Generating Task-specific Robotic Grasps

TL;DR

This paper presents a method for generating task-specific robotic grasps by learning a three-level object representation that encodes task and stability constraints, enabling robots to adapt to various objects and tasks.

Contribution

The paper introduces a novel three-level representation for task-specific grasp generation learned from few exemplars, improving grasp suitability across different tasks and object variations.

Findings

The method successfully generates task-appropriate grasps on a real robot.

It outperforms stability-only baselines in task-specific grasping.

The approach generalizes across object classes with limited training data.

Abstract

This paper describes a method for generating robot grasps by jointly considering stability and other task and object-specific constraints. We introduce a three-level representation that is acquired for each object class from a small number of exemplars of objects, tasks, and relevant grasps. The representation encodes task-specific knowledge for each object class as a relationship between a keypoint skeleton and suitable grasp points that is preserved despite intra-class variations in scale and orientation. The learned models are queried at run time by a simple sampling-based method to guide the generation of grasps that balance task and stability constraints. We ground and evaluate our method in the context of a Franka Emika Panda robot assisting a human in picking tabletop objects for which the robot does not have prior CAD models. Experimental results demonstrate that in comparison with a baseline method that only focuses on stability, our method is able to provide suitable grasps for different tasks.