Energy-Efficient Arm Reaching for a Humanoid Robot via Deep Reinforcement Learning with Identified Power Models

• URL: http://arxiv.org/abs/2606.15918v1
• Date: Sun, 14 Jun 2026 16:46:18 GMT
• Title: Energy-Efficient Arm Reaching for a Humanoid Robot via Deep Reinforcement Learning with Identified Power Models
• Abstract summary: This paper presents an end-to-end, energy-aware reinforcement learning framework for the 7-degree-of-freedom left arm of the UnitreeG1 humanoid robot.<n>The policy is validated over three independent 10-target batches, achieving a mean energy of $71.5 pm 48.3$,J, an end-effector position error of $2.64 pm 1.04$,cm, and an orientation error of $6.92 pm 1.33circ$ -- within the SI4centimetre/$8.6circ$ training tolerance.
• Score: 44.9566685062534
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Humanoid robots performing in-field manipulation tasks, such as robotic apple harvesting, face severe energy constraints that directly limit the number of reaching motions that can be executed per battery charge. This paper presents an end-to-end, energy-aware reinforcement learning framework for the 7-degree-of-freedom left arm of the Unitree~G1 humanoid robot, combining a physics-based, experimentally identified electrical power model with a Soft Actor-Critic (SAC) policy trained in a Pinocchio-based rigid-body dynamics simulator. The RL policy operates on an incremental joint-position action space and is trained with a Hybrid Constellation Reward that combines a four-point end-effector constellation distance with a torque-norm energy proxy; after % $5\times10^6$ training it reaches a $69.9\%$ success rate over $1\,000$ random targets in kinematic simulation, at a mean energy of \SI{98.16}{\joule} on successful episodes. Finally, on the physical Unitree~G1, the policy is validated over three independent 10-target batches, achieving a mean energy of $71.5 \pm 48.3$\,J, an end-effector position error of $2.64 \pm 1.04$\,cm, and an orientation error of $6.92 \pm 1.33^\circ$ -- within the \SI{4}{\centi\metre}/$8.6^\circ$ training tolerance. These results constitute a first step toward energy-aware reinforcement-learning-based arm reaching for humanoid robots.

Related papers

• GigaBrain-WBC-0.5: A Behavior World Model for Robust Whole-Body Control with Environment Interaction [68.67772166423812]
  We present GigaBrain-WBC-0.5, the first Behavior World Model (BWM) for humanoid whole-body control.<n>Rather than a purely reactive tracker, we train a causal Transformer to jointly predict its next action, next state, and the distribution over its next latent behavior command.<n>An automatic terrain-annotation pipeline recovers full 3D contact geometry from retargeted motion, enabling terrain annotation at the scale of existing motion datasets.
  arXiv  Detail & Related papers  (2026-08-18T18:21:36Z)
• NeuralActuator: Neural Actuation Modeling for Robot Dynamics and External Force Perception [32.4225008514158]
  Differentiable simulators have advanced policy learning and model-based control across robotic tasks.<n>We present NeuralActuator, which jointly predicts (i) a torque surrogate for trajectory propagation on low-cost servo platforms.<n>We also demonstrate motor-condition estimation and improved behavior-cloning performance using NeuralActuator as a pretrained module.
  arXiv  Detail & Related papers  (2026-07-13T15:58:34Z)
• Do Rigid-Body Simulators Dream of Soft Robots? Learning Contact-Rich Manipulation for Tendon-Driven Continuum Robots [4.338766069286991]
  We bridge the gap for tendon-driven continuum robots by deriving a continuum-mechanics-informed discretization.<n>This is the first demonstration of sim-to-real transfer for contact-rich manipulation with continuum robots.
  arXiv  Detail & Related papers  (2026-06-21T09:02:53Z)
• DataLadder: A Simulation-Enabled Interconversion Toolchain for the Embodied Data Pyramid [63.45560198934907]
  Generalist robot policies require trustworthy evaluation and robot-usable training data.<n>We present DataLadder, a simulation-enabled interconversion toolchain for human-robot aligned model evaluation and data generation.<n>We package the core reconstruction, simulation, rendering, and realism-augmentation modules as cloud services on JD Cloud.
  arXiv  Detail & Related papers  (2026-06-15T14:21:35Z)
• Data-Driven Autoregressive Power Prediction for GTernal Robots in the Robotarium [0.0]
  Energy-aware algorithms for multi-robot systems require accurate power consumption models.<n>We present a lightweight autoregressive predictor for the GTernal mobile robot platform deployed in the Georgia Tech Robotarium.
  arXiv  Detail & Related papers  (2026-03-14T11:43:42Z)
• EasyMimic: A Low-Cost Framework for Robot Imitation Learning from Human Videos [51.158081196253626]
  EasyMimic is a framework that enables robots to learn manipulation policies from human video demonstrations.<n>Our method first extracts 3D hand trajectories from the videos.<n>An action alignment module then maps these trajectories to the gripper control space of a low-cost robot.
  arXiv  Detail & Related papers  (2026-02-12T00:41:01Z)
• RobotDancing: Residual-Action Reinforcement Learning Enables Robust Long-Horizon Humanoid Motion Tracking [50.200035833530876]
  RobotDancing is a simple, scalable framework that predicts residual joint targets to explicitly correct dynamics discrepancies.<n>It can track multi-minute, high-energy behaviors (jumps, spins, cartwheels) and deploys zero-shot to hardware with high motion tracking quality.
  arXiv  Detail & Related papers  (2025-09-25T03:30:34Z)
• FLARE: Robot Learning with Implicit World Modeling [87.81846091038676]
  $textbfFLARE$ integrates predictive latent world modeling into robot policy learning.<n>$textbfFLARE$ achieves state-of-the-art performance, outperforming prior policy learning baselines by up to 26%.<n>Our results establish $textbfFLARE$ as a general and scalable approach for combining implicit world modeling with high-frequency robotic control.
  arXiv  Detail & Related papers  (2025-05-21T15:33:27Z)
• ManyQuadrupeds: Learning a Single Locomotion Policy for Diverse Quadruped Robots [4.557963624437784]
  We show that drawing inspiration from animal motor control allows us to effectively train a single locomotion policy for quadruped robots. Our policy modulates a representation of the Central Pattern Generator (CPG) in the spinal cord. We observe robust performance, even when adding a 15 kg load, equivalent to 125% of the A1 robot's nominal mass.
  arXiv  Detail & Related papers  (2023-10-16T15:06:16Z)
• Learning Bipedal Walking for Humanoids with Current Feedback [5.429166905724048]
  We present an approach for overcoming the sim2real gap issue for humanoid robots arising from inaccurate torque-tracking at the actuator level. Our approach successfully trains a unified, end-to-end policy in simulation that can be deployed on a real HRP-5P humanoid robot to achieve bipedal locomotion.
  arXiv  Detail & Related papers  (2023-03-07T08:16:46Z)
• REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer [57.045140028275036]
  We consider the problem of transferring a policy across two different robots with significantly different parameters such as kinematics and morphology. Existing approaches that train a new policy by matching the action or state transition distribution, including imitation learning methods, fail due to optimal action and/or state distribution being mismatched in different robots. We propose a novel method named $REvolveR$ of using continuous evolutionary models for robotic policy transfer implemented in a physics simulator.
  arXiv  Detail & Related papers  (2022-02-10T18:50:25Z)

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.