Robot Localization and Navigation through Predictive Processing using LiDAR

TL;DR

This paper introduces a predictive processing-inspired method for robot localization and navigation using LiDAR data, which learns a generative model and performs online estimation without odometry, showing improved accuracy and navigation capabilities.

Contribution

It presents a novel approach combining predictive processing with self-supervised learning for laser-based localization and navigation, eliminating the need for odometry.

Findings

Outperforms particle filter in state estimation accuracy

Enables navigation by inferring actions to minimize prediction error

Operates effectively without odometry data

Abstract

Knowing the position of the robot in the world is crucial for navigation. Nowadays, Bayesian filters, such as Kalman and particle-based, are standard approaches in mobile robotics. Recently, end-to-end learning has allowed for scaling-up to high-dimensional inputs and improved generalization. However, there are still limitations to providing reliable laser navigation. Here we show a proof-of-concept of the predictive processing-inspired approach to perception applied for localization and navigation using laser sensors, without the need for odometry. We learn the generative model of the laser through self-supervised learning and perform both online state-estimation and navigation through stochastic gradient descent on the variational free-energy bound. We evaluated the algorithm on a mobile robot (TIAGo Base) with a laser sensor (SICK) in Gazebo. Results showed improved state-estimation performance when comparing to a state-of-the-art particle filter in the absence of odometry. Furthermore, conversely to standard Bayesian estimation approaches our method also enables the robot to navigate when providing the desired goal by inferring the actions that minimize the prediction error.