Online Trajectory Replanner for Dynamically Grasping Irregular Objects

TL;DR

This paper introduces a real-time trajectory replanning framework for dynamically grasping irregular objects, combining offline initial planning with fast online updates to adapt to pose errors and uncertainties.

Contribution

A novel two-phase trajectory optimization framework enabling dynamic grasping of irregular objects with real-time updates within 100 ms.

Findings

Effective in simulation and real-world tests

Handles pose estimation errors robustly

Achieves seamless grasping of irregular objects

Abstract

This paper presents a new trajectory replanner for grasping irregular objects. Unlike conventional grasping tasks where the object's geometry is assumed simple, we aim to achieve a "dynamic grasp" of the irregular objects, which requires continuous adjustment during the grasping process. To effectively handle irregular objects, we propose a trajectory optimization framework that comprises two phases. Firstly, in a specified time limit of 10s, initial offline trajectories are computed for a seamless motion from an initial configuration of the robot to grasp the object and deliver it to a pre-defined target location. Secondly, fast online trajectory optimization is implemented to update robot trajectories in real-time within 100 ms. This helps to mitigate pose estimation errors from the vision system. To account for model inaccuracies, disturbances, and other non-modeled effects, trajectory tracking controllers for both the robot and the gripper are implemented to execute the optimal trajectories from the proposed framework. The intensive experimental results effectively demonstrate the performance of our trajectory planning framework in both simulation and real-world scenarios.