Rigid-Soft Interactive Learning for Robust Grasping

Abstract

Inspired by widely used soft fingers on grasping, we propose a method of rigid-soft interactive learning, aiming at reducing the time of data collection. In this paper, we classify the interaction categories into Rigid-Rigid, Rigid-Soft, Soft-Rigid according to the interaction surface between grippers and target objects. We find experimental evidence that the interaction types between grippers and target objects play an essential role in the learning methods. We use soft, stuffed toys for training, instead of everyday objects, to reduce the integration complexity and computational burden and exploit such rigid-soft interaction by changing the gripper fingers to the soft ones when dealing with rigid, daily-life items such as the Yale-CMU-Berkeley (YCB) objects. With a small data collection of 5K picking attempts in total, our results suggest that such Rigid-Soft and Soft-Rigid interactions are transferable. Moreover, the combination of different grasp types shows better performance on the grasping test. We achieve the best grasping performance at 97.5\% for easy YCB objects and 81.3\% for difficult YCB objects while using a precise grasp with a two-soft-finger gripper to collect training data and power grasp with a four-soft-finger gripper to test.

8 pages, 5 figures, Accepted for IEEE RAL and IEEE ICRA 2020

References in corpus (5)

• Data-Driven Grasp Synthesis - A Survey
• Benchmarking in Manipulation Research: The YCB Object and Model Set and Benchmarking Protocols
• Dex-Net 2.0: Deep Learning to Plan Robust Grasps with Synthetic Point Clouds and Analytic Grasp Metrics
• Collective Robot Reinforcement Learning with Distributed Asynchronous Guided Policy Search
• REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning

Cited by in corpus (7)

• Proprioceptive Learning with Soft Polyhedral Networks
• Reconfigurable Design for Omni-adaptive Grasp Learning
• Weakly Supervised Disentangled Representation for Goal-conditioned Reinforcement Learning
• Understanding Particles From Video: Property Estimation of Granular Materials via Visuo-Haptic Learning
• Cocktail: Learn a Better Neural Network Controller from Multiple Experts via Adaptive Mixing and Robust Distillation
• Design of an Optoelectronically Innervated Gripper for Rigid-Soft Interactive Grasping
• Learning-based Optoelectronically Innervated Tactile Finger for Rigid-Soft Interactive Grasping