四足机器人靠腿部动作实现动态拾取，无需额外机械臂。
Scoop-and-Toss: Dynamic Object Collection for Quadrupedal Systems
- 用一条腿加装勺状装置，通过抓投动作收集物体。
- 分层策略训练出抓取、投掷与接近目标的专家策略。
- 适合需要灵活拾物的野外或复杂环境任务。
四足机器人在运动能力上已取得显著进展，从受控环境扩展至真实应用。除了行走，近期研究探索了利用腿部执行按按钮、开门等操作。尽管这些工作验证了腿基操作的可行性，但大多聚焦于静态任务。本文提出一种框架，使四足机器人在不增加额外致动器的情况下，通过腿部灵活性实现动态物体收集。通过在一条腿上附加简易勺状装置，机器人可将物体铲起并投掷至背部安装的收集盒中。方法采用分层策略结构，包含两个专家策略（分别负责抓取投掷与靠近目标位置）和一个元策略，该元策略可动态切换两者。专家策略分别训练后，再进行元策略训练以实现多物体协同收集。该方案展示了如何高效利用四足机器人的腿部完成动态操作，拓展其功能边界。
原文摘要 · Abstract (English)
Quadruped robots have made significant advances in locomotion, extending their capabilities from controlled environments to real-world applications. Beyond movement, recent work has explored loco-manipulation using the legs to perform tasks such as pressing buttons or opening doors. While these efforts demonstrate the feasibility of leg-based manipulation, most have focused on relatively static tasks. In this work, we propose a framework that enables quadruped robots to collect objects without additional actuators by leveraging the agility of their legs. By attaching a simple scoop-like add-on to one leg, the robot can scoop objects and toss them into a collection tray mounted on its back. Our method employs a hierarchical policy structure comprising two expert policies-one for scooping and tossing, and one for approaching object positions-and a meta-policy that dynamically switches between them. The expert policies are trained separately, followed by meta-policy training for coordinated multi-object collection. This approach demonstrates how quadruped legs can be effectively utilized for dynamic object manipulation, expanding their role beyond locomotion.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。