Interactive Perception: Leveraging Action in Perception and Perception in Action

TL;DR

This survey explores how interaction with the environment enhances perception in robotics, emphasizing the benefits of sensory data richness and regularity, and aims to define and inspire future research in Interactive Perception.

Contribution

It categorizes and analyzes existing work on Interactive Perception, providing an overview of applications and discussing open questions to shape future research directions.

Findings

Interaction creates richer sensory signals.

Knowledge of sensory-action regularities aids prediction.

The survey identifies key applications and open challenges.

Abstract

Recent approaches in robotics follow the insight that perception is facilitated by interaction with the environment. These approaches are subsumed under the term of Interactive Perception (IP). It provides the following benefits: (i) interaction with the environment creates a rich sensory signal that would otherwise not be present and (ii) knowledge of the regularity in the combined space of sensory data and action parameters facilitate the prediction and interpretation of the signal. In this survey we postulate this as a principle and collect evidence in support by analyzing and categorizing existing work in this area. We also provide an overview of the most important applications of Interactive Perception. We close this survey by discussing remaining open questions. Thereby, we hope to define a field and inspire future work.