外观
论文arXiv 2610.2096814 天前
SOMA：使用四足机器人进行堆叠物体操控
原文链接：SOMA: Stack-of-Objects Manipulation using a Quadruped Robot（arXiv 2610.20968 · 发布日期：2026-10-14）
SOMA: Stack-of-Objects Manipulation using a Quadruped Robot
SOMA用分层强化学习实现四足机器人三维非抓取堆叠物操控，并在仿真基准和Unitree Go1真机上验证。
核心要点
- 四足机器人缺少专用机械臂，在不可预测环境中重载操控仍具挑战。
- SOMA采用分层强化学习，显式控制机身高度以实现三维推动策略。
- 高层用S5编码长时序历史并以Beta分布预测有界跟踪命令。
- 仿真中单物体重定位成功率90.3%，动态双箱堆叠最高90.1%。
验证范围与局限：验证范围为仿真中的单物体重定位和动态双箱堆叠，以及Unitree Go1真机重推不同质量与几何载荷。
英文摘要 (Abstract)
Executing heavy-duty physical manipulation in unpredictable environments remains a major challenge for quadrupedal robots lacking dedicated manipulators. This paper presents SOMA, a hierarchical reinforcement learning framework for whole-body non-prehensile manipulation of multi-object stacks using a quadruped robot. Unlike traditional methods restricted to two-dimensional planar pushing, SOMA integrates explicit robot base-height control, unlocking full three-dimensional pushing strategies. This capability enables the quadruped to manipulate complex payload stacks as a unified system while preventing relative sliding or tipping of upper layers. The architecture factorizes control into a high-level manipulation policy using a Simplified Structured State Space Sequence (S5) encoder to reason over long-horizon temporal history and predict bounded target tracking commands via Beta distributions, and a low-level locomotion policy that dynamically adapts leg stance configurations. In extensive simulation benchmarks, SOMA achieves a $90.3%$ success rate for single-object reposing and up to $90.1%$ for dynamic two-box stacks under stringent error margins ($0.05\text{ m}$ position error, $1^\circ$ orientation error). Finally, we validate zero-shot sim-to-real transfer on a Unitree Go1 quadruped robot across diverse payload masses and geometries, demonstrating active base-height adjustments to maintain traction and balance during heavy pushing tasks.
作者：Stergios E. Bachoumas, Panagiotis Artemiadis
来源
本页事实对应的公开页面，以原文为准。