Guiding Energy-Efficient Locomotion through Impact Mitigation Rewards
On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation
Abstract (arXiv)
Animals achieve energy-efficient locomotion by their implicit passive dynamics, a marvel that has captivated roboticists for decades.Recently, methods incorporated Adversarial Motion Prior (AMP) and Reinforcement learning (RL) shows promising progress to replicate Animals' naturalistic motion. However, such imitation learning approaches predominantly capture explicit kinematic patterns, so-called gaits, while overlooking the implicit passive dynamics. This work bridges this gap by incorporating a reward term guided by Impact Mitigation Factor (IMF), a physics-informed metric that quantifies a robot's ability to passively mitigate impacts. By integrating IMF with AMP, our approach enables RL policies to learn both explicit motion trajectories from animal reference motion and the implicit passive dynamic. We demonstrate energy efficiency improvements of up to 32%, as measured by the Cost of Transport (CoT), across both AMP and handcrafted reward structure.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 16 of its 26 references that are in the map. First posted on arXiv 10 Oct 2025.
Builds on
16 of 26 references.
Closest ancestors · 1
Same direction, newest first
- 2024A Learning Framework for Diverse Legged Robot Locomotion Using Barrier-Based Style Rewards24 Sep
Other references · 15
- 2020Learning Agile Robotic Locomotion Skills by Imitating Animalscited by 251
- 2022Adversarial Motion Priors Make Good Substitutes for Complex Reward Functionscited by 89
- 2023Evaluation of Constrained Reinforcement Learning Algorithms for Legged Locomotioncited by 13
- 2023Learning to Walk and Fly with Adversarial Motion Priorscited by 5
- 2021Generative Design of NU's Husky Carbon, A Morpho-Functional, Legged Robotcited by 2
- 2021Optimization-free Ground Contact Force Constraint Satisfaction in Quadrupedal Locomotioncited by 2
- 2022Efficient Path Planning and Tracking for Multi-Modal Legged-Aerial Locomotion Using Integrated Probabilistic Road Maps (PRM) and Reference Governors (RG)cited by 2
- 2022A Letter on Progress Made on Husky Carbon: A Legged-Aerial, Multi-modal Platformcited by 2
- 2023Quadrupedal Locomotion Control On Inclined Surfaces Using Collocation Methodcited by 2
- 2020Towards thruster-assisted bipedal locomotion for enhanced efficiency and robustnesscited by 1
- 2020Thruster-assisted center manifold shaping in bipedal legged locomotioncited by 1
- 2021Unilateral Ground Contact Force Regulations in Thruster-Assisted Legged Locomotioncited by 1
3 more
- 2024Narrow-Path, Dynamic Walking Using Integrated Posture Manipulation and Thrust Vectoringcited by 1
- 2024Optimization free control and ground force estimation with momentum observer for a multimodal legged aerial robotcited by 1
- 2024Enabling steep slope walking on Husky using reduced order modeling and quadratic programmingcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Passive-Dynamic-Walking-Inspired Dynamics Guidance for Energy-Efficient Humanoid Locomotion ↗
- 2026Physical Imitation Learning: Distilling Control Policies into Passive Elasticity
- 2022Energy-based Legged Robots Terrain Traversability Modeling via Deep Inverse Reinforcement Learning
- 2025Motion Priors Reimagined: Adapting Flat-Terrain Skills for Complex Quadruped Mobility
- 2025Towards bridging the gap: Systematic sim-to-real transfer for diverse legged robots
- 2023Manipulator as a Tail: Promoting Dynamic Stability for Legged Locomotion
- 2024Adaptive Energy Regularization for Autonomous Gait Transition and Energy-Efficient Quadruped Locomotion
- 2025NaviGait: Navigating Dynamically Feasible Gait Libraries using Deep Reinforcement Learning