Terrain Classification Enhanced with Uncertainty for Space Exploration Robots from Proprioceptive Data
This addresses the need for transparent and reliable terrain classification in unpredictable space environments, though it is incremental as it applies existing uncertainty methods to a specific domain.
The paper tackled the problem of unreliable terrain classification for space exploration robots by proposing neural networks with uncertainty quantification, achieving improved trustworthiness for high-stakes decisions.
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.