DeReCo: Decoupling Representation and Coordination Learning for Object-Adaptive Decentralized Multi-Robot Cooperative Transport

• URL: http://arxiv.org/abs/2603.08111v1
• Date: Mon, 09 Mar 2026 08:53:11 GMT
• Title: DeReCo: Decoupling Representation and Coordination Learning for Object-Adaptive Decentralized Multi-Robot Cooperative Transport
• Abstract summary: DeReCo is a novel framework that decouples representation and coordination learning for object-adaptive multi-robot cooperative transport.<n> Experimental results show that DeReCo outperforms baselines in simulation on three training objects, generalizes to six unseen objects with varying masses and friction coefficients, and achieves superior performance on two unseen objects in real-robot experiments.
• Score: 4.030781059424759
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generalizing decentralized multi-robot cooperative transport across objects with diverse shapes and physical properties remains a fundamental challenge. Under decentralized execution, two key challenges arise: object-dependent representation learning under partial observability and coordination learning in multi-agent reinforcement learning (MARL) under non-stationarity. A typical approach jointly optimizes object-dependent representations and coordinated policies in an end-to-end manner while randomizing object shapes and physical properties during training. However, this joint optimization tightly couples representation and coordination learning, introducing bidirectional interference: inaccurate representations under partial observability destabilize coordination learning, while non-stationarity in MARL further degrades representation learning, resulting in sample-inefficient training. To address this structural coupling, we propose DeReCo, a novel MARL framework that decouples representation and coordination learning for object-adaptive multi-robot cooperative transport, improving sample efficiency and generalization across objects and transport scenarios. DeReCo adopts a three-stage training strategy: (1) centralized coordination learning with privileged object information, (2) reconstruction of object-dependent representations from local observations, and (3) progressive removal of privileged information for decentralized execution. This decoupling mitigates interference between representation and coordination learning and enables stable and sample-efficient training. Experimental results show that DeReCo outperforms baselines in simulation on three training objects, generalizes to six unseen objects with varying masses and friction coefficients, and achieves superior performance on two unseen objects in real-robot experiments.

