Trailblazer: Learning offroad costmaps for long range planning

TL;DR

Trailblazer is a framework that uses imitation learning to convert multi-modal sensor data into costmaps for off-road long-range planning, improving autonomous navigation in complex environments.

Contribution

It introduces a novel imitation learning approach with a differentiable planner to automate costmap generation from sensor data, reducing manual tuning and increasing adaptability.

Findings

Robust performance in real-world off-road environments

Effective long-range planning without manual costmap tuning

Enhanced adaptability across diverse terrains

Abstract

Autonomous navigation in off-road environments remains a significant challenge in field robotics, particularly for Unmanned Ground Vehicles (UGVs) tasked with search and rescue, exploration, and surveillance. Effective long-range planning relies on the integration of onboard perception systems with prior environmental knowledge, such as satellite imagery and LiDAR data. This work introduces Trailblazer, a novel framework that automates the conversion of multi-modal sensor data into costmaps, enabling efficient path planning without manual tuning. Unlike traditional approaches, Trailblazer leverages imitation learning and a differentiable A* planner to learn costmaps directly from expert demonstrations, enhancing adaptability across diverse terrains. The proposed methodology was validated through extensive real-world testing, achieving robust performance in dynamic and complex environments, demonstrating Trailblazer's potential for scalable, efficient autonomous navigation.