A novel dynamic-vision-based approach for tactile sensing applications
- Submitting institution
-
Kingston University
- Unit of assessment
- 12 - Engineering
- Output identifier
- 12-105-1657
- Type
- D - Journal article
- DOI
-
10.1109/TIM.2019.2919354
- Title of journal
- IEEE Transactions on Instrumentation and Measurement
- Article number
- -
- First page
- 1881
- Volume
- 69
- Issue
- -
- ISSN
- 0018-9456
- Open access status
- Compliant
- Month of publication
- -
- Year of publication
- 2020
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- Yes
- Number of additional authors
-
-
- Research group(s)
-
-
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- Techniques that estimate contact forces and classify materials between robotic hands and dynamic objects are essential because such estimation and classification are useful for automated manufacturing, but have drawbacks, this paper proposes a new method that solves these drawbacks. This paper is significant in developing fast contact force estimation and material classification techniques for robotic hands grasping and manipulation, showing for the first time how neuromorphic event-based vision sensor and machine learning can be used to estimate the contact force events and classify materials. In collaboration with George’s Hospital, AOUK fund was generated to evaluate the proposed approach.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -