Terrain Classification Enhanced with Uncertainty for Space Exploration Robots from Proprioceptive Data

TL;DR

This paper introduces a method for terrain classification in space exploration robots that incorporates uncertainty quantification into neural networks using proprioceptive data, enhancing reliability in unpredictable environments.

Contribution

It proposes neural network models with uncertainty estimation techniques like Monte Carlo Dropout, DropConnect, and Flipout, optimized with Bayesian Hyperband for trustworthy terrain classification.

Findings

Uncertainty-aware neural networks improve terrain classification reliability.

Bayesian Optimization effectively tunes hyperparameters for optimal models.

Proprioceptive data alone suffices for accurate, trustworthy terrain classification.

Abstract

Terrain Classification is an essential task in space exploration, where unpredictable environments are difficult to observe using only exteroceptive sensors such as vision. Implementing Neural Network classifiers can have high performance but can be deemed untrustworthy as they lack transparency, which makes them unreliable for taking high-stakes decisions during mission planning. We address this by proposing Neural Networks with Uncertainty Quantification in Terrain Classification. We enable our Neural Networks with Monte Carlo Dropout, DropConnect, and Flipout in time series-capable architectures using only proprioceptive data as input. We use Bayesian Optimization with Hyperband for efficient hyperparameter optimization to find optimal models for trustworthy terrain classification.