EnergyAction: Unimanual to Bimanual Composition with Energy-Based Models

• URL: http://arxiv.org/abs/2603.20236v1
• Date: Mon, 09 Mar 2026 04:50:17 GMT
• Title: EnergyAction: Unimanual to Bimanual Composition with Energy-Based Models
• Abstract summary: EnergyAction is a novel framework that compositionally transfers unimanual manipulation policies to bimanual tasks.<n>First, we model individual unimanual policies as EBMs and leverage their compositional properties to compose left and right arm actions.<n>Second, we introduce an energy-based temporal-spatial coordination mechanism through energy constraints.<n>Third, we propose two different energy-aware denoising strategies that dynamically adapt denoising steps based on action quality assessment.
• Score: 73.21721376238233
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Recent advances in unimanual manipulation policies have achieved remarkable success across diverse robotic tasks through abundant training data and well-established model architectures. However, extending these capabilities to bimanual manipulation remains challenging due to the lack of bimanual demonstration data and the complexity of coordinating dual-arm actions. Existing approaches either rely on extensive bimanual datasets or fail to effectively leverage pre-trained unimanual policies. To address this limitation, we propose \textbf{EnergyAction}, a novel framework that compositionally transfers unimanual manipulation policies to bimanual tasks through the Energy-Based Models (EBMs). Specifically, our method incorporates three key innovations. First, we model individual unimanual policies as EBMs and leverage their compositional properties to compose left and right arm actions, enabling the fusion of unimanual policies into a bimanual policy. Second, we introduce an energy-based temporal-spatial coordination mechanism through energy constraints, ensuring the generated bimanual actions are both temporal coherence and spatial feasibility. Third, we propose two different energy-aware denoising strategies that dynamically adapt denoising steps based on action quality assessment. These strategies ensure the generation of high-quality actions while maintaining superior computational efficiency compared to fixed-step denoising approaches. Experimental results demonstrate that EnergyAction effectively transfers unimanual knowledge to bimanual tasks, achieving superior performance on both simulated and real-world tasks with minimal bimanual data.

Related papers

• Unified Learning of Temporal Task Structure and Action Timing for Bimanual Robot Manipulation [11.051601535345819]
  Temporal task structure is fundamental for bimanual manipulation.<n>Existing approaches address these two levels in isolation.<n>This work presents an approach for learning both symbolic and subsymbolic temporal task constraints from human demonstrations.
  arXiv  Detail & Related papers  (2026-03-06T18:25:42Z)
• Primary-Fine Decoupling for Action Generation in Robotic Imitation [91.2899765310853]
  Multi-modal distribution in robotic manipulation action sequences poses critical challenges for imitation learning.<n>We propose Primary-Fine Decoupling for Action Generation (PF-DAG), a two-stage framework that decouples coarse action consistency from fine-grained variations.<n>PF-DAG outperforms state-of-the-art baselines across 56 tasks from Adroit, DexArt, and MetaWorld benchmarks.
  arXiv  Detail & Related papers  (2026-02-25T08:36:45Z)
• The Price Is Not Right: Neuro-Symbolic Methods Outperform VLAs on Structured Long-Horizon Manipulation Tasks with Significantly Lower Energy Consumption [4.898459173551356]
  Vision-Language-Action (VLA) models have been proposed as a pathway toward generalist robotic policies.<n>We present a head-to-head empirical comparison between a fine-tuned open-weight VLA model 0 and a neuro-symbolic architecture.<n>We evaluate both approaches on structured variants of the Towers of Hanoi manipulation task in simulation.
  arXiv  Detail & Related papers  (2026-02-22T16:22:06Z)
• BiKC+: Bimanual Hierarchical Imitation with Keypose-Conditioned Coordination-Aware Consistency Policies [25.25845809170421]
  We propose a novel keypose-conditioned coordination-aware consistency policy tailored for bimanual manipulation.<n>Our framework instantiates hierarchical imitation learning with a high-level keypose predictor and a low-level trajectory generator.<n>In particular, we devise an innovative approach for identifying bimanual keyposes, considering both robot-centric action features and task-centric operation styles.
  arXiv  Detail & Related papers  (2026-01-17T17:33:18Z)
• Fast Visuomotor Policy for Robotic Manipulation [31.26284715644132]
  Energy Policy is designed for high-frequency robotic tasks and resource-constrained systems.<n>It predicts multimodal actions in a single forward pass, enabling high-precision manipulation at high speed.<n>Results show Energy Policy matches or surpasses the performance of state-of-the-art manipulation methods.
  arXiv  Detail & Related papers  (2025-10-14T13:18:45Z)
• StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representation [56.996371714721995]
  We propose an unsupervised approach that learns a highly compressed two-token state representation.<n>Our representation is efficient, interpretable, and integrates seamlessly into existing VLA-based models.<n>We name our method StaMo for its ability to learn generalizable robotic Motion from compact State representation.
  arXiv  Detail & Related papers  (2025-10-06T17:37:24Z)
• 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)
• 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)
• PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation [68.17081518640934]
  We propose a PrIrmitive-driVen waypOinT-aware world model for Robotic manipulation (PIVOT-R) PIVOT-R consists of a Waypoint-aware World Model (WAWM) and a lightweight action prediction module. Our PIVOT-R outperforms state-of-the-art open-source models on the SeaWave benchmark, achieving an average relative improvement of 19.45% across four levels of instruction tasks.
  arXiv  Detail & Related papers  (2024-10-14T11:30:18Z)
• BiKC: Keypose-Conditioned Consistency Policy for Bimanual Robotic Manipulation [48.08416841005715]
  We introduce a novel keypose-conditioned consistency policy tailored for bimanual manipulation. It is a hierarchical imitation learning framework that consists of a high-level keypose predictor and a low-level trajectory generator. Simulated and real-world experimental results demonstrate that the proposed approach surpasses baseline methods in terms of success rate and operational efficiency.
  arXiv  Detail & Related papers  (2024-06-14T14:49:12Z)

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.