MARS-EAI
ICRA 2026 Workshop on Multi-Agent Robotic Systems:
Real-World Collaboration and Interaction
Overview
This workshop brings together researchers across robotics, machine learning, and embodied AI to explore how multi-agent robotic systems can achieve seamless collaboration and interaction in real-world environments. We focus on the critical challenges of deploying multi-robot teams in unstructured, dynamic settings—from warehouses and construction sites to households and healthcare facilities—where robots must coordinate with each other and collaborate naturally with humans.
Key themes include robot-robot coordination for complex physical tasks, human-robot teaming and intuitive interaction interfaces, robust perception and communication in real-world conditions, and safe deployment strategies for multi-agent systems operating alongside humans. Through invited talks, paper sessions, and hands-on discussions, we aim to bridge the gap between simulation-based research and practical deployment of collaborative robotic systems.
The workshop will consist of a combination of invited talks and contributed papers, selected through a rigorous review process. We aim to bring together experts from academia and industry to promote cross-disciplinary collaboration. We also plan to provide best paper awards and registration support for students and junior researchers.
Schedule
Virtual access (all sessions):
Zoom link: https://cmu.zoom.us/j/5314067609
Meeting ID: 531 406 7609
Passcode: icra2026
| Time | Event |
|---|---|
| 09:20 – 09:40 | Opening remarks |
| 09:40 – 10:00 | Poster session |
| 10:10 – 10:40 | Oral presentations 1 (15 min × 2) |
| 10:45 – 11:45 | Poster session & coffee socials 1 (1h) |
| 11:45 – 13:00 | Lunch break |
| 13:00 – 13:20 | Invited talk — Yao Mu (20 min) |
| 13:30 – 13:50 | Invited talk — Yinghao Xu (20 min) |
| 13:50 – 14:20 | Oral presentations 2 (15 min × 2) |
| 14:25 – 15:30 | Poster session & coffee socials 2) |
| 15:30 – 15:50 | Invited talk — Marco Pavone (20 min) |
| 16:00 – 16:20 | Invited talk — Eugene Vinitsky (20 min) |
| 16:30 – 17:00 | Awards and closing |
Call For Papers
Our workshop is Non-Proceedings—a flexible, non-archival venue for sharing a broad range of contributions without restrictive publishing constraints, formatting requirements, or page limits. We warmly welcome full papers, works-in-progress, datasets, technical reports, and position papers.
Topics of interest include:
- Multi-robot coordination for real-world tasks: navigation, manipulation, assembly, and logistics.
- Human-robot collaboration: intuitive interfaces, shared autonomy, and natural interaction.
- Sim-to-real transfer and robust deployment of multi-agent systems in unstructured environments.
- Communication and coordination protocols for heterogeneous robot teams.
- Safety, trust, and transparency in human-multi-robot interaction scenarios.
- Learning-based approaches (RL, imitation learning) for real-world multi-agent coordination.
- Perception, mapping, and situational awareness for collaborative robot teams.
- Real-world benchmarks, datasets, and evaluation metrics for multi-agent robotic systems.
- Applications in warehousing, healthcare, construction, agriculture, search and rescue, and domestic assistance.
Submission Guidelines
We follow the ICRA 2026 main conference paper format.
Page Limit: 8 pages total (mandatory).
Format: IEEE double-column conference format.
Important Dates
Submission Deadline: May 1, 2026 (AoE)
Notification to Authors: May 10, 2026
Camera-Ready Deadline: May 20, 2026
Accepted Papers
Congratulations to all authors of accepted papers!
Outstanding Papers (Oral)
- Graph Neural Planning and Predictive Control for Multi-Robot Communication-Constrained Unlabeled Motion Planning ORAL
- A Real-World Dataset for Collaborative Teams: Event-Based 3D Tracking and Coordination in High-Density Flocks ORAL
- Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning ORAL
- CRAFT: Coaching Reinforcement Learning Autonomously using Foundation Models for Multi-Robot Coordination Tasks ORAL
Poster Papers
- Autonomous Integration and Improvement of Robotic Assembly using Skill Graph Representations POSTER
- MoRoCo: Topology-Adaptive Human-Fleet Coordination under Restricted Communication POSTER
- Toward Optimal Multi-Vehicle Path Planning with Hybrid Roadmaps POSTER
- SRPP: Safe Rescheduled Prioritized Planning Framework for Multi-Agent Path Finding POSTER
- A Boundary Value Problem Approach to Autonomous Rendezvous in Industrial Human-Drone Interaction POSTER
- A Practical Framework of Key Performance Indicators for Multi-Robot Lunar and Planetary Field Tests POSTER
- Constrained Manipulability Polytopes as Visual Cues for Dual-Arm Teleoperation POSTER
- Mixed-Reality Digital Twins: Leveraging the Physical and Virtual Worlds for Hybrid Sim2Real Transition of Multi-Agent Reinforcement Learning Policies POSTER
- EMTP: Efficient Multi-Robot Task Planning with Large Language Models POSTER
- Connectivity-Aware Graph Extension for Decentralized Multi-Robot Exploration POSTER
- Adaptive Swarm Intelligence: Decentralized Multi-Robot Navigation in Dynamic Formations POSTER
- Cooperative Multi-Agent Mobile Manipulation using Learned Dynamical Systems POSTER
- Cooperative Thermoregulation in Multi-Robot Lunar Survival via Reinforcement Learning POSTER
- MultiPush: Multirobot Nonprehensile Rearrangement Planning POSTER
- Controlling Generative Flow Policies of Multi-Robot Systems with Gradient-Based Guidance POSTER
- Safe and Fair Multi-Quadruped Collaborative Box Pushing POSTER
- Geometric Coherence via Weighted Matching for 3D Heterogeneous Multi-Agent Reach-Avoid Games POSTER
- CADENCE: Predicting Realized MAPF Execution Time Beyond Sum of Costs POSTER
- Uncertainty-Aware Shared Autonomy for Multi-Agent Human and Robot Teams: Collaborative Uncertainty Estimation with Conformal Coverage Guarantees POSTER
- Integrated Task and Kinodynamic Path Planning for Heterogeneous Multi-Robot Formations POSTER
Invited Speakers
Given the interdisciplinary nature of the topics our workshop aims to cover, we invited keynote speakers with different backgrounds and perspectives on open-world reasoning and decision-making:
Organizers
Advisory Board
Contact Information
For questions and inquiries, please reach out to the organizers:
Bruno Chen (nybchen@cmu.edu), Yiran Qin (yiranqin@link.cuhk.edu.cn)