor.
- Research Organization:
- Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE National Nuclear Security Administration (NNSA); USDOE Laboratory Directed Research and Development (LDRD) Program
- Grant/Contract Number:
- NA0003525
- OSTI ID:
- 1845399
- Report Number(s):
- SAND2022-1518J; 703370
- Journal Information:
- Journal of Aerospace Information Systems, Journal Name: Journal of Aerospace Information Systems Journal Issue: 7 Vol. 19; ISSN 2327-3097
- Publisher:
- American Institute of Aeronautics and Astronautics (AIAA)Copyright Statement
- Country of Publication:
- United States
- Language:
- English
Similar Records
An Approach to Realize Generalized Optimal Motion Primitives Using Physics Informed Neural Networks
Autonomous Navigation and Control of UGVs' in Nuclear Power Plants - 20381