# Robot Learning of Shifting Objects for Grasping in Cluttered Environments

## TL;DR

This paper introduces a self-supervised learning algorithm enabling robots to shift objects to improve grasp success in cluttered environments, significantly enhancing bin-picking efficiency and generalization to new objects.

## Contribution

The paper presents a novel algorithm for learning manipulation primitives like shifting, which depend on grasping, improving data efficiency and real-world bin-picking performance.

## Key findings

- Achieved 274 picks per hour in bin-picking tasks.
- Learned to shift objects to increase grasp probability.
- System generalizes to novel objects.

## Abstract

Robotic grasping in cluttered environments is often infeasible due to obstacles preventing possible grasps. Then, pre-grasping manipulation like shifting or pushing an object becomes necessary. We developed an algorithm that can learn, in addition to grasping, to shift objects in such a way that their grasp probability increases. Our research contribution is threefold: First, we present an algorithm for learning the optimal pose of manipulation primitives like clamping or shifting. Second, we learn non-prehensible actions that explicitly increase the grasping probability. Making one skill (shifting) directly dependent on another (grasping) removes the need of sparse rewards, leading to more data-efficient learning. Third, we apply a real-world solution to the industrial task of bin picking, resulting in the ability to empty bins completely. The system is trained in a self-supervised manner with around 25000 grasp and 2500 shift actions. Our robot is able to grasp and file objects with 274 picks per hour. Furthermore, we demonstrate the system's ability to generalize to novel objects.