space-robots.org/papers

Browse This week Top picks Missions About Feeds Reading list0 Jobs ↗

space-robots.org / papers

A Space Robots community project. Metadata from arXiv, OpenAlex, NASA NTRS, Crossref and Semantic Scholar.

Inclusion rules Feeds & API Jobs space-robots.org

Top papers of the week / 2026-W43

Benchmarks for free-floating capture, lunar legged locomotion, and onboard language models

Oct 19 – Oct 25, 2026 / curated by Space Robots

A strong week for open tools: a capture benchmark built on ISS hardware and an open lunar rover simulator with shadow ground truth. Alongside them, several takes on legged mobility in lunar gravity.

#1AstroBench: Benchmarking Free-Floating Capture and Space Robotic Manipulation
Zizhe Wang, Jia Deng, Xin Lu, Zehao Jia +6 morePreprint 2026Oct 22, 2026
An open benchmark for capturing free-floating objects with a fixed-base arm. Its tasks are modeled on MELFI sample storage and Robotic Refueling Mission servicing hardware.
Space × RoboticsORBITAL ROBOTICS IN-SPACE SERVICING Manipulation & Grasping Simulation, Digital Twins & Benchmarks Learning-based Methods
PDF HTML Code arXiv
Oct 22, 2026
#2MARE: An Open-Source Lunar Rover Simulator with Shadow Ground Truth for Perception and Autonomy
Raúl Castilla-Arquillo, Miguel Olivares-MendezPreprint 2026Oct 20, 2026
MARE: an open-source lunar rover simulator with ground truth for long polar shadows, aimed at perception and navigation development under extreme illumination.
Space × Robotics × AIPLANETARY ROBOTICS Perception & State Estimation Surface Mobility & Terramechanics Guidance, Dynamics & Control
PDF HTML Code arXiv
Oct 20, 2026
#3Compressing Onboard Language Models for Space Robots under a Behavioral-Fidelity Requirement
Jia Deng, Zizhe Wang, Xin Lu, Yi Huang +1 morePreprint 2026Oct 21, 2026
Treats low-bit compression of an onboard language model as a ground-segment step. Each module is assigned to a quantizer so the static flight artifact stays behaviorally close to the full-precision model.
Space × Robotics × AIFoundation Models & LLMs Learning-based Methods
PDF HTML arXiv
Oct 21, 2026
#4Do Earth-Trained Humanoid Controllers Walk on the Moon? Gravity, Terrain, and Soil Transfer
Guillem Casadesus Vila, Sri Aditya Deevi, Grace X. GaoPreprint 2026Oct 21, 2026
Twelve training strategies for a simulated Unitree G1 compared across gravity, terrain and granular soil. Earth-trained controllers keep falling on the Moon, and Moon-trained ones fail on Earth.
Space × RoboticsSurface Mobility & Terramechanics Learning-based Methods
PDF HTML arXiv
Oct 21, 2026
#5End-to-End Reinforcement Learning for Quadrupedal Jumping in Lunar Gravity
Levin Müller, Oliver Fischer, Marco Trentini, Yusuke Tanaka +1 morePreprint 2026Oct 21, 2026
A single end-to-end RL policy for point-to-point quadruped jumps in lunar gravity, using only mission-compatible onboard sensing.
Space × Robotics × AIPLANETARY ROBOTICS Surface Mobility & Terramechanics Learning-based Methods
PDF HTML arXiv
Oct 21, 2026
#6OWLS: Open-world Language-conditioned Speed Fields for Zero-Shot Rover Navigation
Chahyon Ku, Erica Tevere, Georgios Georgakis, Rudra Mukherjee +1 morePreprint 2026Oct 23, 2026
OWLS plans rover paths directly over a VLM's dense feature map, turning a text prompt describing traversable terrain into a speed field for zero-shot navigation.
Space × Robotics × AIPLANETARY ROBOTICS Motion Planning & Navigation Perception & State Estimation Foundation Models & LLMs
PDF HTML arXiv
Oct 23, 2026
#7PPO vs. SAC: A Comparative Study for Cooperative Motion Control of Dual-Arm Space Robots
Nasim Fallahiarezoodar, Zheng H. ZhuAAS/AIAA Astrodynamics 2026Oct 23, 2026
Head-to-head PPO vs. SAC for coordinated dual-arm space manipulator motion with inter-arm collision avoidance, motivated by debris removal and servicing.
Space × Robotics × AIIN-SPACE SERVICING ORBITAL ROBOTICS Learning-based Methods Manipulation & Grasping Motion Planning & Navigation
PDF HTML arXiv
Oct 23, 2026