High-Speed Robot Navigation using Predicted Occupancy Maps

TL;DR

This paper presents a neural network-based approach for high-speed robot navigation that predicts beyond sensor range to enable safer and faster movement, validated on a physical robot with improved performance.

Contribution

It introduces a generative neural network for predicting occupancy maps beyond sensor view, enhancing high-speed navigation without requiring manual labels.

Findings

Improved navigation speed to 4 m/s with predicted maps.

Successful real-world validation on MIT race car robot.

Enhanced collision avoidance using predicted occupancy regions.

Abstract

Safe and high-speed navigation is a key enabling capability for real world deployment of robotic systems. A significant limitation of existing approaches is the computational bottleneck associated with explicit mapping and the limited field of view (FOV) of existing sensor technologies. In this paper, we study algorithmic approaches that allow the robot to predict spaces extending beyond the sensor horizon for robust planning at high speeds. We accomplish this using a generative neural network trained from real-world data without requiring human annotated labels. Further, we extend our existing control algorithms to support leveraging the predicted spaces to improve collision-free planning and navigation at high speeds. Our experiments are conducted on a physical robot based on the MIT race car using an RGBD sensor where were able to demonstrate improved performance at 4 m/s compared to a controller not operating on predicted regions of the map.