Investigating Active Sampling for Hardness Classification with Vision-Based Tactile Sensors

• URL: http://arxiv.org/abs/2505.13231v1
• Date: Mon, 19 May 2025 15:15:27 GMT
• Title: Investigating Active Sampling for Hardness Classification with Vision-Based Tactile Sensors
• Authors: Junyi Chen, Alap Kshirsagar, Frederik Heller, Mario Gómez Andreu, Boris Belousov, Tim Schneider, Lisa P. Y. Lin, Katja Doerschner, Knut Drewing, Jan Peters,
• Abstract summary: One of the most important object properties that humans and robots perceive through touch is hardness.<n>This paper investigates information-theoretic active sampling strategies for sample-efficient hardness classification with vision-based tactile sensors.
• Score: 13.051209683232447
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: One of the most important object properties that humans and robots perceive through touch is hardness. This paper investigates information-theoretic active sampling strategies for sample-efficient hardness classification with vision-based tactile sensors. We evaluate three probabilistic classifier models and two model-uncertainty-based sampling strategies on a robotic setup as well as on a previously published dataset of samples collected by human testers. Our findings indicate that the active sampling approaches, driven by uncertainty metrics, surpass a random sampling baseline in terms of accuracy and stability. Additionally, while in our human study, the participants achieve an average accuracy of 48.00%, our best approach achieves an average accuracy of 88.78% on the same set of objects, demonstrating the effectiveness of vision-based tactile sensors for object hardness classification.

Related papers

• Multi-Class Human/Object Detection on Robot Manipulators using Proprioceptive Sensing [0.0]
  The aim of this study is to evaluate three-class human/object detection models, offering more detailed contact analysis.<n>A dataset was collected using the Franka Emika Panda robot manipulator, exploring preprocessing strategies for time-series analysis.<n>The best-performing model achieved 91.11% accuracy during real-time testing, demonstrating the feasibility of multi-class detection models.
  arXiv  Detail & Related papers  (2025-08-04T13:45:37Z)
• HeAL3D: Heuristical-enhanced Active Learning for 3D Object Detection [1.623951368574041]
  We introduce HeAL (Heuristical-enhanced Active Learning for 3D Object Detection) to deliver the most contributing samples to the model's training.<n>In contrast to previous works, our approach integrates achievesal features such as object distance and point-quantity to estimate the uncertainty.<n>Our evaluation on KITTI shows that HeAL presents competitive mAP with respect to the State-of-the-Art, and the same mAP as the full-supervised baseline with only 24% of the samples.
  arXiv  Detail & Related papers  (2025-05-01T13:24:55Z)
• Uncertainty for Active Learning on Graphs [70.44714133412592]
  Uncertainty Sampling is an Active Learning strategy that aims to improve the data efficiency of machine learning models.<n>We benchmark Uncertainty Sampling beyond predictive uncertainty and highlight a significant performance gap to other Active Learning strategies.<n>We develop ground-truth Bayesian uncertainty estimates in terms of the data generating process and prove their effectiveness in guiding Uncertainty Sampling toward optimal queries.
  arXiv  Detail & Related papers  (2024-05-02T16:50:47Z)
• What Matters for Active Texture Recognition With Vision-Based Tactile Sensors [17.019982978396122]
  We formalize the active sampling problem in the context of tactile fabric recognition. We investigate which components are crucial for quick and reliable texture recognition. Our best approach reaches 90.0% in under 5 touches, highlighting that vision-based tactile sensors are highly effective for fabric texture recognition.
  arXiv  Detail & Related papers  (2024-03-20T16:06:01Z)
• A model-free approach to fingertip slip and disturbance detection for grasp stability inference [0.0]
  We propose a method for assessing grasp stability using tactile sensing. We use highly sensitive Uskin tactile sensors mounted on an Allegro hand to test and validate our method.
  arXiv  Detail & Related papers  (2023-11-22T09:04:26Z)
• A Real-time Human Pose Estimation Approach for Optimal Sensor Placement in Sensor-based Human Activity Recognition [63.26015736148707]
  This paper introduces a novel methodology to resolve the issue of optimal sensor placement for Human Activity Recognition. The derived skeleton data provides a unique strategy for identifying the optimal sensor location. Our findings indicate that the vision-based method for sensor placement offers comparable results to the conventional deep learning approach.
  arXiv  Detail & Related papers  (2023-07-06T10:38:14Z)
• Learning to Detect Slip through Tactile Estimation of the Contact Force Field and its Entropy [6.739132519488627]
  We introduce a physics-informed, data-driven approach to detect slip continuously in real time. We employ the GelSight Mini, an optical tactile sensor, attached to custom-designed grippers to gather tactile data. Our results show that the best classification algorithm achieves a high average accuracy of 95.61%.
  arXiv  Detail & Related papers  (2023-03-02T03:16:21Z)
• BeCAPTCHA-Type: Biometric Keystroke Data Generation for Improved Bot Detection [63.447493500066045]
  This work proposes a data driven learning model for the synthesis of keystroke biometric data. The proposed method is compared with two statistical approaches based on Universal and User-dependent models. Our experimental framework considers a dataset with 136 million keystroke events from 168 thousand subjects.
  arXiv  Detail & Related papers  (2022-07-27T09:26:15Z)
• Fingerprint Liveness Detection Based on Quality Measures [66.76480178498315]
  The novel feature set is used in a complete liveness detection system and tested on the development set of the LivDET competition. The proposed solution proves to be robust to the multi-sensor scenario, and presents an overall rate of 93% of correctly classified samples.
  arXiv  Detail & Related papers  (2022-07-11T12:15:27Z)
• A high performance fingerprint liveness detection method based on quality related features [66.41574316136379]
  The system is tested on a highly challenging database comprising over 10,500 real and fake images. The proposed solution proves to be robust to the multi-scenario dataset, and presents an overall rate of 90% correctly classified samples.
  arXiv  Detail & Related papers  (2021-11-02T21:09:39Z)
• Robust and Accurate Object Detection via Adversarial Learning [111.36192453882195]
  This work augments the fine-tuning stage for object detectors by exploring adversarial examples. Our approach boosts the performance of state-of-the-art EfficientDets by +1.1 mAP on the object detection benchmark.
  arXiv  Detail & Related papers  (2021-03-23T19:45:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.