PUBLICACIÓN
SocNavGym: A Reinforcement Learning Gym for Social Navigation
ACCEDER A LA PUBLICACIÓN:
Kapoor A., Swamy S., Bachiller P., Manso L.J.
2023 IEEE International Workshop on Robot and Human Communication, RO-MAN
CITAS
2
DOI
10.1109/ro-man57019.2023.10309591
EID
2-s2.0-85186978672
ISSN
1944-9445
EISSN
1944-9437
ISBN
9798350336702
BIBTEX
@inproceedings{0ee295c8c0cd4ec2a6c55989a870f737, title = 'SocNavGym: A Reinforcement Learning Gym for Social Navigation', abstract = 'It is essential for autonomous robots to be socially compliant while navigating in human-popuated environments. Machine Learning and, especially, Deep Reinforcement Learning have recently gained considerable traction in the field of Social Navigation. This can be partially attributed to the resulting policies not being bound by human limitations in terms of code complexity or the number of variables that are handled. Unfortunately, the lack of safety guarantees and the large data requirements by DRL algorithms make learning in the real world unfeasible. To bridge this gap, simulation environments are frequently used. We propose SocNavGym, an advanced simulation environment for social navigation that can generate a wide variety of social navigation scenarios and facilitates the development of intelligent social agents. SocNavGym is lightweight, fast, easy to use, and can be effortlessly configured to generate different types of social navigation scenarios. It can also be configured to work with different hand-crafted and data-driven social reward signals and to yield a variety of evaluation metrics to benchmark agents{\textquoteright} performance. Further, we also provide a case study where a Dueling-DQN agent is trained to learn social-navigation policies using SocNavGym. The results provide evidence that SocNavGym can be used to train an agent from scratch to navigate in simple as well as complex social scenarios. Our experiments also show that the agents trained using the data-driven reward function display more advanced social compliance in comparison to the heuristic-based reward function.', author = 'Aditya Kapoor and Sushant Swamy and Pilar Bachiller-Burgos and Manso, {Luis J.}', year = '2023', month = nov, day = '13', doi = '10.1109/RO-MAN57019.2023.10309591', language = 'English', isbn = '979-8-3503-3671-9', series = 'IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)', publisher = 'IEEE', booktitle = '2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)', address = 'United States', note = '2023 32nd IEEE International Conference on Robot and Human Interactive Communication, RO-MAN 2023 ; Conference date: 28-08-2023 Through 31-08-2023', }
AUTORES DE LA UEX
OTRAS PUBLICACIONES DE INTERÉS
