This workshop focuses on cooperative intelligence within multi-agent embodied intelligent systems. Artificial intelligence has propelled the development of embodied AI, particularly in autonomous vehicles, robotics, and drones. However, achieving full autonomy in complex and dynamic environments remains a formidable challenge for individual agents. Cooperative intelligence offers a transformative approach that allows agents to collaborate and interact with the infrastructure to handle a wide range of tasks more efficiently. 1) In autonomous driving, the availability of datasets and breakthrough algorithms has spurred research interest in cooperative autonomous driving. Vehicle-to-Everything (V2X) interactions, including Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I), empower autonomous vehicles to extend perception, increase safety, and overcome the limitations of single-vehicle autonomy, laying the groundwork for large-scale adoption. 2) In robotics, the evolution of multi-agent systems is revolutionizing the exploration of unknown environments. These advances allow robots to efficiently assist humans in challenging, open-world tasks. 3) In drones, aerial robot swarms collaborate to perform complex tasks such as drone shows, 3D printing, and navigating cluttered environments. Furthermore, ground-air collaboration between drones and mobile robots shows immense potential in areas such as large-scale mapping and joint search and rescue. Despite progress, challenges in coordinating multi-agent systems remain underexplored. Key hurdles include deciding what information to transmit, how to transmit, and how to fuse data across various levels like perception, prediction, and planning. Moreover, obtaining high-quality real-world datasets is difficult. Recent advances in foundational and generative models offer promising ways to overcome these obstacles. This workshop will explore opportunities, challenges, and future directions for multi-agent embodied intelligent systems in the generative-AI era.
Links to Past Workshops: 1st MAAS Workshop @ECCV2024
We invite submissions including but not limited to the following topics:
- Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I)
- Multi-agent Robotic System and Swarm Robots
- Swarm of Drones and Aerial Robots
- Communication-Efficient Cooperative Perception
- Cooperative Motion Prediction and Decision-Making
- End-to-End Cooperative Policy Learning
- Efficient and Intelligent V2X Communication
- Data Security and Privacy in Multi-agent Communication
- Multi-Robot Exploration and Mapping
- Intelligent Transportation System
- Large Language Model-assisted Cooperative System
- Foundation Models for Cooperative System
- Generative Models for Data Synthesis and Simulation
- Datasets and Benchmarks for Cooperative Learning
Important Dates
- Paper Submission Open: Februray 01, 2025
- Submission asbtract deadline: March 10, 2025
- Paper submission deadline: March 20, 2025
- Notification of acceptance: March 31, 2025
- Camera ready: April 07, 2025
Submission Guidance
- Submission Portal: Openreview
We plan to host three challenges: end-to-end autonomous driving through V2X cooperation, multi-robot collaboration, and human–robot interaction.
| Challenge | Organizing Committee | Status | Link |
|---|---|---|---|
| End-to-End Autonomous Driving through V2X Cooperation | Ruiyang Hao, Haibao Yu, Jiaru Zhong, Jiahao Wang, Wenxian Yang, Chuanye Wang, Siqi Fan | Upcoming | Upcoming |
| RoboTwin Dual-Arm Collaboration Challenge | Yao Mu, Tianxing Chen, Zhiqiang Xie | Upcoming | Upcoming |
| Human–Robot Interaction Challenge | Jianing Qiu, Lin Li, Lipeng Chen | Upcoming | Upcoming |
The workshop has been accepted as a full-day event. The schedule will be updated in due course.
Note: We are currently extending invitations to other eminent research scholars, so please stay tuned for updates.
Contact: If you have any questions, please contact us at: coop-intelligence@googlegroups.com or yuhaibao94@gmail.com.