mlsanityData to 7 Oct 2026

Imitation Learning from Human Motion Alone Does Not Guarantee Biomechanically Plausible Gait Kinetics

arXiv 2603.12408 ↗First posted 12 Mar 2026cs.RO cs.LGcited by 0

On the map: Offline RL and imitation learning from data → Real-world robot offline RL

Abstract (arXiv)

Motion imitation learning (IL) is increasingly used in robotics and human gait modeling, yet its ability to recover biomechanically consistent joint moments without explicit kinetic information remains unclear. In this study, we examined whether motion imitation alone can estimate reasonable biological joint moments. We compare motion-only IL (MOIL) against a kinetics-aware IL (KAIL) framework that incorporates ground reaction forces (GRF) and center of pressure (CoP) in imitation rewards, with an ablation study to examine the contribution of each kinetic term. Experiments were conducted using walking data from a non-disabled participant at three speeds (0.9, 1.2, and 1.5 m/s). While both MOIL and KAIL achieved comparable kinematic tracking accuracy, MOIL exhibited substantially larger errors in GRF, CoP, and joint moment estimates relative to inverse dynamics references. In contrast, KAIL produced kinetics more consistent with biomechanical values. These findings highlight a fundamental limitation of MOIL approaches, which may lead to erroneous interpretations of gait biomechanics and downstream applications by failing to estimate consistent human-like gait kinetics.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Real-world robot offline RL, one of 13 directions in Offline RL and imitation learning from data. Builds on 16 of its 37 references that are in the map. First posted on arXiv 12 Mar 2026.

Builds on

16 of 37 references.

Closest ancestors · 3

Same direction, newest first

  1. 2025KinTwin: Imitation Learning with Torque and Muscle Driven Biomechanical Models Enables Precise Replication of Able-Bodied and Impaired Movement from Markerless Motion Capture19 May
  2. 2024Learning Speed-Adaptive Walking Agent Using Imitation Learning with Physics-Informed Simulation5 Dec
  3. 2023LocoMuJoCo: A Comprehensive Imitation Learning Benchmark for Locomotion4 Nov

Other references · 13

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challengescited by 145
  3. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 124
  4. 2020Residual Force Control for Agile Human Behavior Imitation and Extended Motion Synthesiscited by 63
  5. 2025OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interactioncited by 57
  6. 2025Humanoid Locomotion and Manipulation: Current Progress and Challenges in Control, Planning, and Learningcited by 52
  7. 2019Deep Imitation Learning for Autonomous Driving in Generic Urban Scenarios with Enhanced Safetycited by 48
  8. 2020Grasping with Chopsticks: Combating Covariate Shift in Model-free Imitation Learning for Fine Manipulationcited by 37
  9. 2025ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learningcited by 34
  10. 2022DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systemscited by 27
  11. 2024Differentiable Biomechanics Unlocks Opportunities for Markerless Motion Capturecited by 18
  12. 2025AirExo-2: Scaling up Generalizable Robotic Imitation Learning with Low-Cost Exoskeletonscited by 17
1 more
  1. 2023Guided Online Distillation: Promoting Safe Reinforcement Learning by Offline Demonstrationcited by 14

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Biomechanical Comparisons Reveal Divergence of Human and Humanoid Gaits ↗
  2. 2026Beyond Kinematics: Benchmarking Simulation Fidelity for Muscle-Driven Imitation Learning
  3. 2023Orientation-Aware Leg Movement Learning for Action-Driven Human Motion Prediction
  4. 2024Exciting Action: Investigating Efficient Exploration for Learning Musculoskeletal Humanoid Locomotion
  5. 2025Biomechanics-Guided Residual Approach to Generalizable Human Motion Generation and Estimation
  6. 2025Think on your feet: Seamless Transition between Human-like Locomotion in Response to Changing Commands
  7. 2025Learning Human Reaching Optimality Principles from Minimal Observation Inverse Reinforcement Learning
  8. 2026Toward Global Intent Inference for Human Motion by Inverse Reinforcement Learning