Vorträge und Posterpräsentationen (mit Tagungsband-Eintrag):
M. Kobelrausch, A. Jantsch:
"Collision-Free Deep Reinforcement Learning for Mobile Robots using Crash-Prevention Policy";
Vortrag: 2021 7th International Conference on Control, Automation and Robotics (ICCAR),
Singapore;
23.04.2021
- 26.04.2021; in: "2021 7th International Conference on Control, Automation and Robotics (ICCAR)",
IEEE,
(2021),
ISBN: 978-1-6654-4986-1;
S. 52
- 59.
Kurzfassung englisch:
In this paper, we propose a crash-prevention policy for an autonomous collision-free mobile robot based on deep reinforcement learning. The objective is to reach a random location in a limited workspace safely. We go beyond the well-treated navigation paradigm by introducing a crash-prevention policy derived from action-sensor-space characteristics to achieve collision-free learning. This approach enables efficient and safe exploration by guaranteeing continuous collision-free actions, especially for agents learning in physical systems. We use Deep Deterministic Policy Gradient as a base method to evaluate the proposed crash-prevention policy on a mobile robot environment. Experiments show that using our approach maintains or even slightly improves training results while collisions are entirely avoided.
Schlagworte:
Safe Reinforcement Learning, Deep Reinforcement Learning, Continuous Control, Collision-Free Learning, Mobile Robots
"Offizielle" elektronische Version der Publikation (entsprechend ihrem Digital Object Identifier - DOI)
http://dx.doi.org/10.1109/ICCAR52225.2021.9463474
Erstellt aus der Publikationsdatenbank der Technischen Universität Wien.