mlsanityData to 14 Oct 2026

Towards Low-Gravity Planetary Exploration using Reinforcement Learning for Walking, Jumping, and In-flight Attitude Control

arXiv 2605.24643 ↗First posted 23 May 2026cs.RO cs.SY eess.SYcited by 0

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

Abstract (arXiv)

This paper presents reinforcement learning (RL) policies for dynamic quadrupedal locomotion in planetary exploration scenarios. Building on a taskoptimized quadruped with a 5-bar leg design, we develop RL policies for walking, vertical jumping, forward jumping, and in-flight attitude control, explicitly tailored to the reduced gravity on Mars. These policies jointly enable such robots to overcome obstacles larger than themselves through coordinated jumping and precise in-flight reorientation for safe landings. We demonstrate Sim2Real transfer of the attitude control policy on the Olympus quadruped through single-axis reorientation tests, while all locomotion policies are validated in simulation. A complete Mars exploration mission scenario demonstrates coordinated policy deployment across challenging terrain. Experimental results show 90deg attitude reorientation in 2.6 seconds, with simulations demonstrating 3.1 meter vertical jumps and 3.9 meter forward jumps under Martian gravity conditions. - Supplementary video: https://www.youtube.com/watch?v=qlSJ3P87A4A

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 11 of its 20 references that are in the map. First posted on arXiv 23 May 2026.

Builds on

11 of 20 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Towards Quadrupedal Jumping and Walking for Dynamic Locomotion using Reinforcement Learning28 Oct
  2. 2024Curriculum-Based Reinforcement Learning for Quadrupedal Jumping: A Reference-free Design29 Jan

Other references · 9

  1. 2020Learning Quadrupedal Locomotion over Challenging Terraincited by 604
  2. 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 319
  3. 2023Orbit: A Unified Simulation Framework for Interactive Robot Learning Environmentscited by 295
  4. 2023Scientific Exploration of Challenging Planetary Analog Environments with a Team of Legged Robotscited by 20
  5. 2021Cat-like Jumping and Landing of Legged Robots in Low-gravity Using Deep Reinforcement Learningcited by 17
  6. 2022Towards Energy Efficient Autonomous Exploration of Mars Lava Tube with a Martian Coaxial Quadrotorcited by 4
  7. 2017Flying, Hopping Pit-Bots for Cave and Lava Tube Exploration on the Moon and Marscited by 2
  8. 2023Design and Experimental Verification of a Jumping Legged Robot for Martian Lava Tube Explorationcited by 2
  9. 2025Olympus: A Jumping Quadruped for Planetary Exploration Utilizing Reinforcement Learning for In-Flight Attitude Controlcited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Integrating Trajectory Optimization and Reinforcement Learning for Quadrupedal Jumping with Terrain-Adaptive Landing
  2. 2026Towards Torque-Driven Reinforcement Learning for Quadruped Locomotion
  3. 2026Learning Safety-Constrained Whole-Body Loco-Manipulation for Lunar Surface Operations ↗
  4. 2023Learning Agile Locomotion on Risky Terrains
  5. 2025Efficient Learning-Based Control of a Legged Robot in Lunar Gravity
  6. 2025Autonomous Legged Mobile Manipulation for Lunar Surface Operations via Constrained Reinforcement Learning ↗
  7. 2025Guided Reinforcement Learning for Omnidirectional 3D Jumping in Quadruped Robots
  8. 2024Reinforcement Learning For Quadrupedal Locomotion: Current Advancements And Future Perspectives