mlsanityData to 14 Oct 2026

Guided Reinforcement Learning for Omnidirectional 3D Jumping in Quadruped Robots

arXiv 2507.16481 ↗First posted 22 Jul 2025cs.RO cs.SY eess.SYcited by 4

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

Abstract (arXiv)

Jumping poses a significant challenge for quadruped robots, despite being crucial for many operational scenarios. While optimisation methods exist for controlling such motions, they are often time-consuming and demand extensive knowledge of robot and terrain parameters, making them less robust in real-world scenarios. Reinforcement learning (RL) is emerging as a viable alternative, yet conventional end-to-end approaches lack efficiency in terms of sample complexity, requiring extensive training in simulations, and predictability of the final motion, which makes it difficult to certify the safety of the final motion. To overcome these limitations, this paper introduces a novel guided reinforcement learning approach that leverages physical intuition for efficient and explainable jumping, by combining B'ezier curves with a Uniformly Accelerated Rectilinear Motion (UARM) model. Extensive simulation and experimental results clearly demonstrate the advantages of our approach over existing alternatives.

Key facts. Cited by 4 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 35 of its 50 references that are in the map. First posted on arXiv 22 Jul 2025.

Builds on

35 of 50 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Leveraging Symmetry in RL-based Legged Locomotion Control26 Mar
  2. 2024Curriculum-Based Reinforcement Learning for Quadrupedal Jumping: A Reference-free Design29 Jan

Other references · 33

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2015Continuous control with deep reinforcement learningcited by 3,407
  3. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 512
  4. 2019Learning agile and dynamic motor skills for legged robotscited by 504
  5. 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 295
  6. 2020Learning Agile Robotic Locomotion Skills by Imitating Animalscited by 251
  7. 2023ANYmal Parkour: Learning Agile Navigation for Quadrupedal Robotscited by 152
  8. 2022Concurrent Training of a Control Policy and a State Estimator for Dynamic and Robust Legged Locomotioncited by 88
  9. 2016Learning Locomotion Skills Using DeepRL: Does the Choice of Action Space Matter?cited by 48
  10. 2022GenLoco: Generalized Locomotion Controllers for Quadrupedal Robotscited by 48
  11. 2022Learning Torque Control for Quadrupedal Locomotioncited by 29
  12. 2021Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Surveycited by 28
21 more
  1. 2020Robust Quadruped Jumping via Deep Reinforcement Learningcited by 27
  2. 2018Clipped Action Policy Gradientcited by 19
  3. 2021Model-free Reinforcement Learning for Robust Locomotion using Demonstrations from Trajectory Optimizationcited by 19
  4. 2023ManyQuadrupeds: Learning a Single Locomotion Policy for Diverse Quadruped Robotscited by 19
  5. 2023Controlling the Solo12 Quadruped Robot with Deep Reinforcement Learningcited by 16
  6. 2022TAMOLS: Terrain-Aware Motion Optimization for Legged Systemscited by 14
  7. 2024Morphological Symmetries in Roboticscited by 13
  8. 2022CACTO: Continuous Actor-Critic with Trajectory Optimization -- Towards global optimalitycited by 12
  9. 2021Contact-timing and Trajectory Optimization for 3D Jumping on Quadruped Robotscited by 10
  10. 2024Cafe-Mpc: A Cascaded-Fidelity Model Predictive Control Framework with Tuning-Free Whole-Body Controlcited by 10
  11. 2022Agile Maneuvers in Legged Robots: a Predictive Control Approachcited by 8
  12. 2023Continuous Versatile Jumping Using Learned Action Residualscited by 8
  13. 2019Training in Task Space to Speed Up and Guide Reinforcement Learningcited by 7
  14. 2023Two-Stage Learning of Highly Dynamic Motions with Rigid and Articulated Soft Quadrupedscited by 7
  15. 2021Online Trajectory Optimization for Dynamic Aerial Motions of a Quadruped Robotcited by 5
  16. 2021Rapid and Reliable Quadruped Motion Planning with Omnidirectional Jumpingcited by 5
  17. 2022An Optimal Motion Planning Framework for Quadruped Jumpingcited by 4
  18. 2024Quadruped-Frog: Rapid Online Optimization of Continuous Quadruped Jumpingcited by 4
  19. 2023Reactive Landing Controller for Quadruped Robotscited by 3
  20. 2023Locosim: an Open-Source Cross-Platform Robotics Frameworkcited by 2
  21. 2023Efficient Reinforcement Learning for Jumping Monopodscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025LocoMamba: Vision-Driven Locomotion via End-to-End Deep Reinforcement Learning with Mambacited by 3
  2. 2026LineRides: Line-Guided Reinforcement Learning for Bicycle Robot Stuntscited by 1
  3. 2025Vision-Proprioception Fusion with Mamba2 in End-to-End Reinforcement Learning for Motion Controlcited by 0
  4. 2026Bicycle Acrobatics with Reinforcement Learningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Towards Quadrupedal Jumping and Walking for Dynamic Locomotion using Reinforcement Learning
  2. 2025Explosive Jumping with Rigid and Articulated Soft Quadrupeds via Example Guided Reinforcement Learning
  3. 2025Integrating Trajectory Optimization and Reinforcement Learning for Quadrupedal Jumping with Terrain-Adaptive Landing
  4. 2024Reinforcement Learning For Quadrupedal Locomotion: Current Advancements And Future Perspectives
  5. 2025Gait in Eight: Efficient On-Robot Learning for Omnidirectional Quadruped Locomotion
  6. 2025Acrobotics: A Generalist Approach to Quadrupedal Robots' Parkour
  7. 2026Towards Torque-Driven Reinforcement Learning for Quadruped Locomotion
  8. 2023A Real-World Quadrupedal Locomotion Benchmark for Offline Reinforcement Learning