Visual Memory for Robust Path Following

TL;DR

This paper introduces a neural network-based approach enabling robots to reliably retrace paths in changing environments by learning path abstractions and decision-making under uncertainty, outperforming classical and baseline methods.

Contribution

The paper presents a novel end-to-end trainable system with two networks for path abstraction and action decision, improving robustness in path following and homing tasks.

Findings

Outperforms classical path following methods.

Effective under actuation noise and environmental changes.

Demonstrates robustness in realistic simulators.

Abstract

Humans routinely retrace paths in a novel environment both forwards and backwards despite uncertainty in their motion. This paper presents an approach for doing so. Given a demonstration of a path, a first network generates a path abstraction. Equipped with this abstraction, a second network observes the world and decides how to act to retrace the path under noisy actuation and a changing environment. The two networks are optimized end-to-end at training time. We evaluate the method in two realistic simulators, performing path following and homing under actuation noise and environmental changes. Our experiments show that our approach outperforms classical approaches and other learning based baselines.