Spike-timing based coding in neuromimetic tactile system enables dynamic object classification
Authors/Creators
- 1. Uppsala University
- 2. Karolinska Institute
Description
Coding dynamic tactile information in spike timing is essential to human haptic exploration and dexterous object manipulation. Conventional electronic skins generate frames of tactile signals upon interaction with objects and are unfortunately ill-suited for efficient coding of temporal information and rapid feature extraction. Here, we report a neuromorphic tactile system that uses spike timing, especially the first-spike timing, to code dynamic tactile information about touch and grasp. This strategy enables the system to seamlessly code highly dynamic information with millisecond temporal resolution on par with the biological nervous system, yielding dynamic extraction of tactile features. Upon interaction with objects, the system rapidly classifies them in the initial phase of touch and grasp, thus paving the way to fast tactile feedback desired for neuro-robotics and neuro-prosthetics.
Notes
Funding provided by: Swedish Research Council
Crossref Funder Registry ID: https://ror.org/03zttf063
Award Number: 2019-05484
Funding provided by: Swedish Research Council
Crossref Funder Registry ID: https://ror.org/03zttf063
Award Number: 2022-06725
Funding provided by: Swedish Foundation for Strategic Research
Crossref Funder Registry ID: https://ror.org/044wr7g58
Award Number: FUS21-0067
Funding provided by: European Horizon 2020 Research and Innovation Program
Award Number: 965044
Funding provided by: eSSENCE Research Program
Award Number:
Methods
The method is provided in SM. In brief, the raw data of spike trains in voltage were generated and collected by using the e-skin that touched surfaces and grasped objects. The raw data was converted to digital spike trains with 1 as a spike and 0 as non-spike. The processed spike trains were analyzed to study the encoding performance of the system and were used to train and test the spiking neural networks for classification tasks. The tabular data provided are corresponding to the main text figures (i.e., Fig 2, Fig 3 and Fig 4).
Files
README.md
Files
(768.6 kB)
| Name | Size | Download all |
|---|---|---|
|
md5:4e6745645fdd24a4daaa8934e19137f9
|
503.2 kB | Download |
|
md5:03890f30bec304bd4f997c21ed843ed7
|
20.1 kB | Download |
|
md5:1666a4b6677af7bdeb6d95c3b46231d3
|
9.0 kB | Download |
|
md5:788127bcdd9146bff0d938eb1bc471e9
|
10.3 kB | Download |
|
md5:5690d7f389b8affcee950ad99906ce63
|
35.8 kB | Download |
|
md5:5171cbb463cda5ccc53d259c285f85de
|
38.5 kB | Download |
|
md5:5ef60bbaae8594b8754ee661f375195b
|
9.0 kB | Download |
|
md5:c7215349ca346216e9f06c70c95dce58
|
8.9 kB | Download |
|
md5:3d403d71e0bf4b8807fac4fc82ddc981
|
9.0 kB | Download |
|
md5:1fda3ba40159fa55396fe3e2cf0b8a93
|
9.3 kB | Download |
|
md5:a9f6728051718f653a53ea2a0561e8b0
|
9.7 kB | Download |
|
md5:f8701d44cfd1bf86c594e4e8c39727f0
|
14.1 kB | Download |
|
md5:69aec3327b9188c1226b847522984f28
|
26.8 kB | Download |
|
md5:e2d2c3d6d86e0ce135c731fa41b76b0d
|
30.2 kB | Download |
|
md5:6bebbcfc2fc2e3f6b6714c4481dcf61e
|
30.1 kB | Download |
|
md5:aa56c29d40499b8f1868a50781f8e268
|
4.5 kB | Preview Download |