Sensory Anticipation of Optical Flow in Mobile Robotics

TL;DR

This paper presents a sensorimotor model for mobile robots that predicts optical flow and anticipates collisions using reinforcement learning, improving long-term safety predictions in uncertain environments.

Contribution

It introduces an online learning method for optical flow distribution and demonstrates its use in collision anticipation through reinforcement learning.

Findings

Multi-modal optical flow predictions simplify when actions are considered.

The model effectively anticipates collisions in dynamic environments.

Long-term predictions improve robot safety awareness.

Abstract

In order to anticipate dangerous events, like a collision, an agent needs to make long-term predictions. However, those are challenging due to uncertainties in internal and external variables and environment dynamics. A sensorimotor model is acquired online by the mobile robot using a state-of-the-art method that learns the optical flow distribution in images, both in space and time. The learnt model is used to anticipate the optical flow up to a given time horizon and to predict an imminent collision by using reinforcement learning. We demonstrate that multi-modal predictions reduce to simpler distributions once actions are taken into account.