Learning by Breaking: Food Fracture Anticipation for Robotic Food Manipulation
This study aimed to anticipate fractures of fragile food during robotic food manipulation. Anticipating fractures allows a robot to manipulate ingredients without irreversible failure. Food fracture models investigated in food texture fields explain the properties of fragile objects well. However, t...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9894412/ |
| _version_ | 1811206257725407232 |
|---|---|
| author | Reina Ishikawa Masashi Hamaya Felix Von Drigalski Kazutoshi Tanaka Atsushi Hashimoto |
| author_facet | Reina Ishikawa Masashi Hamaya Felix Von Drigalski Kazutoshi Tanaka Atsushi Hashimoto |
| author_sort | Reina Ishikawa |
| collection | DOAJ |
| description | This study aimed to anticipate fractures of fragile food during robotic food manipulation. Anticipating fractures allows a robot to manipulate ingredients without irreversible failure. Food fracture models investigated in food texture fields explain the properties of fragile objects well. However, they may not directly apply to robot manipulation due to the variance in physical properties even within the same ingredient. To this end, we developed a fracture-anticipation system with a tactile sensing module and a simple recurrent neural network. The key idea was to allow the robot to break ingredients during training-sample collection. The timing of fractures was identified via simple signal processing and used for supervision. We performed real robot experiments with three typical fragile foods: tofu, potato chips, and bananas. As the first step toward flexible fragile-object manipulation, we evaluated the proposed method for the fundamental task of object picking. The method successfully grasped the fragile foods without fractures in an online demonstration. In an offline evaluation, the method predicted the fractures with a recall of approximately 80% for all ingredients with 60 breaking trials. We believe that our method can be used to avoid breakage in other types of food manipulation, e.g., holding, pressing, and rolling. |
| first_indexed | 2024-04-12T03:44:43Z |
| format | Article |
| id | doaj.art-c0047f77bbc54cdca20c42ab52a7d96d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T03:44:43Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-c0047f77bbc54cdca20c42ab52a7d96d2022-12-22T03:49:11ZengIEEEIEEE Access2169-35362022-01-0110993219932910.1109/ACCESS.2022.32074919894412Learning by Breaking: Food Fracture Anticipation for Robotic Food ManipulationReina Ishikawa0https://orcid.org/0000-0003-4792-6380Masashi Hamaya1https://orcid.org/0000-0003-4189-8219Felix Von Drigalski2https://orcid.org/0000-0002-2679-8968Kazutoshi Tanaka3https://orcid.org/0000-0003-0880-9333Atsushi Hashimoto4https://orcid.org/0000-0002-0799-4269OMRON SINIC X Corporation, Tokyo, JapanOMRON SINIC X Corporation, Tokyo, JapanOMRON SINIC X Corporation, Tokyo, JapanOMRON SINIC X Corporation, Tokyo, JapanOMRON SINIC X Corporation, Tokyo, JapanThis study aimed to anticipate fractures of fragile food during robotic food manipulation. Anticipating fractures allows a robot to manipulate ingredients without irreversible failure. Food fracture models investigated in food texture fields explain the properties of fragile objects well. However, they may not directly apply to robot manipulation due to the variance in physical properties even within the same ingredient. To this end, we developed a fracture-anticipation system with a tactile sensing module and a simple recurrent neural network. The key idea was to allow the robot to break ingredients during training-sample collection. The timing of fractures was identified via simple signal processing and used for supervision. We performed real robot experiments with three typical fragile foods: tofu, potato chips, and bananas. As the first step toward flexible fragile-object manipulation, we evaluated the proposed method for the fundamental task of object picking. The method successfully grasped the fragile foods without fractures in an online demonstration. In an offline evaluation, the method predicted the fractures with a recall of approximately 80% for all ingredients with 60 breaking trials. We believe that our method can be used to avoid breakage in other types of food manipulation, e.g., holding, pressing, and rolling.https://ieeexplore.ieee.org/document/9894412/Robotic food manipulationfracture anticipationtactile sensing |
| spellingShingle | Reina Ishikawa Masashi Hamaya Felix Von Drigalski Kazutoshi Tanaka Atsushi Hashimoto Learning by Breaking: Food Fracture Anticipation for Robotic Food Manipulation IEEE Access Robotic food manipulation fracture anticipation tactile sensing |
| title | Learning by Breaking: Food Fracture Anticipation for Robotic Food Manipulation |
| title_full | Learning by Breaking: Food Fracture Anticipation for Robotic Food Manipulation |
| title_fullStr | Learning by Breaking: Food Fracture Anticipation for Robotic Food Manipulation |
| title_full_unstemmed | Learning by Breaking: Food Fracture Anticipation for Robotic Food Manipulation |
| title_short | Learning by Breaking: Food Fracture Anticipation for Robotic Food Manipulation |
| title_sort | learning by breaking food fracture anticipation for robotic food manipulation |
| topic | Robotic food manipulation fracture anticipation tactile sensing |
| url | https://ieeexplore.ieee.org/document/9894412/ |
| work_keys_str_mv | AT reinaishikawa learningbybreakingfoodfractureanticipationforroboticfoodmanipulation AT masashihamaya learningbybreakingfoodfractureanticipationforroboticfoodmanipulation AT felixvondrigalski learningbybreakingfoodfractureanticipationforroboticfoodmanipulation AT kazutoshitanaka learningbybreakingfoodfractureanticipationforroboticfoodmanipulation AT atsushihashimoto learningbybreakingfoodfractureanticipationforroboticfoodmanipulation |