mlsanityData to 14 Oct 2026

CPG-RL: Learning Central Pattern Generators for Quadruped Locomotion

arXiv 2211.00458 ↗First posted 1 Nov 2022cs.RO cs.AI cs.LGcited by 34

Not on the map. Why?

Abstract (arXiv)

In this letter, we present a method for integrating central pattern generators (CPGs), i.e. systems of coupled oscillators, into the deep reinforcement learning (DRL) framework to produce robust and omnidirectional quadruped locomotion. The agent learns to directly modulate the intrinsic oscillator setpoints (amplitude and frequency) and coordinate rhythmic behavior among different oscillators. This approach also allows the use of DRL to explore questions related to neuroscience, namely the role of descending pathways, interoscillator couplings, and sensory feedback in gait generation. We train our policies in simulation and perform a sim-to-real transfer to the Unitree A1 quadruped, where we observe robust behavior to disturbances unseen during training, most notably to a dynamically added 13.75 kg load representing 115% of the nominal quadruped mass. We test several different observation spaces based on proprioceptive sensing and show that our framework is deployable with no domain randomization and very little feedback, where along with the oscillator states, it is possible to provide only contact booleans in the observation space. Video results can be found at https://youtu.be/xqXHLzLsEV4.

Key facts. Cited by 34 papers in the map (data through 14 Oct 2026). Builds on 24 of its 45 references that are in the map. First posted on arXiv 1 Nov 2022.

Builds on

24 of 45 references.

References · 24

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  3. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 604
  4. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 512
  5. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 508
  6. 2019Learning agile and dynamic motor skills for legged robotscited by 504
  7. 2022Learning robust perceptive locomotion for quadrupedal robots in the wildcited by 382
  8. 2016The CMA Evolution Strategy: A Tutorialcited by 377
  9. 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 319
  10. 2020Learning Agile Robotic Locomotion Skills by Imitating Animalscited by 251
  11. 2021Learning Vision-Guided Quadrupedal Locomotion End-to-End with Cross-Modal Transformerscited by 79
  12. 2021Minimizing Energy Consumption Leads to the Emergence of Gaits in Legged Robotscited by 76
12 more
  1. 2019Highly Dynamic Quadruped Locomotion via Whole-Body Impulse Control and Model Predictive Controlcited by 54
  2. 2021Fast and Efficient Locomotion via Learned Gait Transitionscited by 54
  3. 2019Policies Modulating Trajectory Generatorscited by 49
  4. 2021Learning to Jump from Pixelscited by 45
  5. 2022Learning Free Gait Transition for Quadruped Robots via Phase-Guided Controllercited by 29
  6. 2022Learning Torque Control for Quadrupedal Locomotioncited by 29
  7. 2020Robust Quadruped Jumping via Deep Reinforcement Learningcited by 27
  8. 2021Robust High-speed Running for Quadruped Robots via Deep Reinforcement Learningcited by 22
  9. 2021Reinforcement Learning with Evolutionary Trajectory Generator: A General Approach for Quadrupedal Locomotioncited by 14
  10. 2019Training in Task Space to Speed Up and Guide Reinforcement Learningcited by 7
  11. 2020Adaptive Force-based Control for Legged Robotscited by 6
  12. 2021A CPG-Based Agile and Versatile Locomotion Framework Using Proximal Symmetry Losscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 7; 2024: 11; 2025: 7; 2026: 8.

34 papers.

Sort:

By area:

  1. 2023Robust and Versatile Bipedal Jumping Control through Reinforcement Learningcited by 36
  2. 2024Symmetry Considerations for Learning Task Symmetric Robot Policiescited by 28
  3. 2024Leveraging Symmetry in RL-based Legged Locomotion Controlcited by 25
  4. 2024CaT: Constraints as Terminations for Legged Locomotion Reinforcement Learningcited by 23
  5. 2023ManyQuadrupeds: Learning a Single Locomotion Policy for Diverse Quadruped Robotscited by 19
  6. 2024Learning to Walk from Three Minutes of Real-World Data with Semi-structured Dynamics Modelscited by 16
  7. 2022Visual CPG-RL: Learning Central Pattern Generators for Visually-Guided Quadruped Locomotioncited by 14
  8. 2024Residual Policy Learning for Perceptive Quadruped Control Using Differentiable Simulationcited by 13
  9. 2024A Learning Framework for Diverse Legged Robot Locomotion Using Barrier-Based Style Rewardscited by 12
  10. 2023Identifying Important Sensory Feedback for Learning Locomotion Skillscited by 6
  11. 2023Puppeteer and Marionette: Learning Anticipatory Quadrupedal Locomotion Based on Interactions of a Central Pattern Generator and Supraspinal Drivecited by 5
  12. 2023DeepCPG Policies for Robot Locomotioncited by 4
22 more
  1. 2025Disturbance-Aware Adaptive Compensation in Hybrid Force-Position Locomotion Policy for Legged Robotscited by 3
  2. 2023DeepTransition: Viability Leads to the Emergence of Gait Transitions in Learning Anticipatory Quadrupedal Locomotion Skillscited by 2
  3. 2024Neural Circuit Architectural Priors for Quadruped Locomotioncited by 2
  4. 2025Coordinated Humanoid Robot Locomotion with Symmetry Equivariant Reinforcement Learning Policycited by 2
  5. 2024Learning Emergent Gaits with Decentralized Phase Oscillators: on the role of Observations, Rewards, and Feedbackcited by 1
  6. 2024Behavior evolution-inspired approach to walking gait reinforcement training for quadruped robotscited by 1
  7. 2025SATA: Safe and Adaptive Torque-Based Locomotion Policies Inspired by Animal Learningcited by 1
  8. 2026GPO: Growing Policy Optimization for Legged Robot Locomotion and Whole-Body Controlcited by 1
  9. 2026Agile perceptive multi-skill locomotion for quadrupedal robots in the wildcited by 1
  10. 2023A Central Motor System Inspired Pre-training Reinforcement Learning for Robotic Controlcited by 0
  11. 2024Hierarchical learning control for autonomous robots inspired by central nervous systemcited by 0
  12. 2024Latent Action Priors for Locomotion with Deep Reinforcement Learningcited by 0
  13. 2025SpikingSoft: A Spiking Neuron Controller for Bio-inspired Locomotion with Soft Snake Robotscited by 0
  14. 2025PALo: Learning Posture-Aware Locomotion for Quadruped Robotscited by 0
  15. 2025RANDPOL: Parameter-Efficient End-to-End Quadruped Locomotion via Randomized Policy Learningcited by 0
  16. 2025PGTT: Phase-Guided Terrain Traversal for Perceptive Legged Locomotioncited by 0
  17. 2026Benefits of Low-Cost Bio-Inspiration in the Age of Overparametrizationcited by 0
  18. 2026Neuromorphic Reinforcement Learning for Quadruped Locomotion Control on Uneven Terraincited by 0
  19. 2026ARC-RL: A Reinforcement Learning Playground Inspired by ARC Raiderscited by 0
  20. 2026SRL: Combining SLIP Model and Reinforcement Learning for Agile Robotic Jumpingcited by 0
  21. 2026WARL: Wrench-Augmented Reinforcement Learning for Task-Agnostic Learning in Legged Robotscited by 0
  22. 2026GLAMDRING: Gait Learning And Morphology co-Design via Reinforcement LearnING of CPGscited by 0