arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2605.31352cs.RO
收藏

Haptic Sorter: 一种用于在线形状估计和实时位姿推断的统一规划框架

Haptic Sorter: A Unified Planning Framework for Online Shape Estimation and Real-Time Pose Inference

School of Mechanical and Aerospace Engineering, Nanyang Technological University (NTU), Singapore(南洋理工大学机械与航空航天工程学院)

Zhuoyi Lu, Lin Yang, Sri Harsha Turlapati, Domenico Campolo

AI总结:

提出一种基于模型的统一几何框架,结合贝叶斯优化引导的触觉探索、超椭圆形状近似、操作势能自适应公式以及在线常微分方程实时位姿推断,用于机器人操作中的形状估计和位姿跟踪。

摘要:

机器人操作通常假设在运动规划之前,物体的形状和位姿是已知的。然而,在实践中精确的几何信息并不总是可用的,并且位姿推断受到传感器不确定性和视角遮挡的影响。在这项工作中,我们提出了一个统一的基于模型的几何框架,集成了机器人触觉感知、建模和操作规划。我们的创新点包括: i) 引入贝叶斯优化(BO)来指导触觉探索以推断物体形状,其中使用超椭圆来近似几何边界; ii) 自适应地制定操作势能,编码物体几何以用于准静态机器人-物体交互; iii) 提出一个在线常微分方程(ODE),基于模型预测和触觉反馈进行实时位姿推断。 我们在一个二维机器人分拣任务上部署了我们的系统,并改变物体几何形状,以在仿真和真实世界的多臂设置中验证我们框架的鲁棒性和泛化能力。

英文摘要:

Robotics manipulation usually assumes that the shape and pose of the object are known to the robot prior to motion planning. However, precise geometric information is not always available in practice, and pose inference suffers from sensor uncertainties and view occlusion. In this work, we propose a unified model-based geometric framework integrating robotic haptic perception, modeling, and manipulation planning. Our novelties involve: \textit{i)} Introducing Bayesian Optimization (BO) to guide the haptic exploration for object shape inference, where superellipses are used to approximate geometric boundary; \textit{ii)} Adaptive formulation of manipulation potential encoding object geometry for quasi-static robot-object interaction; \textit{iii)} Proposing an online Ordinary Differential Equation (ODE) for real-time pose inference based on model prediction and tactile feedback. We deploy our system on a 2D robotic sorting task, and vary object geometries to validate the robustness and generalizability of our framework in both simulation and a real-world multi-arm setup.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