Complex Terrain Navigation via Model Error Prediction

TL;DR

This paper introduces a learning-based navigation approach that predicts terrain traversability errors to navigate complex, deformable terrains more effectively than traditional geometric methods, using minimal training data.

Contribution

It presents a novel method of predicting model error for terrain traversability, enabling efficient navigation in deformable environments with limited training data.

Findings

Successful navigation in complex terrains like grassland and forest

Achieved effective navigation with only 50 minutes of training data

Outperforms traditional geometric-based navigation methods

Abstract

Robot navigation traditionally relies on building an explicit map that is used to plan collision-free trajectories to a desired target. In deformable, complex terrain, using geometric-based approaches can fail to find a path due to mischaracterizing deformable objects as rigid and impassable. Instead, we learn to predict an estimate of traversability of terrain regions and to prefer regions that are easier to navigate (e.g., short grass over small shrubs). Rather than predicting collisions, we instead regress on realized error compared to a canonical dynamics model. We train with an on-policy approach, resulting in successful navigation policies using as little as 50 minutes of training data split across simulation and real world. Our learning-based navigation system is a sample efficient short-term planner that we demonstrate on a Clearpath Husky navigating through a variety of terrain including grassland and forest