Selected work

Representative Papers

Attention-Based Surface Representation Learning for Robot State Prediction and Open-Ended Surface Classification

Oct 03, 2026

This study addresses the limitation of fixed-category classification in outdoor terrain perception for ground robots, which hinders scalability to novel classes. To overcome this, we propose an open-set surface classification method based on temporal state prediction and attention mechanisms. The core innovation lies in parameterizing novel surface categories as trainable vectors, enabling dynamic class addition and thereby transcending traditional closed-set constraints. Experimental evaluations demonstrate that the proposed approach achieves classification accuracies of 98.56% and 94.8% on the Belyaev-Kushnarev and BorealTC datasets, respectively. These results confirm the method's capability to deliver high-precision and scalable open-world terrain perception for autonomous ground navigation.

0 citationsRead paper

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

Jun 17, 2026

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.

0 citationsRead paper

Vision-Language Based Expert Reporting for Painting Authentication and Defect Detection

Mar 13, 2026

This study addresses the reliance on expert intuition in thermographic analysis of cultural heritage artifacts, which lacks standardized, interpretable, and cross-sample comparable automated methods. The authors propose the first fully automated framework that integrates multimodal active infrared thermography with a vision-language model. By leveraging Principal Component Thermography (PCT), Thermographic Signal Reconstruction (TSR), and Pulse Phase Thermography (PPT), the framework generates a consensus segmentation mask to guide the vision-language model in producing structured diagnostic reports accompanied by uncertainty quantification. Experiments on marquetry samples demonstrate that the method reliably detects anomalies and yields consistent, generalizable, expert-level interpretations, significantly enhancing the systematic applicability of thermography in artifact conservation.

0 citationsRead paper

Recent publications

Latest Papers

Attention-Based Surface Representation Learning for Robot State Prediction and Open-Ended Surface Classification

Oct 03, 2026

This study addresses the limitation of fixed-category classification in outdoor terrain perception for ground robots, which hinders scalability to novel classes. To overcome this, we propose an open-set surface classification method based on temporal state prediction and attention mechanisms. The core innovation lies in parameterizing novel surface categories as trainable vectors, enabling dynamic class addition and thereby transcending traditional closed-set constraints. Experimental evaluations demonstrate that the proposed approach achieves classification accuracies of 98.56% and 94.8% on the Belyaev-Kushnarev and BorealTC datasets, respectively. These results confirm the method's capability to deliver high-precision and scalable open-world terrain perception for autonomous ground navigation.

0 citationsRead paper

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

Jun 17, 2026

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.

0 citationsRead paper

Vision-Language Based Expert Reporting for Painting Authentication and Defect Detection

Mar 13, 2026

This study addresses the reliance on expert intuition in thermographic analysis of cultural heritage artifacts, which lacks standardized, interpretable, and cross-sample comparable automated methods. The authors propose the first fully automated framework that integrates multimodal active infrared thermography with a vision-language model. By leveraging Principal Component Thermography (PCT), Thermographic Signal Reconstruction (TSR), and Pulse Phase Thermography (PPT), the framework generates a consensus segmentation mask to guide the vision-language model in producing structured diagnostic reports accompanied by uncertainty quantification. Experiments on marquetry samples demonstrate that the method reliably detects anomalies and yields consistent, generalizable, expert-level interpretations, significantly enhancing the systematic applicability of thermography in artifact conservation.

0 citationsRead paper