Morphologically Symmetric Reinforcement Learning for Ambidextrous Bimanual Manipulation

• URL: http://arxiv.org/abs/2505.05287v2
• Date: Mon, 01 Sep 2025 18:49:59 GMT
• Title: Morphologically Symmetric Reinforcement Learning for Ambidextrous Bimanual Manipulation
• Abstract summary: We introduce SYMDEX, a reinforcement learning framework for ambidextrous bi-manipulation.<n>By exploiting bilateral symmetry via equivariant neural networks, experience from one arm is inherently leveraged by the opposite arm.<n>Our approach strongly outperforms baselines on complex task in which the left and right hands perform different roles.
• Score: 12.053370079908325
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Humans naturally exhibit bilateral symmetry in their gross manipulation skills, effortlessly mirroring simple actions between left and right hands. Bimanual robots-which also feature bilateral symmetry-should similarly exploit this property to perform tasks with either hand. Unlike humans, who often favor a dominant hand for fine dexterous skills, robots should ideally execute ambidextrous manipulation with equal proficiency. To this end, we introduce SYMDEX (SYMmetric DEXterity), a reinforcement learning framework for ambidextrous bi-manipulation that leverages the robot's inherent bilateral symmetry as an inductive bias. SYMDEX decomposes complex bimanual manipulation tasks into per-hand subtasks and trains dedicated policies for each. By exploiting bilateral symmetry via equivariant neural networks, experience from one arm is inherently leveraged by the opposite arm. We then distill the subtask policies into a global ambidextrous policy that is independent of the hand-task assignment. We evaluate SYMDEX on six challenging simulated manipulation tasks and demonstrate successful real-world deployment on two of them. Our approach strongly outperforms baselines on complex task in which the left and right hands perform different roles. We further demonstrate SYMDEX's scalability by extending it to a four-arm manipulation setup, where our symmetry-aware policies enable effective multi-arm collaboration and coordination. Our results highlight how structural symmetry as inductive bias in policy learning enhances sample efficiency, robustness, and generalization across diverse dexterous manipulation tasks.

