Please use this identifier to cite or link to this item:
|Title:||iTD3-CLN: learn to navigate in dynamic scene through Deep Reinforcement Learning||Authors:||Jiang, Haoge
Esfahani, Mahdi Abolfazli
|Keywords:||Engineering::Electrical and electronic engineering||Issue Date:||2022||Source:||Jiang, H., Esfahani, M. A., Wu, K., Wan, K., Heng, K., Wang, H. & Jiang, X. (2022). iTD3-CLN: learn to navigate in dynamic scene through Deep Reinforcement Learning. Neurocomputing, 503, 118-128. https://dx.doi.org/10.1016/j.neucom.2022.06.102||Project:||192 2500049||Journal:||Neurocomputing||Abstract:||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 channel-based Convolutional Laser Network (CLN) architecture. In contrast to the conventional methods such as the DWA, our approach is found superior in the following ways: no need for prior knowledge of the environment and metric map, lower reliance on an accurate sensor, learning emergent behavior in dynamic scene that is intuitive, and more remarkably, able to transfer to the real robot without further fine-tuning. Our extensive studies show that in comparison to the original TD3, the proposed approach can obtain approximately 50% reduction in training to get same performance, 50% higher accumulated reward, and 30–50% increase in generalization performance when tested in unseen environments. Videos of our experiments are available at https://youtu.be/BRN0Gk5oLOc (Simulation) and https://youtu.be/yIxGH9TPQCc (Real experiment).||URI:||https://hdl.handle.net/10356/163356||ISSN:||0925-2312||DOI:||10.1016/j.neucom.2022.06.102||Rights:||© 2022 Elsevier B.V. All rights reserved.||Fulltext Permission:||none||Fulltext Availability:||No Fulltext|
|Appears in Collections:||EEE Journal Articles|
Updated on Jan 29, 2023
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.