How the Environment Shapes Tactile Sensing: Understanding the Relationship between Tactile Filters and Surrounding Environment
Frontiers in Robotics and AI
MetadataShow full item record
Costi, L., Maiolino, P., & Iida, F. How the Environment Shapes Tactile Sensing: Understanding the Relationship between Tactile Filters and Surrounding Environment. Frontiers in Robotics and AI https://doi.org/10.17863/CAM.85420
The mechanical properties of a sensor strongly affect its tactile sensing capabilities. By exploiting tactile filters, mechanical structures between the sensing unit and the environment, it is possible to tune the interaction dynamics with the surrounding environment. But how can we design a good tactile filter? Previously, the role of filters' geometry and stiffness on the quality of the tactile data has been the subject of several studies, both implementing static filters and adaptable filters. State-of-the-art works on online adaptive stiffness highlight a crucial role of the filters' mechanical behaviour in the structure of the recorded tactile data. However, the relation between the filter's and environment's characteristics is still largely unknown. We want to show what is the effect of the environment's mechanical properties on the structure of the acquired tactile data and the performance of a classification task, while testing a wide range of static tactile filters. Moreover, we fabricate the filters using 4 materials commonly exploited in soft robotics, to merge the gap between tactile sensing and robotic applications. We collect data from the interaction with a standard set of 12 objects of different materials, shapes and textures, and we analyze the effect of the filter's material on the structure of such data and the performance of 9 common machine learning classifiers, both considering the overall test set and the 3 individual subsets made by all objects of the same material. We show that depending on the material of the test objects, there is a drastic change in performance of the 4 tested filters, and that the filter that matches the mechanical properties of the environment always outperforms the others.
This work was supported by the SMART project, European Union's Horizon 2020 research and innovation under the Marie Sklodowska-Curie (grant agreement ID 860108).
European Commission Horizon 2020 (H2020) Marie Sk?odowska-Curie actions (860108)
Embargo Lift Date
This record's DOI: https://doi.org/10.17863/CAM.85420
This record's URL: https://www.repository.cam.ac.uk/handle/1810/338015
Attribution 4.0 International
Licence URL: https://creativecommons.org/licenses/by/4.0/