We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
Collective Transport Behavior in a Robotic Swarm with Hierarchical Imitation Learning.
- Authors
Han, Ziyao; Yi, Fan; Ohkura, Kazuhiro
- Abstract
Swarm robotics is the study of how a large number of relatively simple physically embodied robots can be designed such that a desired collective behavior emerges from local interactions. Furthermore, reinforcement learning (RL) is a promising approach for training robotic swarm controllers. However, the conventional RL approach suffers from the sparse reward problem in some complex tasks, such as key-to-door tasks. In this study, we applied hierarchical imitation learning to train a robotic swarm to address a key-to-door transport task with sparse rewards. The results demonstrate that the proposed approach outperforms the conventional RL method. Moreover, the proposed method outperforms the conventional hierarchical RL method in its ability to adapt to changes in the training environment.
- Subjects
AGGREGATION (Robotics); COLLECTIVE behavior; ROBOTICS; REINFORCEMENT learning; SPACE robotics
- Publication
Journal of Robotics & Mechatronics, 2024, Vol 36, Issue 3, p538
- ISSN
0915-3942
- Publication type
Article
- DOI
10.20965/jrm.2024.p0538