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
- AI Agents in Cooperative Systems
- Foundation Models for Cooperative System
- Generative Models for Data Synthesis and Simulation
- Datasets and Benchmarks for Cooperative Learning
- Safety and Security of Multi-Agent Systems
Important Dates
- Paper Submission Open: Februray 01, 2025
- Submission asbtract deadline:
March 10, 2025March 21, 2025 (Anywhere on Earth) - Paper submission deadline:
March 20, 2025March 23, 2025 (Anywhere on Earth) - Notification of acceptance: March 29, 2025 (Anywhere on Earth)
- Paper metadata submission deadline: March 30, 2025 (Anywhere on Earth)
- Camera ready: April 07, 2025
Submission Guidance
- Submission Portal: Openreview
- Submission format: Submissions must follow the CVPR 2025 template (here) and will be peer-reviewed in a double-blind manner. Submission must be no more than 8 pages (excluding references). By default, accepted papers will be included in the CVPR workshop proceedings. Accepted papers will be presented in the form of posters, with several papers being selected for spotlight sessions.
Awards
- 🏆Best Paper Award ($500)
- 🏆Best Paper Runner-up Award ($500)
Area Chairs
- Dandan Zhang (Imperial College London)
- Li Chen (Shanghai AI Lab)
- Siqi Fan (Tsinghua University)
- Jianing Qiu (Chinese University of Hong Kong)
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 | 🌐 |
| RoboTwin Dual-Arm Collaboration Challenge | Yao Mu, Tianxing Chen, Zhiqiang Xie | Upcoming | 🌐 |
| Human–Robot Object Throwing and Catching Challenge | Jianing Qiu, Lin Li, Lipeng Chen | Upcoming | 🌐 |
Awards for Each Challenge
- 🥇 First Prize ($1500)
- 🥈 Second Prize ($1000)
- 🥉 Third Prize ($500)
- Date - June 12th, 2025 (Full Day)
- Location - Room 102 A, Music City Center, Nashville TN, USA
- Agenda are as follows:
| Time | Schedule | Hoster |
|---|---|---|
| 08:50 - 09:00 | Introduction and Opening Remarks Haibao Yu (HKU) | - |
| 09:00 - 09:30 | Keynote Speak 1: Enze Xie (Nvidia) Talk Title: Building an efficient and high-quality Text to Image foundation generative model from scratch | Shanghang Zhang (PKU) |
| 09:30 - 10:00 | Keynote Speak 2: Jeannette Bohg (Stanford) Talk Title: TBD | |
| 10:00 - 10:30 | Keynote Speak 3: Guillaume Sartoretti (NUS) Talk Title: High-Dimensional Multi-Agent Robot Learning | |
| 10:30 - 11:00 | Coffe Break & Poster Presentation | - |
| 11:00 - 11:30 | Keynote Speak 4: Deepak Pathak (SkildAI & CMU) Talk Title: TBD | Shanghang Zhang (PKU) |
| 11:30 - 12:00 | Keynote Speak 5: Jiachen Li (University of California, Riverside) Talk Title: Toward Trustworthy Embodied Agents: From Individuals to Teams | |
| 12:00 - 12:10 | Oral Paper 1: Paper Title: Efficient Task-specific Conditional Diffusion Policies: Shortcut Model Acceleration and SO(3) Optimization Presenter: Haiyong Yu | Haibao Yu (HKU) |
| 12:10 - 12:20 | Oral Paper 2: Paper Title: Multi-Agent Systems for Robotic Autonomy with LLMs Presenter: Dandan Zhang | |
| 12:20 - 12:30 | Oral Paper 3: Paper Title: A Multi-Agent Autonomous Mechatronics Design Framework Presenter: Zeyu Wang | |
| - | Lunch Break | - |
| 13:30 - 14:00 | Keynote Speak 6: Marco Pavone (Nvidia & Stanford) Talk Title: TBD | Dandan Zhang (Imperial College London) |
| 14:00 - 14:30 | Keynote Speak 7: Hongyang Li (OpenDriveLab & HKU) Talk Title: VLAs on the Horizon for Embodied Systems | |
| 14:30 - 15:00 | Keynote Speak 8: Siheng Chen (SJTU) Talk Title: Multi-agent collaborative perception | |
| 15:00 - 15:30 | Keynote Speak 9: Hao Zhao (THU) Talk Title: World Models: Subjunctives | |
| 15:30 - 16:00 | Coffe Break & Poster Presentation | - |
| 16:00 - 16:30 | Keynote Speak 10: Zsolt Kira (Georgia Institute of Technology) Talk Title: Vision-Language Models for Cooperative Intelligence | Dandan Zhang (Imperial College London) |
| 16:30 - 17:00 | Keynote Speak 11: Sergey Levine (PI & UC Berkeley) Talk Title: Responsive and Interactive Vision-Language-Action Models (Remote) | |
| 17:00 - 17:15 | Autonomous Driving through V2X Cooperation Challenge: Overview & Awards & Sharing Ruiyang Hao (THU) | Haibao Yu (HKU) |
| 17:15 - 17:30 | RoboTwin Dual-Arm Collaboration Challenge: Overview & Awards & Sharing Yao Mu (HKU & SJTU) | |
| 17:30 - 17:40 | Oral Paper 4: Paper Title: LangCoop: Collaborative Driving with Language Presenter: Xiangbo Gao | |
| 17:40 - 17:50 | Oral Paper 5: Paper Title: RoboFactory: Exploring Embodied Agent Collaboration with Compositional Constraints Presenter: Yiran Qin | |
| 17:50 - 18:00 | Closed Remarks & Best Paper Awards Haibao Yu (HKU) | - |
| 19:00 - 21:00 | MEIS Workshop Banquet (About 20 people) Location: near Center, TBD | Haibao Yu (HKU) |
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.
Jiahao Wang
Tsinghua University
Jiahui Xu
Beijing Institute of Technology
Haoyu Li
Beijing Institute of Technology
Ruiyang Hao
Tsinghua University
Siqi Fan
Tsinghua University
Wenxian Yang
Tsinghua University
Yuexin Ma
ShanghaiTech University
Yang Liu
Tsinghua University
Yan Wang
Tsinghua University
Guangliang Cheng
University of Liverpool
Jirui Yuan
Tsinghua University
Mingyu Ding
UNC-Chapel Hill
Lipeng Chen
Tencent Robotics X
Lin Li
King’s College London
Yue Hu
Shanghai Jiao Tong University
Yunshuang Yuan
Leibniz University Hannover
Xuting Duan
Beihang University
Deyuan Qu
University of North Texas
Minh David Thao Chan
Tsinghua University
Hyunchul Bae
Korea Advanced Institute of Science and Technology
Alberto Justo
Tecnalia Research & Innovation
Je-Seok Ham
Electronics and Telecommunications Research Institute
Hao Wei
The Chinese University of Hong Kong
Carlos Plou
University of Zaragoza
Xiaosong Jia
Shanghai Jiao Tong University
Guoyu Zhang
Tongji University
