Header logo is

Robust Surface Recognition with the Maximum Mean Discrepancy: Degrading Haptic-Auditory Signals through Bandwidth and Noise

2024

Article

hi


Sliding a tool across a surface generates rich sensations that can be analyzed to recognize what is being touched. However, the optimal configuration for capturing these signals is yet unclear. To bridge this gap, we consider haptic-auditory data as a human explores surfaces with different steel tools, including accelerations of the tool and finger, force and torque applied to the surface, and contact sounds. Our classification pipeline uses the maximum mean discrepancy (MMD) to quantify differences in data distributions in a high-dimensional space for inference. With recordings from three hemispherical tool diameters and ten diverse surfaces, we conducted two degradation studies by decreasing sensing bandwidth and increasing added noise. We evaluate the haptic-auditory recognition performance achieved with the MMD to compare newly gathered data to each surface in our known library. The results indicate that acceleration signals alone have great potential for high-accuracy surface recognition and are robust against noise contamination. The optimal accelerometer bandwidth exceeds 1000 Hz, suggesting that useful vibrotactile information extends beyond human perception range. Finally, smaller tool tips generate contact vibrations with better noise robustness. The provided sensing guidelines may enable superhuman performance in portable surface recognition, which could benefit quality control, material documentation, and robotics.

Award: (Best ToH Short Paper Award at the IEEE Haptics Symposium Conference 2024)
Author(s): Behnam Khojasteh and Yitian Shao and Katherine J. Kuchenbecker
Journal: IEEE Transactions on Haptics
Volume: 17
Number (issue): 1
Pages: 58--65
Year: 2024
Month: January

Department(s): Haptische Intelligenz
Research Project(s): Surface Interactions as Probability Distributions in Embedding Spaces
Bibtex Type: Article (article)
Paper Type: Journal

Award Paper: Best ToH Short Paper Award at the IEEE Haptics Symposium Conference 2024
DOI: 10.1109/TOH.2024.3356609
Note: Presented at the IEEE Haptics Symposium
State: Published

BibTex

@article{Khojasteh24-TH-Discrepancy,
  title = {Robust Surface Recognition with the Maximum Mean Discrepancy: Degrading Haptic-Auditory Signals through Bandwidth and Noise},
  author = {Khojasteh, Behnam and Shao, Yitian and Kuchenbecker, Katherine J.},
  journal = {IEEE Transactions on Haptics},
  volume = {17},
  number = {1},
  pages = {58--65},
  month = jan,
  year = {2024},
  note = {Presented at the IEEE Haptics Symposium},
  doi = {10.1109/TOH.2024.3356609},
  month_numeric = {1}
}