Experimental Validation on Aerial Vehicles of Real-Time Motion Planning with Continuous-Time Q-Learning
Year: 2023
Type: article
Abstract: In this paper, we propose an algorithm and implementation for real-time optimized kinodynamic motion planning for aerial vehicles with unknown dynamics in crowded environments. A random-sampling space-filling tree is used for both planning and rapidly replanning a path through the environment. Then, continuous-time Q-learning is used to approximately solve the resulting finite-horizon optimal control problem online to optimally track the planned path. To facilitate the Q-learning, we propose an actor-critic structure with integral reinforcement learning to approximate the Hamilton-Jacobi-Bellman equation. The critic approximates the Q-function while the actor approximates the control policy. We demonstrate our approach on custom drone hardware in which all planning, learning, and control computations are conducted onboard in real-time.
Source: IFAC-PapersOnLine
Institution: Georgia Institute of Technology
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
Awards: NRI: FND: Robust and Scalable Planning for Agile and Collaborative Robot Teammates in Complex Environments, Collaborative Research: CPS: Small: An Integrated Reactive and Proactive Adversarial Learning for Cyber-Physical-Human Systems, Collaborative Research: CPS: Medium: Wildland Fire Observation, Management, and Evacuation using Intelligent Collaborative Flying and Ground Systems, G6168030749, CAREER: Towards an Intermittent Learning Framework for Smart and Efficient Cyber-Physical Autonomy
OpenAlex ID: W4390017876
