TY - GEN
T1 - Robust Unmanned Surface Vehicle Navigation with Distributional Reinforcement Learning
AU - Lin, Xi
AU - McConnell, John
AU - Englot, Brendan
N1 - Publisher Copyright:
© 2023 IEEE.
PY - 2023
Y1 - 2023
N2 - Autonomous navigation of Unmanned Surface Vehicles (USV) in marine environments with current flows is challenging, and few prior works have addressed the sensor-based navigation problem in such environments under no prior knowledge of the current flow and obstacles. We propose a Distributional Reinforcement Learning (RL) based local path planner that learns return distributions which capture the uncertainty of action outcomes, and an adaptive algorithm that automatically tunes the level of sensitivity to the risk in the environment. The proposed planner achieves a more stable learning performance and converges to safer policies than a traditional RL based planner. Computational experiments demonstrate that comparing to a traditional RL based planner and classical local planning methods such as Artificial Potential Fields and the Bug Algorithm, the proposed planner is robust against environmental flows, and is able to plan trajectories that are superior in safety, time and energy consumption.
AB - Autonomous navigation of Unmanned Surface Vehicles (USV) in marine environments with current flows is challenging, and few prior works have addressed the sensor-based navigation problem in such environments under no prior knowledge of the current flow and obstacles. We propose a Distributional Reinforcement Learning (RL) based local path planner that learns return distributions which capture the uncertainty of action outcomes, and an adaptive algorithm that automatically tunes the level of sensitivity to the risk in the environment. The proposed planner achieves a more stable learning performance and converges to safer policies than a traditional RL based planner. Computational experiments demonstrate that comparing to a traditional RL based planner and classical local planning methods such as Artificial Potential Fields and the Bug Algorithm, the proposed planner is robust against environmental flows, and is able to plan trajectories that are superior in safety, time and energy consumption.
UR - http://www.scopus.com/inward/record.url?scp=85182526241&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85182526241&partnerID=8YFLogxK
U2 - 10.1109/IROS55552.2023.10342389
DO - 10.1109/IROS55552.2023.10342389
M3 - Conference contribution
AN - SCOPUS:85182526241
T3 - IEEE International Conference on Intelligent Robots and Systems
SP - 6185
EP - 6191
BT - 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2023
T2 - 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2023
Y2 - 1 October 2023 through 5 October 2023
ER -