I Move Therefore I Learn: Experience-Based Traversability in Outdoor Robotics

TL;DR

This paper presents an experience-based traversability estimation method for outdoor robots that learns terrain safety from prior navigation without needing pre-labeled data, enabling robust and adaptive navigation.

Contribution

It introduces a novel approach combining VAE and clustering to enable robots to learn traversability from experience, generalizing across environments without prior targeted training.

Findings

Effective in diverse real-world environments

Outperforms existing traversability methods

Robust across different robot platforms

Abstract

Accurate traversability estimation is essential for safe and effective navigation of outdoor robots operating in complex environments. This paper introduces a novel experience-based method that allows robots to autonomously learn which terrains are traversable based on prior navigation experience, without relying on extensive pre-labeled datasets. The approach integrates elevation and texture data into multi-layered grid maps, which are processed using a variational autoencoder (VAE) trained on a generic texture dataset. During an initial teleoperated phase, the robot collects sensory data while moving around the environment. These experiences are encoded into compact feature vectors and clustered using the BIRCH algorithm to represent traversable terrain areas efficiently. In deployment, the robot compares new terrain patches to its learned feature clusters to assess traversability in real time. The proposed method does not require training with data from the targeted scenarios, generalizes across diverse surfaces and platforms, and dynamically adapts as new terrains are encountered. Extensive evaluations on both synthetic benchmarks and real-world scenarios with wheeled and legged robots demonstrate its effectiveness, robustness, and superior adaptability compared to state-of-the-art approaches.