论文/arXiv 2610.15486·17 天前

面向月球表面作业的安全约束全身移动操作学习

针对月面机器人自主安全移动操作，提出约束强化学习全身单策略，并在月球类比仿真多地形中验证。

AI 整理

• 本体 SDK 与控制
• 仿真与训练
• 具身模型

原文链接：Learning Safety-Constrained Whole-Body Loco-Manipulation for Lunar Surface Operations（arXiv 2610.15486 · 发布日期：2026-10-11）

Learning Safety-Constrained Whole-Body Loco-Manipulation for Lunar Surface Operations

针对月面机器人自主安全移动操作，提出约束强化学习全身单策略，并在月球类比仿真多地形中验证。

核心要点

• 月面作业难以持续监督且故障不可恢复，机器人需自主行动并保持自身完整性。
• 框架为四足移动操作器学习跟踪任务空间6D末端位姿的全身单策略，并在学习中执行操作限制。
• 奖励设计使行走与操作的过渡由奖励几何涌现，并加入面向低重力动力学的稳定项。
• 仿真中标称位置和姿态误差为3.22 cm、6.83 deg.，较无约束基线显著减少软约束违反且无硬约束违反。

验证范围与局限：验证限于月球重力下的月球类比仿真，覆盖三类地形、五个难度和由松散到致密的风化层接触属性。

英文摘要 (Abstract)

Robotic systems for lunar surface operations must act autonomously and preserve their own integrity in an environment where failures are unrecoverable and continuous supervision is impossible. This paper presents a Constrained Reinforcement Learning framework for quadrupedal mobile manipulators that learns a single whole-body policy for tracking a 6D end-effector pose specified in task space, with operational limits enforced during learning through a constrained learning mechanism. We introduce a reward formulation in which the transition between locomotion and manipulation emerges from the reward geometry rather than from an explicit gating mechanism, a stability term derived from the Gravito-Inertial Inclination Margin and motivated by the reduced-gravity dynamics of the lunar surface, and a design rule for reward regularization that follows from the multiplicative structure of the termination-based objective. The framework is evaluated in a lunar-analog simulation spanning three terrain morphologies at five difficulty levels under lunar gravity, with regolith contact properties calibrated to the JSC-1a simulant and varied from loose to dense. The learned policy attains mean position and orientation errors of 3.22 cm and 6.83 deg. under nominal conditions, retains this precision across regolith densities and over the operationally representative range of terrain difficulty, and reduces soft-constraint violation time by up to an order of magnitude relative to an unconstrained baseline while incurring no hard-constraint violations.

作者：Álvaro Belmonte-Baeza, Miguel Cazorla, Gabriel Jesús Garcia, C. Pérez del Pulgar, Jorge Pomares

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.15486：Learning Safety-Constrained Whole-Body Loco-Manipulation for Lunar Surface Operations访问 2026-10-21