Lightweight Uncertainty Quantification with Simplex Semantic Segmentation for Terrain Traversability

TL;DR

This paper introduces a lightweight, architecture-agnostic uncertainty estimation module for terrain segmentation that enhances robot navigation safety without significant computational overhead.

Contribution

It presents a novel, simple module that can be integrated with any pretrained segmentation model to estimate uncertainty efficiently.

Findings

Effective uncertainty estimation for terrain segmentation

Compatible with various pretrained models

Low additional computational cost

Abstract

For navigation of robots, image segmentation is an important component to determining a terrain's traversability. For safe and efficient navigation, it is key to assess the uncertainty of the predicted segments. Current uncertainty estimation methods are limited to a specific choice of model architecture, are costly in terms of training time, require large memory for inference (ensembles), or involve complex model architectures (energy-based, hyperbolic, masking). In this paper, we propose a simple, light-weight module that can be connected to any pretrained image segmentation model, regardless of its architecture, with marginal additional computation cost because it reuses the model's backbone. Our module is based on maximum separation of the segmentation classes by respective prototype vectors. This optimizes the probability that out-of-distribution segments are projected in between the prototype vectors. The uncertainty value in the classification label is obtained from the distance to the nearest prototype. We demonstrate the effectiveness of our module for terrain segmentation.