Related papers

• Towards Human-level Dexterous Teleoperation [62.77371751776912]
  Human-level dexterous teleoperation requires precise control of object motion via dynamic hand-object contact.<n>We introduce TeleDexter, a hand-object co-tracking controller that maps operator intent into learned, low-level contact execution.<n>We evaluate TeleDexter on seven challenging dexterous teleoperation tasks spanning object reorientation and long-horizon tool use across two dexterous hands.
  arXiv  Detail & Related papers  (2026-07-13T12:36:47Z)
• Morphologically Equivariant Flow Matching for Bimanual Mobile Manipulation [25.389467312557127]
  morphological symmetry is an underexplored but crucial inductive bias for learning in bimanual mobile manipulation.<n>Knowing how to solve a task in one configuration directly determines how to solve its mirrored counterpart.<n>Across planar and 6-DoF mobile manipulation tasks, symmetry-informed policies consistently improve sample efficiency.
  arXiv  Detail & Related papers  (2026-05-12T15:04:38Z)
• EquiBim: Learning Symmetry-Equivariant Policy for Bimanual Manipulation [6.9686350006975]
  We introduce EquiBim, a symmetry-equivariant policy learning framework for bimanual manipulation.<n>Our approach formulates physical symmetry as a group action on both observation and action spaces.<n>We evaluate it across diverse observation and action configurations in simulation and validate it on a real-world dual-arm system.
  arXiv  Detail & Related papers  (2026-03-09T16:09:18Z)
• ManiGaussian++: General Robotic Bimanual Manipulation with Hierarchical Gaussian World Model [52.02220087880269]
  We propose an extension of ManiGaussian framework that improves bimanual manipulation by digesting multi-task scene dynamics through a hierarchical world model.<n>Our method significantly outperforms the current state-of-the-art bimanual manipulation techniques by an improvement of 20.2% in 10 simulated tasks, and 60% success rate on average in 9 challenging real-world tasks.
  arXiv  Detail & Related papers  (2025-06-24T17:59:06Z)
• Learning Bimanual Manipulation via Action Chunking and Inter-Arm Coordination with Transformers [4.119006369973485]
  We focus on coordination and efficiency between both arms, particularly synchronized actions.<n>We propose a novel imitation learning architecture that predicts cooperative actions.<n>Our model demonstrated a high success rate for comparison and suggested a suitable architecture for the policy learning of bimanual manipulation.
  arXiv  Detail & Related papers  (2025-03-18T05:20:34Z)
• Rethinking Bimanual Robotic Manipulation: Learning with Decoupled Interaction Framework [51.39847596489193]
  Bimanual robotic manipulation is an emerging and critical topic in the robotics community.<n>We propose a novel decoupled interaction framework that considers the characteristics of different tasks in bimanual manipulation.<n>Our framework achieves outstanding performance, with a 23.5% boost over the SOTA method.
  arXiv  Detail & Related papers  (2025-03-12T09:28:41Z)
• Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids [56.892520712892804]
  We introduce a practical sim-to-real RL recipe that trains a humanoid robot to perform three dexterous manipulation tasks.<n>We demonstrate high success rates on unseen objects and robust, adaptive policy behaviors.
  arXiv  Detail & Related papers  (2025-02-27T18:59:52Z)
• Modality-Driven Design for Multi-Step Dexterous Manipulation: Insights from Neuroscience [14.49331945543691]
  Multi-step dexterous manipulation is a fundamental skill in household scenarios, yet remains an underexplored area in robotics.<n>This paper proposes a modular approach, where each step of the manipulation process is addressed with dedicated policies based on effective modality input.
  arXiv  Detail & Related papers  (2024-12-15T23:05:16Z)
• DexHandDiff: Interaction-aware Diffusion Planning for Adaptive Dexterous Manipulation [78.60543357822957]
  Dexterous manipulation with contact-rich interactions is crucial for advanced robotics.<n>We introduce DexHandDiff, an interaction-aware diffusion planning framework for adaptive dexterous manipulation.<n>Our framework achieves an average of 70.7% success rate on goal adaptive dexterous tasks, highlighting its robustness and flexibility in contact-rich manipulation.
  arXiv  Detail & Related papers  (2024-11-27T18:03:26Z)
• Cross-Embodiment Dexterous Grasping with Reinforcement Learning [29.867524903691802]
  Dexterous hands exhibit significant potential for complex real-world grasping tasks. We study the learning of cross-embodiment dexterous grasping policies using reinforcement learning. Our approach demonstrates an 80% success rate in grasping objects from the YCB dataset.
  arXiv  Detail & Related papers  (2024-10-03T13:36:02Z)
• Symmetry Considerations for Learning Task Symmetric Robot Policies [12.856889419651521]
  Symmetry is a fundamental aspect of many real-world robotic tasks. Current deep reinforcement learning (DRL) approaches can seldom harness and exploit symmetry effectively.
  arXiv  Detail & Related papers  (2024-03-07T09:41:11Z)
• Twisting Lids Off with Two Hands [82.21668778600414]
  We show how policies trained in simulation can be effectively and efficiently transferred to the real world. Specifically, we consider the problem of twisting lids of various bottle-like objects with two hands. This is the first sim-to-real RL system that enables such capabilities on bimanual multi-fingered hands.
  arXiv  Detail & Related papers  (2024-03-04T18:59:30Z)
• Left/Right Brain, human motor control and the implications for robotics [0.5062312533373298]
  This research explores a bilateral neural network architecture as a control system for motor tasks. We aimed to achieve hemispheric specialisation similar to what is observed in humans across different tasks.
  arXiv  Detail & Related papers  (2024-01-25T10:29:07Z)
• RObotic MAnipulation Network (ROMAN) $\unicode{x2013}$ Hybrid Hierarchical Learning for Solving Complex Sequential Tasks [70.69063219750952]
  We present a Hybrid Hierarchical Learning framework, the Robotic Manipulation Network (ROMAN) ROMAN achieves task versatility and robust failure recovery by integrating behavioural cloning, imitation learning, and reinforcement learning. Experimental results show that by orchestrating and activating these specialised manipulation experts, ROMAN generates correct sequential activations for accomplishing long sequences of sophisticated manipulation tasks.
  arXiv  Detail & Related papers  (2023-06-30T20:35:22Z)
• Dexterous Manipulation from Images: Autonomous Real-World RL via Substep Guidance [71.36749876465618]
  We describe a system for vision-based dexterous manipulation that provides a "programming-free" approach for users to define new tasks. Our system includes a framework for users to define a final task and intermediate sub-tasks with image examples. experimental results with a four-finger robotic hand learning multi-stage object manipulation tasks directly in the real world.
  arXiv  Detail & Related papers  (2022-12-19T22:50:40Z)
• 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.