Abstract
Multi-robot systems (MRS) enable cooperation between multiple robots to achieve common goals or tasks. These systems can enhance efficiency and productivity in various applications, such as transportation, manufacturing, and exploration. However, a critical issue in MRS operation is the possibility of collisions between robots or with static/dynamic obstacles. This survey presents the latest trends and advancements in collision avoidance approaches for multi-robot systems. We analyze centralized and distributed collision avoidance methods, examining the overall performance, applicable vehicle platforms, and the necessity for inter-robot communication. This survey also explores the applicability of reinforcement learning-based methods for collision avoidance in multi-agent systems.
| Original language | English |
|---|---|
| Pages (from-to) | 402-411 |
| Number of pages | 10 |
| Journal | Journal of Institute of Control, Robotics and Systems |
| Volume | 30 |
| Issue number | 4 |
| DOIs | |
| State | Published - 2024 |
Keywords
- collision avoidance
- multi-robot systems
- path planning
- reinforcement learning
- survey
