Haptic Sorter: A Unified Planning Framework for Online Shape Estimation and Real-Time Pose Inference
This work addresses the problem of manipulating objects with unknown shape and pose for robotic systems, which is a common challenge in real-world applications where precise geometric information is often unavailable.
This paper proposes a unified model-based geometric framework that integrates robotic haptic perception, modeling, and manipulation planning to address the challenge of unknown object shape and pose in robotics manipulation. The framework uses Bayesian Optimization for shape inference and an online Ordinary Differential Equation for real-time pose inference, demonstrating robustness and generalizability in a 2D robotic sorting task in both simulation and real-world multi-arm setups.
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.