Safe Deep Reinforcement Learning-Based Controller (SDRLC) for Autonomous Navigation of Planetary Rovers

Jana, RK and Majumder, R and Bharathwaj, KS and Sundaram, S (2024) Safe Deep Reinforcement Learning-Based Controller (SDRLC) for Autonomous Navigation of Planetary Rovers. In: 2024 IEEE Space, Aerospace and Defence Conference, SPACE 2024, 22 July 2024 through 23 July 2024, Bangalore, pp. 799-803.

PDF Saf_Dee_Rei_Lea_Con_SDRLC_for_Aut_Nav_of_Pla_Rov_2024.pdf - Published Version Restricted to Registered users only Download (1MB) | Request a copy

Abstract

Surface exploration and data collection by planetary rovers are challenging due to unknown complex planet terrains. This paper focuses on developing a Deep Reinforcement Learning (DRL)-based controller for rovers to enable safe operation. The necessary control input for safe and efficient vehicle maneuver is derived using the Control Barrier Function (CBF)-based safety protocols. Deep Deterministic Policy Gradient (DDPG) algorithm is used as a DRL framework to find the optimal exploration policies for the rover. Numerical simulations on different vehicle models show the efficacy of the proposed safety method for planetary rovers. © 2024 IEEE.

Item Type:	Conference Paper
Publication:	2024 IEEE Space, Aerospace and Defence Conference, SPACE 2024
Publisher:	Institute of Electrical and Electronics Engineers Inc.
Additional Information:	The copyright for this article belongs to the publishers.
Keywords:	Motion planning; Reinforcement learning; Rovers, Autonomous navigation; Barriers functions; Control barrier function; Control barriers; Data collection; Obstacles avoidance; Planetary rovers; Reinforcement learnings; Surface data; Surface exploration, Deep reinforcement learning
Department/Centre:	Division of Mechanical Sciences > Aerospace Engineering(Formerly Aeronautical Engineering)
Date Deposited:	17 Oct 2024 06:35
Last Modified:	17 Oct 2024 06:35
URI:	http://eprints.iisc.ac.in/id/eprint/86559

Actions (login required)

View Item