A Physical Imitation Learning Pipeline for Energy-Efficient Quadruped Locomotion Assisted by Parallel Elastic Joint

• URL: http://arxiv.org/abs/2604.00611v1
• Date: Wed, 01 Apr 2026 08:13:54 GMT
• Title: A Physical Imitation Learning Pipeline for Energy-Efficient Quadruped Locomotion Assisted by Parallel Elastic Joint
• Abstract summary: We introduce Physical Imitation Learning (PIL), which distils a Reinforcement Learning (RL) control policy into physically implementable body responses.<n>The results are an overall reduced energy consumption thanks to outsourcing parts of the control policy to the PEJs.
• Score: 1.5385430249576606
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Due to brain-body co-evolution, animals' intrinsic body dynamics play a crucial role in energy-efficient locomotion, which shares control effort between active muscles and passive body dynamics -- a principle known as Embodied Physical Intelligence. In contrast, robot bodies are often designed with one centralised controller that typically suppress the intrinsic body dynamics instead of exploiting it. We introduce Physical Imitation Learning (PIL), which distils a Reinforcement Learning (RL) control policy into physically implementable body responses that can be directly offloaded to passive Parallel Elastic Joints (PEJs), enabling therefore the body to imitate part of the controlled behaviour. Meanwhile, the residual policy commands the motors to recover the RL policy's performance. The results is an overall reduced energy consumption thanks to outsourcing parts of the control policy to the PEJs. Here we show in simulated quadrupeds, that our PIL approach can offloads up to 87% of mechanical power to PEJs on flat terrain and 18% on rough terrain. Because the body design is distilled from -- rather than jointly optimised with -- the control policy, PIL realises brain-body co-design without expanding the search space with body design parameters, providing a computationally efficient route to task-specific Embodied Physical Intelligence applicable to a wide range of joint-based robot morphologies.

Related papers

• Learn Weightlessness: Imitate Non-Self-Stabilizing Motions on Humanoid Robot [56.377161933570335]
  Humans naturally exploit a "weightless" state during non-self-stabilizing (NSS) motions.<n>Inspired by this biological mechanism, we propose a weightlessness-state auto-labeling strategy for dataset annotation.<n>Our work bridges the gap between precise trajectory tracking and adaptive environmental interaction, offering a biologically-inspired solution for contact-rich humanoid control.
  arXiv  Detail & Related papers  (2026-04-23T07:10:05Z)
• Scaling Whole-Body Human Musculoskeletal Behavior Emulation for Specificity and Diversity [11.002363474183683]
  We introduce a large-scale parallel musculoskeletal computation framework for biomechanically grounded whole-body motion reproduction.<n>It achieves high joint angle accuracy and body position alignment for highly dynamic tasks such as dance, cartwheel, and backflip.<n>This work establishes a tractable computational route to analyzing the specificity and diversity underlying human embodied control of movement.
  arXiv  Detail & Related papers  (2026-03-31T06:55:10Z)
• PhysMoDPO: Physically-Plausible Humanoid Motion with Preference Optimization [55.25800735159481]
  Whole-Body Controller (WBC) converts diffusion-generated motions into executable trajectories.<n>WBC trajectories become compliant with physics, but they may expose substantial deviations from original motion.<n>We propose PhysMoDPO, a Direct Preference Optimization framework.<n> PhysMoDPO results in significant improvements when applied to zero-shot motion transfer in simulation and for real-world deployment on a G1 humanoid robot.
  arXiv  Detail & Related papers  (2026-03-13T17:59:59Z)
• HybridMimic: Hybrid RL-Centroidal Control for Humanoid Motion Mimicking [3.446278503007937]
  HybridMimic is a framework in which a learned policy dynamically modulates a centroidal-model-based controller.<n>It reduces the average base position tracking error by 13% compared to a state-of-the-art RL baseline.
  arXiv  Detail & Related papers  (2026-03-06T17:58:02Z)
• Interaction-Aware Whole-Body Control for Compliant Object Transport [33.233203393813376]
  This paper proposes an interaction-oriented whole-body control (IO-WBC) that functions as an artificial cerebellum.<n>IO-WBC translates upstream (skill-level) commands into stable, physically consistent whole-body behavior under contact.
  arXiv  Detail & Related papers  (2026-03-04T05:50:40Z)
• CHIP: Adaptive Compliance for Humanoid Control through Hindsight Perturbation [70.5382178207975]
  hIsight Perturbation (CHIP) is a plug-and-play module that enables controllable end-effector stiffness.<n>CHIP is easy to implement and requires neither data augmentation nor additional reward tuning.<n>We show that a generalist motion-tracking controller trained with CHIP can perform a diverse set of forceful manipulation tasks.
  arXiv  Detail & Related papers  (2025-12-16T18:56:04Z)
• Reinforcement Learning for Versatile, Dynamic, and Robust Bipedal Locomotion Control [106.32794844077534]
  This paper presents a study on using deep reinforcement learning to create dynamic locomotion controllers for bipedal robots. We develop a general control solution that can be used for a range of dynamic bipedal skills, from periodic walking and running to aperiodic jumping and standing. This work pushes the limits of agility for bipedal robots through extensive real-world experiments.
  arXiv  Detail & Related papers  (2024-01-30T10:48:43Z)
• Grow Your Limits: Continuous Improvement with Real-World RL for Robotic Locomotion [66.69666636971922]
  We present APRL, a policy regularization framework that modulates the robot's exploration over the course of training. APRL enables a quadrupedal robot to efficiently learn to walk entirely in the real world within minutes.
  arXiv  Detail & Related papers  (2023-10-26T17:51:46Z)
• Low-Rank Modular Reinforcement Learning via Muscle Synergy [25.120547719120765]
  Modular Reinforcement Learning (RL) decentralizes the control of multi-joint robots by learning policies for each actuator. We propose a Synergy-Oriented LeARning (SOLAR) framework that exploits the redundant nature of DoF in robot control.
  arXiv  Detail & Related papers  (2022-10-26T16:01:31Z)
• DMAP: a Distributed Morphological Attention Policy for Learning to Locomote with a Changing Body [126.52031472297413]
  We introduce DMAP, a biologically-inspired, attention-based policy network architecture. We show that a control policy based on the proprioceptive state performs poorly with highly variable body configurations. DMAP can be trained end-to-end in all the considered environments, overall matching or surpassing the performance of an oracle agent.
  arXiv  Detail & Related papers  (2022-09-28T16:45:35Z)
• An Energy-Saving Snake Locomotion Gait Policy Using Deep Reinforcement Learning [0.0]
  In this work, a snake locomotion gait policy is developed via deep reinforcement learning (DRL) for energy-efficient control. We apply proximal policy optimization (PPO) to each joint motor parameterized by angular velocity and the DRL agent learns the standard serpenoid curve at each timestep. Comparing to conventional control strategies, the snake robots controlled by the trained PPO agent can achieve faster movement and more energy-efficient locomotion gait.
  arXiv  Detail & Related papers  (2021-03-08T02:06:44Z)

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.