Towards Natural Language Communication for Cooperative Autonomous Driving via Self-Play
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909628943564800 |
|---|---|
| author | Cui, Jiaxun Tang, Chen Holtz, Jarrett Nguyen, Janice Allievi, Alessandro G. Qiu, Hang Stone, Peter |
| author_facet | Cui, Jiaxun Tang, Chen Holtz, Jarrett Nguyen, Janice Allievi, Alessandro G. Qiu, Hang Stone, Peter |
| contents | Past work has demonstrated that autonomous vehicles can drive more safely if they communicate with one another than if they do not. However, their communication has often not been human-understandable. Using natural language as a vehicle-to-vehicle (V2V) communication protocol offers the potential for autonomous vehicles to drive cooperatively not only with each other but also with human drivers. In this work, we propose a suite of traffic tasks in autonomous driving where vehicles in a traffic scenario need to communicate in natural language to facilitate coordination in order to avoid an imminent collision and/or support efficient traffic flow. To this end, this paper introduces a novel method, LLM+Debrief, to learn a message generation and high-level decision-making policy for autonomous vehicles through multi-agent discussion. To evaluate LLM agents for driving, we developed a gym-like simulation environment that contains a range of driving scenarios. Our experimental results demonstrate that LLM+Debrief is more effective at generating meaningful and human-understandable natural language messages to facilitate cooperation and coordination than a zero-shot LLM agent. Our code and demo videos are available at https://talking-vehicles.github.io/. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_18334 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Towards Natural Language Communication for Cooperative Autonomous Driving via Self-Play Cui, Jiaxun Tang, Chen Holtz, Jarrett Nguyen, Janice Allievi, Alessandro G. Qiu, Hang Stone, Peter Robotics Artificial Intelligence Multiagent Systems Past work has demonstrated that autonomous vehicles can drive more safely if they communicate with one another than if they do not. However, their communication has often not been human-understandable. Using natural language as a vehicle-to-vehicle (V2V) communication protocol offers the potential for autonomous vehicles to drive cooperatively not only with each other but also with human drivers. In this work, we propose a suite of traffic tasks in autonomous driving where vehicles in a traffic scenario need to communicate in natural language to facilitate coordination in order to avoid an imminent collision and/or support efficient traffic flow. To this end, this paper introduces a novel method, LLM+Debrief, to learn a message generation and high-level decision-making policy for autonomous vehicles through multi-agent discussion. To evaluate LLM agents for driving, we developed a gym-like simulation environment that contains a range of driving scenarios. Our experimental results demonstrate that LLM+Debrief is more effective at generating meaningful and human-understandable natural language messages to facilitate cooperation and coordination than a zero-shot LLM agent. Our code and demo videos are available at https://talking-vehicles.github.io/. |
| title | Towards Natural Language Communication for Cooperative Autonomous Driving via Self-Play |
| topic | Robotics Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2505.18334 |