Related papers

• Structured LLM Reasoning for Zero-Shot Human--Robot Coordination Under Hidden Goals [3.158926173252809]
  We present a structured large-language-model (LLM) architecture for zero-shot human--robot coordination in a cooperative construction task with private goal views.<n> Guided by a Dec-POMDP formulation, the architecture decomposes decision-making into (i) action-conditioned Theory-of-Mind (ToM) inference, (ii) hierarchical planning, (iii) conversation interpretation, (iv) action verification, and (v) feedback-based replanning.
  arXiv  Detail & Related papers  (2026-08-05T00:40:03Z)
• Scaling Behavior Foundation Model for Humanoid Robots [77.31115920959364]
  Behavior Foundation Models (BFMs) have emerged as a promising solution to address challenges by leveraging large-scale behavioral data.<n>We show that our approach yields significant improvements in control fidelity and task generalization.<n>These results establish BFM as a principled and effective foundation for scalable and general-purpose humanoid control.
  arXiv  Detail & Related papers  (2026-07-16T16:08:27Z)
• Multi-Agent Model-Based Reinforcement Learning with Joint State-Action Learned Embeddings [10.36125908359289]
  We present a novel model-based multi-agent reinforcement learning framework.<n>We design a world model trained with variational auto-encoders and augment the model using the state-action learned embedding.<n>By coupling imagined trajectories with SALE-based action values, the agents acquire a richer understanding of how their choices influence collective outcomes.
  arXiv  Detail & Related papers  (2026-02-13T01:57:21Z)
• Rethinking Visual-Language-Action Model Scaling: Alignment, Mixture, and Regularization [65.37179698521766]
  Vision-Language-Action (VLA) models show strong promise for generalist robot control.<n>It remains unclear whether -- and under what conditions -- the standard "scale data" recipe translates to robotics.<n>We present a systematic, controlled study of VLA scaling that revisits core training choices for pretraining across diverse robots.
  arXiv  Detail & Related papers  (2026-02-10T12:25:43Z)
• DRL: Discriminative Representation Learning with Parallel Adapters for Class Incremental Learning [63.65467569295623]
  We propose the Discriminative Representation Learning (DRL) framework to specifically address these challenges.<n>To conduct incremental learning effectively and yet efficiently, the DRL's network is built upon a PTM.<n>Our DRL consistently outperforms other state-of-the-art methods throughout the entire CIL period.
  arXiv  Detail & Related papers  (2025-10-14T03:19:15Z)
• CoCoL: A Communication Efficient Decentralized Collaborative Method for Multi-Robot Systems [12.818331958107429]
  We propose a Communication efficient decentralized Collaborative Learning method tailored for multi-robot systems with heterogeneous local datasets.<n>CoCoL achieves remarkable communication efficiency with approximate Newton-type updates by capturing the similarity between objective functions of robots.
  arXiv  Detail & Related papers  (2025-08-28T15:25:48Z)
• CoDiEmb: A Collaborative yet Distinct Framework for Unified Representation Learning in Information Retrieval and Semantic Textual Similarity [20.349897901019574]
  We introduce CoDiEmb, a unified framework for training unified text embeddings.<n>CoDiEmb integrates three key innovations for effective joint optimization.<n>Our results and analysis demonstrate that the framework mitigates cross-task trade-offs.
  arXiv  Detail & Related papers  (2025-08-15T12:46:35Z)
• Inter3D: A Benchmark and Strong Baseline for Human-Interactive 3D Object Reconstruction [34.89563280020313]
  We propose Inter3D, a new benchmark and approach for novel state synthesis of human-interactive objects.<n>We conduct extensive experiments on the proposed benchmark, showcasing the challenges of the task and the superiority of our approach.
  arXiv  Detail & Related papers  (2025-02-19T10:00:00Z)
• COMBO-Grasp: Learning Constraint-Based Manipulation for Bimanual Occluded Grasping [56.907940167333656]
  Occluded robot grasping is where the desired grasp poses are kinematically infeasible due to environmental constraints such as surface collisions.<n>Traditional robot manipulation approaches struggle with the complexity of non-prehensile or bimanual strategies commonly used by humans.<n>We introduce Constraint-based Manipulation for Bimanual Occluded Grasping (COMBO-Grasp), a learning-based approach which leverages two coordinated policies.
  arXiv  Detail & Related papers  (2025-02-12T01:31:01Z)
• Cross-modal Consensus Network for Weakly Supervised Temporal Action Localization [74.34699679568818]
  Weakly supervised temporal action localization (WS-TAL) is a challenging task that aims to localize action instances in the given video with video-level categorical supervision. We propose a cross-modal consensus network (CO2-Net) to tackle this problem.
  arXiv  Detail & Related papers  (2021-07-27T04:21:01Z)
• Reinforcement Learning for Sparse-Reward Object-Interaction Tasks in a First-person Simulated 3D Environment [73.9469267445146]
  First-person object-interaction tasks in high-fidelity, 3D, simulated environments such as the AI2Thor pose significant sample-efficiency challenges for reinforcement learning agents. We show that one can learn object-interaction tasks from scratch without supervision by learning an attentive object-model as an auxiliary task.
  arXiv  Detail & Related papers  (2020-10-28T19:27:26Z)
• Dynamic Federated Learning [57.14673504239551]
  Federated learning has emerged as an umbrella term for centralized coordination strategies in multi-agent environments. We consider a federated learning model where at every iteration, a random subset of available agents perform local updates based on their data. Under a non-stationary random walk model on the true minimizer for the aggregate optimization problem, we establish that the performance of the architecture is determined by three factors, namely, the data variability at each agent, the model variability across all agents, and a tracking term that is inversely proportional to the learning rate of the algorithm.
  arXiv  Detail & Related papers  (2020-02-20T15:00:54Z)

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.