kPAM 2.0: Feedback Control for Category-Level Robotic Manipulation

TL;DR

This paper introduces a novel feedback control framework for category-level robotic manipulation that uses oriented keypoints to handle intra-category shape variations and enables precise, contact-rich tasks across diverse object instances.

Contribution

It extends the kPAM framework with local orientation-augmented keypoints and a new object-centric action representation for robust, flexible manipulation of varied objects.

Findings

Successfully performs peg-hole insertion with significant shape variation.

Achieves precise contact-rich manipulation across object categories.

Framework is robot-agnostic and adaptable to different initial configurations.

Abstract

In this paper, we explore generalizable, perception-to-action robotic manipulation for precise, contact-rich tasks. In particular, we contribute a framework for closed-loop robotic manipulation that automatically handles a category of objects, despite potentially unseen object instances and significant intra-category variations in shape, size and appearance. Previous approaches typically build a feedback loop on top of a real-time 6-DOF pose estimator. However, representing an object with a parameterized transformation from a fixed geometric template does not capture large intra-category shape variation. Hence we adopt the keypoint-based object representation proposed in kPAM for category-level pick-and-place, and extend it to closed-loop manipulation policies with contact-rich tasks. We first augment keypoints with local orientation information. Using the oriented keypoints, we propose a novel object-centric action representation in terms of regulating the linear/angular velocity or force/torque of these oriented keypoints. This formulation is surprisingly versatile -- we demonstrate that it can accomplish contact-rich manipulation tasks that require precision and dexterity for a category of objects with different shapes, sizes and appearances, such as peg-hole insertion for pegs and holes with significant shape variation and tight clearance. With the proposed object and action representation, our framework is also agnostic to the robot grasp pose and initial object configuration, making it flexible for integration and deployment.