Journal
IEEE SENSORS JOURNAL
Volume 18, Issue 9, Pages 3852-3863Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSEN.2018.2814839
Keywords
Robot sensing systems; force feedback; neural networks
Funding
- National Science Foundation [CNS-1544636]
- Direct For Computer & Info Scie & Enginr [1544895] Funding Source: National Science Foundation
- Division Of Computer and Network Systems [1544636] Funding Source: National Science Foundation
Ask authors/readers for more resources
Recent advances in robotics promise a future where robots co-exist and collaborate with humans in unstructured environments, which will require frequent physical interactions where accurate tactile information will be crucial for performance and safety. This article describes the design, fabrication, modeling, and experimental validation of a soft-bodied tactile sensor that accurately measures the complete 3-D force vector for both normal and shear loading conditions. Our research considers the detection of changes in the magnetic field vector due to the motion of a miniature magnet in a soft substrate to measure normal and shear forces with high accuracy and bandwidth. The proposed sensor is a pyramid-shaped tactile unit with a tri-axis Hall element and a magnet embedded in a silicone rubber substrate. The non-linear mapping between the 3-D force vector and the Hall effect voltages is characterized by training a neural network. We validate the proposed soft force sensor over static and dynamic loading experiments and obtain a mean absolute error below 11.7 mN or 2.2% of the force range. These results were obtained for a soft force sensor prototype and loading conditions not included in the training process, indicating strong generalization of the model. To demonstrate its utility, the proposed sensor is used in a force-controlled pick-and-place experiment as a proof-of-concept case study.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available