kPAM 2.0: Feedback Control for Category-Level Robotic Manipulation

Autor: Russ Tedrake, Wei Gao
Jazyk: angličtina
Rok vydání: 2021
Předmět:
FOS: Computer and information sciences
0209 industrial biotechnology
Control and Optimization
Source code
Computer science
media_common.quotation_subject
Biomedical Engineering
02 engineering and technology
Computer Science - Robotics
020901 industrial engineering & automation
Artificial Intelligence
0202 electrical engineering
electronic engineering
information engineering
Computer vision
media_common
Robot kinematics
business.industry
Orientation (computer vision)
Mechanical Engineering
GRASP
Representation (systemics)
Object (computer science)
Computer Science Applications
Human-Computer Interaction
Control and Systems Engineering
Robot
020201 artificial intelligence & image processing
Computer Vision and Pattern Recognition
Artificial intelligence
business
Robotics (cs.RO)
Initial and terminal objects
Popis: 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.
IEEE Robotics and Automation Letter. The video demo is on https://sites.google.com/view/kpam2/
Databáze: OpenAIRE
Externí odkaz: