用视觉闭环控制提升复杂环境抓取成功率，比传统方法高33%
Grasp-MPC: Closed-Loop Visual Grasping via Value-Guided Model Predictive Control
- 基于价值引导的模型预测控制，实时调整抓取动作
- 仿真和真实场景下成功率分别提升32.6%和33.3%
- 适用于新物体与杂乱环境，适合机器人抓取研发者
在非结构化环境中抓取多样化物体仍是重大挑战。开环抓取方法在受控环境下有效，但在杂乱场景中因抓取预测误差和物体位姿变化易失败。现有闭环方法仅适用于简化场景（如桌面上单一物体）且难以泛化。本文提出Grasp-MPC，一种基于视觉的6-自由度闭环抓取策略，可在杂乱环境中稳健、实时地抓取新物体。该方法利用在200万条抓取轨迹（含成功与失败）上训练的视觉价值函数，结合模型预测控制框架，并加入避障与动作平滑成本项。在FetchBench仿真与真实世界多环境测试中，Grasp-MPC相比开环、扩散策略、Transformer策略及IQL方法，仿真成功率提升最高32.6%，真实场景噪声条件下提升达33.3%。视频与更多信息见http://grasp-mpc.github.io。
原文摘要 · Abstract (English)
Grasping of diverse objects in unstructured environments remains a significant challenge. Open-loop grasping methods, effective in controlled settings, struggle in cluttered environments. Grasp prediction errors and object pose changes during grasping are the main causes of failure. In contrast, closed-loop methods address these challenges in simplified settings (e.g., single object on a table) on a limited set of objects, with no path to generalization. We propose Grasp-MPC, a closed-loop 6-DoF vision-based grasping policy designed for robust and reactive grasping of novel objects in cluttered environments. Grasp-MPC incorporates a value function, trained on visual observations from a large-scale synthetic dataset of 2 million grasp trajectories that include successful and failed attempts. We deploy this learned value function in an MPC framework in combination with other cost terms that encourage collision avoidance and smooth execution. We evaluate Grasp-MPC on FetchBench and real-world settings across diverse environments. Grasp-MPC improves grasp success rates by up to 32.6% in simulation and 33.3% in real-world noisy conditions, outperforming open-loop, diffusion policy, transformer policy, and IQL approaches. Videos and more at http://grasp-mpc.github.io.
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。