mlsanityData to 14 Oct 2026

A Learning Framework for Diverse Legged Robot Locomotion Using Barrier-Based Style Rewards

arXiv 2409.15780 ↗First posted 24 Sep 2024cs.ROcited by 12

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

This work introduces a model-free reinforcement learning framework that enables various modes of motion (quadruped, tripod, or biped) and diverse tasks for legged robot locomotion. We employ a motion-style reward based on a relaxed logarithmic barrier function as a soft constraint, to bias the learning process toward the desired motion style, such as gait, foot clearance, joint position, or body height. The predefined gait cycle is encoded in a flexible manner, facilitating gait adjustments throughout the learning process. Extensive experiments demonstrate that KAIST HOUND, a 45 kg robotic system, can achieve biped, tripod, and quadruped locomotion using the proposed framework; quadrupedal capabilities include traversing uneven terrain, galloping at 4.67 m/s, and overcoming obstacles up to 58 cm (67 cm for HOUND2); bipedal capabilities include running at 3.6 m/s, carrying a 7.5 kg object, and ascending stairs-all performed without exteroceptive input.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 24 of its 35 references that are in the map. First posted on arXiv 24 Sep 2024.

Builds on

24 of 35 references.

References · 24

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2021Convex optimizationcited by 2,515
  3. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 604
  4. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 512
  5. 2019Learning agile and dynamic motor skills for legged robotscited by 504
  6. 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 382
  7. 2017Asymmetric Actor Critic for Image-Based Robot Learningcited by 238
  8. 2018DeepMimic: Example-Guided Deep Reinforcement Learning of Physics-Based Character Skillscited by 163
  9. 2019IPO: Interior-point Policy Optimization under Constraintscited by 132
  10. 2020Sim-to-Real Learning of All Common Bipedal Gaits via Periodic Reward Compositioncited by 96
  11. 2022Adversarial Motion Priors Make Good Substitutes for Complex Reward Functionscited by 89
  12. 2022Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotioncited by 88
12 more
  1. 2023DreamWaQ: Learning Robust Quadrupedal Locomotion With Implicit Terrain Imagination via Deep Reinforcement Learningcited by 66
  2. 2019Highly Dynamic Quadruped Locomotion via Whole-Body Impulse Control and Model Predictive Controlcited by 54
  3. 2023Not Only Rewards But Also Constraints: Applications on Legged Robot Locomotioncited by 47
  4. 2022Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learningcited by 37
  5. 2022OPT-Mimic: Imitation of Optimized Trajectories for Dynamic Quadruped Behaviorscited by 35
  6. 2022Optimization-Based Control for Dynamic Legged Robotscited by 35
  7. 2022CPG-RL: Learning Central Pattern Generators for Quadruped Locomotioncited by 34
  8. 2019Feedback MPC for Torque-Controlled Legged Robotscited by 21
  9. 2024RobotKeyframing: Learning Locomotion with High-Level Objectives via Mixture of Dense and Sparse Rewardscited by 18
  10. 2023Evaluation of Constrained Reinforcement Learning Algorithms for Legged Locomotioncited by 13
  11. 2024Barrier Functions Inspired Reward Shaping for Reinforcement Learningcited by 11
  12. 2023Imitating and Finetuning Model Predictive Control for Robust and Symmetric Quadrupedal Locomotioncited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 6; 2026: 6.

12 papers.

  1. 2025Spectral Normalization for Lipschitz-Constrained Policies on Learning Humanoid Locomotioncited by 3
  2. 2026Learning Gait-Aware Quadruped Locomotion with Temporal Logic Specificationscited by 2
  3. 2025GRoQ-LoCO: Generalist and Robot-agnostic Quadruped Locomotion Control using Offline Datasetscited by 1
  4. 2026MPC-Injection: Biasing Off-Policy Locomotion RL Toward Controller-Induced Behavior Basinscited by 1
  5. 2026Agile perceptive multi-skill locomotion for quadrupedal robots in the wildcited by 1
  6. 2025Development of a PPO-Reinforcement Learned Walking Tripedal Soft-Legged Robot using SOFAcited by 0
  7. 2025Learning Impact-Rich Rotational Maneuvers via Centroidal Velocity Rewards and Sim-to-Real Techniques: A One-Leg Hopper Flip Case Studycited by 0
  8. 2025Guiding Energy-Efficient Locomotion through Impact Mitigation Rewardscited by 0
  9. 2025Reinforcement Learning-based Robust Wall Climbing Locomotion Controller in Ferromagnetic Environmentcited by 0
  10. 2026Beyond Safety Filtering: Control Barrier Function-Informed Reinforcement Learning for Connected and Automated Vehiclescited by 0
  11. 2026From LLM-Generated Specifications to Learned Quadruped Locomotioncited by 0
  12. 2026OmniMimic: Dynamics-completed Motion Augmentation for Multi-style Omnidirectional Quadruped Locomotioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Learning Robust, Agile, Natural Legged Locomotion Skills in the Wild
  2. 2025Whole-Body Constrained Learning for Legged Locomotion via Hierarchical Optimization
  3. 2024Experience-Learning Inspired Two-Step Reward Method for Efficient Legged Locomotion Learning Towards Natural and Robust Gaits
  4. 2025Gait-Conditioned Reinforcement Learning with Multi-Phase Curriculum for Humanoid Locomotion
  5. 2025Bipedalism for Quadrupedal Robots: Versatile Loco-Manipulation through Risk-Adaptive Reinforcement Learning
  6. 2025A Gait Driven Reinforcement Learning Framework for Humanoid Robots
  7. 2025Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion
  8. 2024Adaptive Energy Regularization for Autonomous Gait Transition and Energy-Efficient Quadruped Locomotion