iTD3-CLN: learn to navigate in dynamic scene through Deep Reinforcement Learning

• Main Authors: Jiang, Haoge, Esfahani, Mahdi Abolfazli, Wu, Keyu, Wan, Kong-wah, Heng, Kuan-kian, Wang, Han, Jiang, Xudong
• Other Authors: School of Electrical and Electronic Engineering
• Format: Article
• Language: English
• Published: 2022
• Subjects: Engineering::Electrical and electronic engineering; Deep Reinforcement Learning; Collision Avoidance
• Online Access: https://hdl.handle.net/10356/163356
• Institution: Nanyang Technological University

This paper proposes iTD3-CLN, a Deep Reinforcement Learning (DRL) based low-level motion controller, to achieve map-less autonomous navigation in dynamic scene. We consider three enhancements to the Twin Delayed DDPG (TD3) for the navigation task: N-step returns, Priority Experience Replay, and a ch...