CHORUS: Decentralized Multi-Embodiment Collaboration with One VLA Policy

• URL: http://arxiv.org/abs/2606.12352v1
• Date: Wed, 10 Jun 2026 17:26:08 GMT
• Title: CHORUS: Decentralized Multi-Embodiment Collaboration with One VLA Policy
• Abstract summary: CHORUS is a framework that adapts a single vision-language-action (VLA) backbone to control diverse, multi-robot teams.<n>In experiments, CHORUS achieves a 64% point improvement over decentralized, from-scratch models.<n>Results show that a shared VLA backbone is capable of achieving decentralized multi-robot collaboration.
• Score: 67.76658561040625
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-robot collaboration allows robots to efficiently take on a wide range of tasks, from moving a couch through a doorway to assembling structures on a construction site. However, achieving such coordination in mobile multi-robot settings remains challenging: centralized methods conditioned on the combined observations of a team scale poorly with team size, and decentralized methods that train one policy per robot often require explicit alignment procedures or information sharing at inference time to overcome partial observability. Our key insight is that the visuomotor priors of pretrained vision-language-action (VLA) models should enable reactive, decentralized collaboration from each robot's local observations alone, without these inference-time assumptions. We propose CHORUS, a framework that adapts a single VLA backbone to control diverse, multi-robot teams. At inference time, each robot runs an independent copy of CHORUS, conditioned only on its own observations and a robot-identifying prompt. In real-world experiments including mobile tape measurement, library book handovers, and laundry basket lifting, CHORUS achieves a 64% point improvement over decentralized, from-scratch models, improves reactivity to teammate behavior by 40% points, and outperforms centralized baselines. Together, these results show that a shared VLA backbone is capable of achieving decentralized multi-robot collaboration, without per-robot policies or inter-robot communication at inference.

Related papers

• Cooperative Informative Sensing for Monitoring Dynamic Indoor Environments via Multi-Agent Reinforcement Learning [56.64821510576244]
  We formulate cooperative active observation as a decentralized control problem in which multiple robots adjust their motion to directly optimize monitoring accuracy under partial observability.<n>We propose a learning-based framework for cooperative policies from decentralized observations using multi-agent reinforcement learning (MARL), supported by an architecture that handles variable numbers of humans and temporal dependencies.
  arXiv  Detail & Related papers  (2026-04-25T07:20:15Z)
• Federated Single-Agent Robotics: Multi-Robot Coordination Without Intra-Robot Multi-Agent Fragmentation [14.412476605788482]
  We present Federated Single-Agent Robotics, a runtime architecture for multi-robot coordination built on single-agent robot runtimes.<n>We formalize key coordination relations including authority delegation, inter-robot capability requests, local-versus-fleet recovery boundaries, and hierarchical human supervision.<n>Results show statistically significant gains in governance locality and recovery containment against decomposition-heavy baselines.
  arXiv  Detail & Related papers  (2026-04-13T05:51:13Z)
• LPAC: Learnable Perception-Action-Communication Loops with Applications to Coverage Control [72.81786007015471]
  We propose a learnable Perception-Action-Communication (LPAC) architecture for the problem.<n>CNN processes localized perception; a graph neural network (GNN) facilitates robot communications.<n> Evaluations show that the LPAC models outperform standard decentralized and centralized coverage control algorithms.
  arXiv  Detail & Related papers  (2024-01-10T00:08:00Z)
• A Scalable Multi-Robot Framework for Decentralized and Asynchronous Perception-Action-Communication Loops [72.1902268440158]
  Collaboration in large robot swarms to achieve a common global objective is a challenging problem in large environments.<n>The robots must execute a Perception-Action-Communication loop -- they perceive their local environment, communicate with other robots, and take actions in real time.<n>Recently, this has been addressed using Graph Neural Networks (GNNs) for applications such as flocking and coverage control.<n>This paper proposes a framework for asynchronous PAC in robot swarms, where decentralized GNNs are used to compute navigation actions and generate messages for communication.
  arXiv  Detail & Related papers  (2023-09-18T21:20:50Z)
• AdverSAR: Adversarial Search and Rescue via Multi-Agent Reinforcement Learning [4.843554492319537]
  We propose an algorithm that allows robots to efficiently coordinate their strategies in the presence of adversarial inter-agent communications. It is assumed that the robots have no prior knowledge of the target locations, and they can interact with only a subset of neighboring robots at any time. The effectiveness of our approach is demonstrated on a collection of prototype grid-world environments.
  arXiv  Detail & Related papers  (2022-12-20T08:13:29Z)
• Multi-robot Social-aware Cooperative Planning in Pedestrian Environments Using Multi-agent Reinforcement Learning [2.7716102039510564]
  We propose a novel multi-robot social-aware efficient cooperative planner that on the basis of off-policy multi-agent reinforcement learning (MARL) We adopt temporal-spatial graph (TSG)-based social encoder to better extract the importance of social relation between each robot and the pedestrians in its field of view (FOV)
  arXiv  Detail & Related papers  (2022-11-29T03:38:47Z)
• CLAS: Coordinating Multi-Robot Manipulation with Central Latent Action Spaces [9.578169216444813]
  This paper proposes an approach to coordinating multi-robot manipulation through learned latent action spaces that are shared across different agents. We validate our method in simulated multi-robot manipulation tasks and demonstrate improvement over previous baselines in terms of sample efficiency and learning performance.
  arXiv  Detail & Related papers  (2022-11-28T23:20:47Z)
• Distributed Reinforcement Learning for Robot Teams: A Review [10.92709534981466]
  Recent advances in sensing, actuation, and computation have opened the door to multi-robot systems. Community has leveraged model-free multi-agent reinforcement learning to devise efficient, scalable controllers for multi-robot systems. Recent findings: Decentralized MRS face fundamental challenges, such as non-stationarity and partial observability.
  arXiv  Detail & Related papers  (2022-04-07T15:34:19Z)
• Centralizing State-Values in Dueling Networks for Multi-Robot Reinforcement Learning Mapless Navigation [87.85646257351212]
  We study the problem of multi-robot mapless navigation in the popular Training and Decentralized Execution (CTDE) paradigm. This problem is challenging when each robot considers its path without explicitly sharing observations with other robots. We propose a novel architecture for CTDE that uses a centralized state-value network to compute a joint state-value.
  arXiv  Detail & Related papers  (2021-12-16T16:47:00Z)
• Learning Multi-Arm Manipulation Through Collaborative Teleoperation [63.35924708783826]
  Imitation Learning (IL) is a powerful paradigm to teach robots to perform manipulation tasks. Many real-world tasks require multiple arms, such as lifting a heavy object or assembling a desk. We present Multi-Arm RoboTurk (MART), a multi-user data collection platform that allows multiple remote users to simultaneously teleoperate a set of robotic arms.
  arXiv  Detail & Related papers  (2020-12-12T05:43:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.