Generative adversarial imitation learning for robot swarms: Learning from human demonstrations and trained policies
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911482036355072 |
|---|---|
| author | Kraus, Mattes Kuckling, Jonas |
| author_facet | Kraus, Mattes Kuckling, Jonas |
| contents | In imitation learning, robots are supposed to learn from demonstrations of the desired behavior. Most of the work in imitation learning for swarm robotics provides the demonstrations as rollouts of an existing policy. In this work, we provide a framework based on generative adversarial imitation learning that aims to learn collective behaviors from human demonstrations. Our framework is evaluated across six different missions, learning both from manual demonstrations and demonstrations derived from a PPO-trained policy. Results show that the imitation learning process is able to learn qualitatively meaningful behaviors that perform similarly well as the provided demonstrations. Additionally, we deploy the learned policies on a swarm of TurtleBot 4 robots in real-robot experiments. The exhibited behaviors preserved their visually recognizable character and their performance is comparable to the one achieved in simulation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_02783 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Generative adversarial imitation learning for robot swarms: Learning from human demonstrations and trained policies Kraus, Mattes Kuckling, Jonas Robotics Machine Learning Multiagent Systems In imitation learning, robots are supposed to learn from demonstrations of the desired behavior. Most of the work in imitation learning for swarm robotics provides the demonstrations as rollouts of an existing policy. In this work, we provide a framework based on generative adversarial imitation learning that aims to learn collective behaviors from human demonstrations. Our framework is evaluated across six different missions, learning both from manual demonstrations and demonstrations derived from a PPO-trained policy. Results show that the imitation learning process is able to learn qualitatively meaningful behaviors that perform similarly well as the provided demonstrations. Additionally, we deploy the learned policies on a swarm of TurtleBot 4 robots in real-robot experiments. The exhibited behaviors preserved their visually recognizable character and their performance is comparable to the one achieved in simulation. |
| title | Generative adversarial imitation learning for robot swarms: Learning from human demonstrations and trained policies |
| topic | Robotics Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2603.02783 |