Learning to Predict Perceptual Distributions of Haptic Adjectives
When humans touch an object with their fingertips, they can immediately describe its tactile properties using haptic adjectives, such as hardness and roughness; however, human perception is subjective and noisy, with significant variation across individuals and interactions. Recent research has work...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2020-02-01
|
| Series: | Frontiers in Neurorobotics |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/article/10.3389/fnbot.2019.00116/full |
| _version_ | 1828396811097735168 |
|---|---|
| author | Benjamin A. Richardson Katherine J. Kuchenbecker |
| author_facet | Benjamin A. Richardson Katherine J. Kuchenbecker |
| author_sort | Benjamin A. Richardson |
| collection | DOAJ |
| description | When humans touch an object with their fingertips, they can immediately describe its tactile properties using haptic adjectives, such as hardness and roughness; however, human perception is subjective and noisy, with significant variation across individuals and interactions. Recent research has worked to provide robots with similar haptic intelligence but was focused on identifying binary haptic adjectives, ignoring both attribute intensity and perceptual variability. Combining ordinal haptic adjective labels gathered from human subjects for a set of 60 objects with features automatically extracted from raw multi-modal tactile data collected by a robot repeatedly touching the same objects, we designed a machine-learning method that incorporates partial knowledge of the distribution of object labels into training; then, from a single interaction, it predicts a probability distribution over the set of ordinal labels. In addition to analyzing the collected labels (10 basic haptic adjectives) and demonstrating the quality of our method's predictions, we hold out specific features to determine the influence of individual sensor modalities on the predictive performance for each adjective. Our results demonstrate the feasibility of modeling both the intensity and the variation of haptic perception, two crucial yet previously neglected components of human haptic perception. |
| first_indexed | 2024-12-10T08:37:48Z |
| format | Article |
| id | doaj.art-12e668a033804d5abd0b1fe522440355 |
| institution | Directory Open Access Journal |
| issn | 1662-5218 |
| language | English |
| last_indexed | 2024-12-10T08:37:48Z |
| publishDate | 2020-02-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Neurorobotics |
| spelling | doaj.art-12e668a033804d5abd0b1fe5224403552022-12-22T01:55:56ZengFrontiers Media S.A.Frontiers in Neurorobotics1662-52182020-02-011310.3389/fnbot.2019.00116449773Learning to Predict Perceptual Distributions of Haptic AdjectivesBenjamin A. RichardsonKatherine J. KuchenbeckerWhen humans touch an object with their fingertips, they can immediately describe its tactile properties using haptic adjectives, such as hardness and roughness; however, human perception is subjective and noisy, with significant variation across individuals and interactions. Recent research has worked to provide robots with similar haptic intelligence but was focused on identifying binary haptic adjectives, ignoring both attribute intensity and perceptual variability. Combining ordinal haptic adjective labels gathered from human subjects for a set of 60 objects with features automatically extracted from raw multi-modal tactile data collected by a robot repeatedly touching the same objects, we designed a machine-learning method that incorporates partial knowledge of the distribution of object labels into training; then, from a single interaction, it predicts a probability distribution over the set of ordinal labels. In addition to analyzing the collected labels (10 basic haptic adjectives) and demonstrating the quality of our method's predictions, we hold out specific features to determine the influence of individual sensor modalities on the predictive performance for each adjective. Our results demonstrate the feasibility of modeling both the intensity and the variation of haptic perception, two crucial yet previously neglected components of human haptic perception.https://www.frontiersin.org/article/10.3389/fnbot.2019.00116/fullhaptic intelligenceperceptionordinal regressiontactile sensingpredicting probability distributionshaptic adjectives |
| spellingShingle | Benjamin A. Richardson Katherine J. Kuchenbecker Learning to Predict Perceptual Distributions of Haptic Adjectives Frontiers in Neurorobotics haptic intelligence perception ordinal regression tactile sensing predicting probability distributions haptic adjectives |
| title | Learning to Predict Perceptual Distributions of Haptic Adjectives |
| title_full | Learning to Predict Perceptual Distributions of Haptic Adjectives |
| title_fullStr | Learning to Predict Perceptual Distributions of Haptic Adjectives |
| title_full_unstemmed | Learning to Predict Perceptual Distributions of Haptic Adjectives |
| title_short | Learning to Predict Perceptual Distributions of Haptic Adjectives |
| title_sort | learning to predict perceptual distributions of haptic adjectives |
| topic | haptic intelligence perception ordinal regression tactile sensing predicting probability distributions haptic adjectives |
| url | https://www.frontiersin.org/article/10.3389/fnbot.2019.00116/full |
| work_keys_str_mv | AT benjaminarichardson learningtopredictperceptualdistributionsofhapticadjectives AT katherinejkuchenbecker learningtopredictperceptualdistributionsofhapticadjectives |