Human-Guided Reinforcement Learning With Sim-to-Real Transfer for Autonomous Navigation
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2023-12 · 45 (12) · 14745-14759
DOI: 10.1109/tpami.2023.3314762 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2023-12. Verfasst von Jingda Wu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 118-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: A*STAR AME Young Individual Research, MTC Individual Research, ANR-NRF.
Abstract (Originalsprache)
Reinforcement learning (RL) is a promising approach in unmanned ground vehicles (UGVs) applications, but limited computing resource makes it challenging to deploy a well-behaved RL strategy with sophisticated neural networks. Meanwhile, the training of RL on navigation tasks is difficult, which requires a carefully-designed reward function and a large number of interactions, yet RL navigation can still fail due to many corner cases. This shows the limited intelligence of current RL methods, thereby prompting us to rethink combining RL with human intelligence. In this paper, a human-guided RL framework is proposed to improve RL performance both during learning in the simulator and deployment in the real world. The framework allows humans to intervene in RL's control progress and provide demonstrations as needed, thereby improving RL's capabilities. An innovative human-guided RL algorithm is proposed that utilizes a series of mechanisms to improve the effectiveness of human guidance, including human-guided learning objective, prioritized human experience replay, and human intervention-based reward shaping. Our RL method is trained in simulation and then transferred to the real world, and we develop a denoised representation for domain adaptation to mitigate the simulation-to-real gap. Our method is validated through simulations and real-world experiments to navigate UGVs in diverse and dynamic environments based only on tiny neural networks and image inputs. Our method performs better in goal-reaching and safety than existing learning- and model-based navigation approaches and is robust to changes in input features and ego kinetics. Furthermore, our method allows small-scale human demonstrations to be used to improve the trained RL agent and learn expected behaviors online.
Förderung
- A*STAR AME Young Individual Research
- MTC Individual Research
- ANR-NRF
- SUG-NAP Grant of Nanyang Technological University, Singapore
Zitieren
APA
Wu, J., Zhou, Y., Yang, H., Huang, Z., & Lv, C. (2023). Human-Guided Reinforcement Learning With Sim-to-Real Transfer for Autonomous Navigation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(12), 14745-14759. https://doi.org/10.1109/tpami.2023.3314762
Vancouver
Wu J, Zhou Y, Yang H, Huang Z, Lv C. Human-Guided Reinforcement Learning With Sim-to-Real Transfer for Autonomous Navigation. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2023;45(12):14745-14759. doi:10.1109/tpami.2023.3314762
BibTeX
@article{Wu2023,
author = {Wu, Jingda and Zhou, Yanxin and Yang, Haohan and Huang, Zhiyu and Lv, Chen},
title = {Human-Guided Reinforcement Learning With Sim-to-Real Transfer for Autonomous Navigation},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2023},
volume = {45},
number = {12},
pages = {14745--14759},
doi = {10.1109/tpami.2023.3314762}
}
EUVIMED