Real-time Motion Generation and Data Augmentation for Grasping Moving Objects with Dynamic Speed and Position Changes

TL;DR

This paper introduces a data augmentation technique that allows robots to grasp moving objects with varying speeds and positions by learning from augmented time-series data, improving robustness and adaptability.

Contribution

The authors propose a low-cost data augmentation method that enables robots to learn grasping motions for moving objects with dynamic speed and position changes.

Findings

Robots can grasp objects with untrained speeds and positions.

Data augmentation improves grasping robustness.

Method reduces trial-and-error in robot learning.

Abstract

While deep learning enables real robots to perform complex tasks had been difficult to implement in the past, the challenge is the enormous amount of trial-and-error and motion teaching in a real environment. The manipulation of moving objects, due to their dynamic properties, requires learning a wide range of factors such as the object's position, movement speed, and grasping timing. We propose a data augmentation method for enabling a robot to grasp moving objects with different speeds and grasping timings at low cost. Specifically, the robot is taught to grasp an object moving at low speed using teleoperation, and multiple data with different speeds and grasping timings are generated by down-sampling and padding the robot sensor data in the time-series direction. By learning multiple sensor data in a time series, the robot can generate motions while adjusting the grasping timing for unlearned movement speeds and sudden speed changes. We have shown using a real robot that this data augmentation method facilitates learning the relationship between object position and velocity and enables the robot to perform robust grasping motions for unlearned positions and objects with dynamically changing positions and velocities.