Dynamic Grasping with Reachability and Motion Awareness

TL;DR

This paper introduces a real-time, dynamic grasping framework that integrates reachability modeling, grasp quality prediction, and motion prediction to improve robotic grasping in moving object scenarios.

Contribution

It presents a novel reachability-aware and motion-aware grasping system using neural networks and signed distance fields for real-time adaptive grasping.

Findings

Effective real-time grasp filtering using neural networks.

Successful implementation on a real robot in dynamic environments.

Improved grasp stability and adaptability in moving object scenarios.

Abstract

Grasping in dynamic environments presents a unique set of challenges. A stable and reachable grasp can become unreachable and unstable as the target object moves, motion planning needs to be adaptive and in real time, the delay in computation makes prediction necessary. In this paper, we present a dynamic grasping framework that is reachability-aware and motion-aware. Specifically, we model the reachability space of the robot using a signed distance field which enables us to quickly screen unreachable grasps. Also, we train a neural network to predict the grasp quality conditioned on the current motion of the target. Using these as ranking functions, we quickly filter a large grasp database to a few grasps in real time. In addition, we present a seeding approach for arm motion generation that utilizes solution from previous time step. This quickly generates a new arm trajectory that is close to the previous plan and prevents fluctuation. We implement a recurrent neural network (RNN) for modelling and predicting the object motion. Our extensive experiments demonstrate the importance of each of these components and we validate our pipeline on a real robot.