Learning When to Stop: Efficient Active Tactile Perception with Deep Reinforcement Learning
Open accessThe DOI matches its Crossref record; 20 of the 20 references it cites were found in a registry or an index.
Abstract
Actively guiding attention is an important mechanism to employ limited processing resources efficiently. The Recurrent Visual Attention Model (RAM) has been successfully applied to process large input images by sequentially attending to smaller image regions with an RL framework. In tactile perception, sequential attention methods are required naturally due to the limited size of the tactile receptive field. The concept of RAM was transferred to the haptic domain by the Haptic Attention Model (HAM) to iteratively generate a fixed number of informative haptic glances for tactile object classification. We extend HAM to a system capable of actively determining when sufficient haptic data is available for reliable classification. To this end, we introduce a hybrid action space, augmenting the continuous glance location with the discrete decision of when to classify. This allows balancing the cost of obtaining new samples against the cost of misclassification, resulting in an optimized number of glances while maintaining reasonable accuracy. We evaluate the efficiency of our approach on a handcrafted dataset, which allows us to compute the most efficient glance locations.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
Proximal Policy Optimization Algorithms
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., & Klimov, O. (2017) · arXiv · doi:10.48550/arxiv.1707.06347 · Cited by 10,625
(1999) · Cited by 5,147
MuJoCo: A physics engine for model-based control
Todorov, E., Erez, T., & Tassa, Y. (2012) · 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2012.6386109 · Cited by 4,767 · cited 1×
“IV-A with an open-source simulation based on MuJoCo [19] with ROS support 1 .”
Trust region policy optimization
Schulman, J., Levine, S., Moritz, P., Jordan, M. I., & Abbeel, P. (2015) · arXiv · doi:10.48550/arxiv.1502.05477 · Cited by 4,578
Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning
Williams, R. J. (1992) · Machine Learning · doi:10.1007/bf00992696 · Cited by 3,416 · cited 1×
“1) Policy Optimization: To learn a policy that generates efficient glance parameters a g and decisions a d , we use the RL algorithm REINFORCE with baseline [11], which is also employed by RAM and HAM.”
Recurrent Models of Visual Attention
Mnih, V., Heess, N., Graves, A., & Kavukcuoglu, K. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1406.6247 · Cited by 2,568
High-Dimensional Continuous Control Using Generalized Advantage Estimation
Schulman, J., Moritz, P., Levine, S., Jordan, M., & Abbeel, P. (2015) · arXiv · doi:10.48550/arxiv.1506.02438 · Cited by 2,103
Robotic tactile perception of object properties: A review
Luo, S., Bimbo, J., Dahiya, R., & Liu, H. (2017) · Mechatronics · doi:10.1016/j.mechatronics.2017.11.002 · Cited by 425 · cited 1×
“Active object exploration based on tactile feedback has become a popular area of research in robotics [1].”
Bayesian Exploration for Intelligent Identification of Textures
Fishel, J. A., & Loeb, G. E. (2012) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2012.00004 · Cited by 358 · cited 1×
“Early works base their exploration policy on Bayesian inference [2], [3], [4] or Gaussian processes [5].”
Research works printed but not linked: 1
- Sutton, 2018, Reinforcement Learning: An Introduction
Cited by
Precision-Focused Reinforcement Learning Model for Robotic Object Pushing
Bergmann, L., Leins, D. P., Haschke, R., & Neumann, K. (2025) · International Conference on Advanced Robotics and Mechatronics (ICARM) · doi:10.1109/icarm65671.2025.11293485
Self-citation
Metadata
- Authors
- Niemann, C., Leins, D., Lach, L., & Haschke, R.
- Affiliations
- Bielefeld University (DE)
- Institut de Robòtica i Informàtica Industrial (ES)
- Venue
- 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
- Publisher
- IEEE
- Published
- 2024-10-14
- Pages
- 685-692
- ISSN
- 2153-0858 (ISSN-L)
- OpenAlex
- W4405785133
- Semantic Scholar
- 24af025775b214a9b047ce3b3ec2702bb385b621
- Cited by
- 1
- References
- 20
- Citations by year
- 2025: 1
- FWCI
- 0.63
- Type
- conference paper
- Language
- en
- Open access
- green
- pub.uni-bielefeld.de
- Locations
- IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (publishedVersion)
- Publikationen an der Universität Bielefeld (Universität Bielefeld) (submittedVersion, cc-by)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Life Sciences › Neuroscience › Cognitive Neuroscience › Tactile and Sensory Interactions
- Keywords
- deep reinforcement learning, stopping rules, hybrid action space, cost-sensitive classification
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Learning When to Stop: Efficient Active Tactile Perception with Deep Reinforcement Learning. https://app.cochat.ai/papers/10.1109/iros58592.2024.10801966
- The paper
- Niemann, C., Leins, D., Lach, L., & Haschke, R. (2024). Learning When to Stop: Efficient Active Tactile Perception with Deep Reinforcement Learning. 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). https://doi.org/10.1109/iros58592.2024.10801966
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.