Model-Informed Safe Reinforcement Learning for Bipedal Locomotion via Step-to-Step Prediction
On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation
Abstract (arXiv)
Humanoid robots promise versatile mobility in cluttered, human-centric environments, but real deployment demands principled safety. Classical model-based gait generators yield interpretable motions but often lack the robustness and adaptability of modern reinforcement learning (RL) based approaches. We propose a model-informed reinforcement learning framework anchored to the analytical Angular Momentum Linear Inverted Pendulum (ALIP) template. We provide a step-to-step safety certificate for ALIP stepping via a discrete exponential control barrier function (DECBF) and use it as (i) a training-time shaping signal and (ii) a runtime action filter that minimally adjusts swing-foot placement to satisfy template-level constraints. Full-order safety is evaluated empirically on the Digit humanoid in MuJoCo with a whole-body controller stack. Compared to an unconstrained baseline, our approach reduces safety-violation events in the reported external-disturbance trial, while larger lateral-velocity transients reveal a safety-tracking tradeoff.
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 29 references that are in the map. First posted on arXiv 28 Sep 2026.
Builds on
16 of 29 references.
References · 16
- 2019Control Barrier Functions: Theory and Applicationscited by 372
- 2023Real-World Humanoid Locomotion with Reinforcement Learningcited by 187
- 2021Reinforcement Learning for Robust Parameterized Locomotion Control of Bipedal Robotscited by 116
- 20213D Underactuated Bipedal Walking via H-LIP based Gait Synthesis and Stepping Stabilizationcited by 9
- 2023Template Model Inspired Task Space Learning for Robust Bipedal Locomotioncited by 9
- 2019Hybrid Zero Dynamics Inspired Feedback Control Policy Design for 3D Bipedal Locomotion using Reinforcement Learningcited by 8
- 2014Momentum Control with Hierarchical Inverse Dynamics on a Torque-Controlled Humanoidcited by 7
- 2021Zero Dynamics, Pendulum Models, and Angular Momentum in Feedback Control of Bipedal Locomotioncited by 6
- 2021Terrain-Adaptive, ALIP-Based Bipedal Locomotion Controller via Model Predictive Control and Virtual Constraintscited by 4
- 2020Inverse Dynamics Control of Compliant Hybrid Zero Dynamic Walkingcited by 3
- 2022Time-Varying ALIP Model and Robust Foot-Placement Control for Underactuated Bipedal Robot Walking on a Swaying Rigid Surfacecited by 3
- 2023Safe Whole-Body Task Space Control for Humanoid Robotscited by 3
4 more
- 2020Dynamic and Versatile Humanoid Walking via Embedding 3D Actuated SLIP Model with Hybrid LIP Based Steppingcited by 2
- 2023Data-Driven Latent Space Representation for Robust Bipedal Locomotion Learningcited by 2
- 2021SLIP Walking over Rough Terrain via H-LIP Stepping and Backstepping-Barrier Function Inspired Quadratic Programcited by 1
- 2022Resolved Motion Control for 3D Underactuated Bipedal Walking using Linear Inverted Pendulum Dynamics and Neural Adaptationcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025SHIELD: Safety on Humanoids via CBFs In Expectation on Learned Dynamics
- 2026MARCH: Model-Assisted Reinforcement Learning for the Perceptive Control of Humanoids over Sparse Footholds
- 2024Enhancing Model-Based Step Adaptation for Push Recovery through Reinforcement Learning of Step Timing and Region
- 2026ResSafe: Learning Safety Filtering with Residual Reinforcement Learning for Humanoids
- 2024Safe Navigation of Bipedal Robots via Koopman Operator-Based Model Predictive Control ↗
- 2024Integrating Model-Based Footstep Planning with Model-Free Reinforcement Learning for Dynamic Legged Locomotion
- 2025RL-augmented Adaptive Model Predictive Control for Bipedal Locomotion over Challenging Terrain
- 2024RL-augmented MPC Framework for Agile and Robust Bipedal Footstep Locomotion Planning and Control