TerraPN: Unstructured Terrain Navigation using Online Self-Supervised Learning

TL;DR

TerraPN introduces a self-supervised learning approach for autonomous outdoor terrain navigation, enabling robots to learn surface properties directly from interactions and improve navigation safety and efficiency.

Contribution

It presents a novel self-supervised method to learn terrain surface properties from robot-terrain interactions using RGB images and IMU data, with a new navigation algorithm based on surface costs.

Findings

Reduces inference time by 47.27% with non-uniform sampling.

Outperforms previous methods with up to 35.84% higher success rates.

Lowers trajectory vibration costs by up to 21.52%.

Abstract

We present TerraPN, a novel method that learns the surface properties (traction, bumpiness, deformability, etc.) of complex outdoor terrains directly from robot-terrain interactions through self-supervised learning, and uses it for autonomous robot navigation. Our method uses RGB images of terrain surfaces and the robot's velocities as inputs, and the IMU vibrations and odometry errors experienced by the robot as labels for self-supervision. Our method computes a surface cost map that differentiates smooth, high-traction surfaces (low navigation costs) from bumpy, slippery, deformable surfaces (high navigation costs). We compute the cost map by non-uniformly sampling patches from the input RGB image by detecting boundaries between surfaces resulting in low inference times (47.27% lower) compared to uniform sampling and existing segmentation methods. We present a novel navigation algorithm that accounts for a surface's cost, computes cost-based acceleration limits for the robot, and dynamically feasible, collision-free trajectories. TerraPN's surface cost prediction can be trained in ~25 minutes for five different surfaces, compared to several hours for previous learning-based segmentation methods. In terms of navigation, our method outperforms previous works in terms of success rates (up to 35.84% higher), vibration cost of the trajectories (up to 21.52% lower), and slowing the robot on bumpy, deformable surfaces (up to 46.76% slower) in different scenarios.