Leveraging Energy Features for Surface Classification with Deep Learning: A Comparative Analysis Across Three Independent Datasets

2026-06-17

AI Summary

This study investigates the effectiveness of energy-based features for terrain classification in mobile robotics, particularly under modality-constrained scenarios where only a single sensory input is available. Through systematic evaluation on three public datasets, the work demonstrates for the first time that energy features alone possess strong discriminative capability as an independent modality. The experimental framework encompasses diverse deep learning architectures—including CNNs, RNNs, Encoder-only Transformers, and Mamba—augmented with automated hyperparameter tuning and optimized input sequence lengths. Results show that energy-only features achieve classification accuracies of 85–90%, which further improve to 96–99% when fused with inertial data, yielding an average accuracy gain of 1–2% and outperforming existing state-of-the-art methods.

Abstract

The energy-based method remains a comparatively underexamined approach for surface classification in mobile robotics, despite promising results in constrained environments. This study evaluated the viability of using energy-derived features as either a standalone classification modality or as supplementary input to inertial data. A comprehensive evaluation was conducted across three publicly available datasets, comparing the performance of modern deep learning architectures including recurrent neural networks, convolutional neural networks, encoder-only transformers, and Mamba state-space models, under automated hyperparameter tuning and input sequence length optimization. The models achieved higher accuracy than previously reported values on all evaluated datasets, with the convolutional neural network yielding the highest overall performance. When relying exclusively on energy-based features, the models attained classification accuracies in the range of 85-90%, approximately 5-10% lower than those achieved when combined with inertial features (96-99%). Augmenting inertial data with energy features resulted in a consistent mean accuracy improvement of 1-2%. These findings indicate that classifiers relying solely on energy features offer sufficient accuracy for standalone deployment, while also providing a consistent gain when used in combination with other sensing modalities.

Problem

• surface classification
• energy features
• mobile robotics
• inertial data
• deep learning

Innovation

• energy-based features
• surface classification
• deep learning
• multimodal fusion
• Mamba state-space model