ProxMaP: Proximal Occupancy Map Prediction for Efficient Indoor Robot Navigation

TL;DR

ProxMaP introduces a self-supervised method for predicting occupancy in occluded regions near a robot, enabling more efficient indoor navigation by reducing unnecessary detours and improving navigation speed.

Contribution

The paper presents ProxMaP, a novel self-supervised occupancy prediction technique that enhances indoor robot navigation efficiency by accurately predicting occluded areas.

Findings

ProxMaP improves navigation efficiency by 12.40% in simulation.

ProxMaP generalizes well across different environments.

The method is self-supervised and does not require extensive labeled data.

Abstract

Planning a path for a mobile robot typically requires building a map (e.g., an occupancy grid) of the environment as the robot moves around. While navigating in an unknown environment, the map built by the robot online may have many as-yet-unknown regions. A conservative planner may avoid such regions taking a longer time to navigate to the goal. Instead, if a robot is able to correctly predict the occupancy in the occluded regions, the robot may navigate efficiently. We present a self-supervised occupancy prediction technique, ProxMaP, to predict the occupancy within the proximity of the robot to enable faster navigation. We show that ProxMaP generalizes well across realistic and real domains, and improves the robot navigation efficiency in simulation by 12.40% against a traditional navigation method. We share our findings and code at https://raaslab.org/projects/ProxMaP.