# Let's Push Things Forward: A Survey on Robot Pushing

## TL;DR

This survey reviews the state-of-the-art in robotic pushing, covering analytical, learning-based, and deep learning methods for predicting object motion and enhancing manipulation capabilities in diverse environments.

## Contribution

It provides a comprehensive overview of pushing techniques, highlighting recent advances in deep learning and data-driven models for robotic manipulation.

## Key findings

- Deep learning approaches have recently gained prominence in pushing tasks.
- Physics-based and analytical models remain foundational for motion prediction.
- The survey identifies future research directions in data-driven manipulation methods.

## Abstract

As robot make their way out of factories into human environments, outer space, and beyond, they require the skill to manipulate their environment in multifarious, unforeseeable circumstances. With this regard, pushing is an essential motion primitive that dramatically extends a robot's manipulation repertoire. In this work, we review the robotic pushing literature. While focusing on work concerned with predicting the motion of pushed objects, we also cover relevant applications of pushing for planning and control. Beginning with analytical approaches, under which we also subsume physics engines, we then proceed to discuss work on learning models from data. In doing so, we dedicate a separate section to deep learning approaches which have seen a recent upsurge in the literature. Concluding remarks and further research perspectives are given at the end of the paper.