用视觉强化学习让机械臂自动完成插销任务，提升成功率和效率
A Visual Reinforcement Learning-Based Separate Primitive Policy for Peg-in-Hole Tasks
- 设计分离式动作策略，同步学习定位与插入动作
- 在10种不同形状的插孔任务中，成功率显著提升，样本效率更高
- 适用于真实机器人场景，对力控约束有良好适应性
在插销任务中，人类依赖双目视觉判断销钉位置并完成插入。本文借鉴此行为，提出一种基于视觉强化学习的分离基础策略（S2P），使智能体能同时学习定位与插入动作，兼容无模型强化学习算法。设计了10个包含不同多边形的插入任务作为基准评估。仿真实验表明，即使在施加力约束条件下，S2P仍可显著提升样本效率与成功率。真实世界实验验证了S2P的可行性。消融实验进一步分析了S2P的泛化能力及影响其性能的关键因素。
原文摘要 · Abstract (English)
For peg-in-hole tasks, humans rely on binocular visual perception to locate the peg above the hole surface and then proceed with insertion. This paper draws insights from this behavior to enable agents to learn efficient assembly strategies through visual reinforcement learning. Hence, we propose a Separate Primitive Policy (S2P) to learn how to derive location and insertion actions simultaneously. S2P is compatible with model-free reinforcement learning algorithms. Ten insertion tasks featuring different polygons are developed as benchmarks for evaluations. Simulation experiments show that S2P can boost the sample efficiency and success rate even with force constraints. Real-world experiments are also performed to verify the feasibility of S2P. Ablations are finally given to discuss the generalizability of S2P and some factors that affect its performance.
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。