Recognition of Human Chef’s Intentions for Incremental Learning of Cookbook by Robotic Salad Chef
Robotic chefs are a promising technology that can bring sizeable health and economic benefits when deployed ubiquitously. This deployment is hindered by the costly process of programming the robots to cook specific dishes while humans learn from observation or freely available videos. In this paper,...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10124218/ |
| _version_ | 1797804041986637824 |
|---|---|
| author | Grzegorz Sochacki Arsen Abdulali Narges Khadem Hosseini Fumiya Iida |
| author_facet | Grzegorz Sochacki Arsen Abdulali Narges Khadem Hosseini Fumiya Iida |
| author_sort | Grzegorz Sochacki |
| collection | DOAJ |
| description | Robotic chefs are a promising technology that can bring sizeable health and economic benefits when deployed ubiquitously. This deployment is hindered by the costly process of programming the robots to cook specific dishes while humans learn from observation or freely available videos. In this paper, we propose an algorithm that incrementally adds recipes to the robot’s cookbook based on the visual observation of a human chef, enabling the easier and cheaper deployment of robotic chefs. A new recipe is added only if the current observation is substantially different than all recipes in the cookbook, which is decided by computing the similarity between the vectorizations of these two. The algorithm correctly recognizes known recipes in 93% of the demonstrations and successfully learned new recipes when shown, using off-the-shelf neural networks for computer vision. We show that videos and demonstrations are viable sources of data for robotic chef programming when extended to massive publicly available data sources like YouTube. |
| first_indexed | 2024-03-13T05:30:11Z |
| format | Article |
| id | doaj.art-29258644c2a540e7a903c45bfeee015d |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-13T05:30:11Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-29258644c2a540e7a903c45bfeee015d2023-06-14T23:00:26ZengIEEEIEEE Access2169-35362023-01-0111570065702010.1109/ACCESS.2023.327623410124218Recognition of Human Chef’s Intentions for Incremental Learning of Cookbook by Robotic Salad ChefGrzegorz Sochacki0https://orcid.org/0009-0007-5661-0210Arsen Abdulali1Narges Khadem Hosseini2Fumiya Iida3https://orcid.org/0000-0001-9246-7190Department of Engineering, Bio-Inspired Robotics Laboratory (BIRL), University of Cambridge, Cambridge, U.KDepartment of Engineering, Bio-Inspired Robotics Laboratory (BIRL), University of Cambridge, Cambridge, U.KDepartment of Engineering, Bio-Inspired Robotics Laboratory (BIRL), University of Cambridge, Cambridge, U.KDepartment of Engineering, Bio-Inspired Robotics Laboratory (BIRL), University of Cambridge, Cambridge, U.KRobotic chefs are a promising technology that can bring sizeable health and economic benefits when deployed ubiquitously. This deployment is hindered by the costly process of programming the robots to cook specific dishes while humans learn from observation or freely available videos. In this paper, we propose an algorithm that incrementally adds recipes to the robot’s cookbook based on the visual observation of a human chef, enabling the easier and cheaper deployment of robotic chefs. A new recipe is added only if the current observation is substantially different than all recipes in the cookbook, which is decided by computing the similarity between the vectorizations of these two. The algorithm correctly recognizes known recipes in 93% of the demonstrations and successfully learned new recipes when shown, using off-the-shelf neural networks for computer vision. We show that videos and demonstrations are viable sources of data for robotic chef programming when extended to massive publicly available data sources like YouTube.https://ieeexplore.ieee.org/document/10124218/Computer visionhidden Markov modellearning by demonstrationrobotic chefsalad chef |
| spellingShingle | Grzegorz Sochacki Arsen Abdulali Narges Khadem Hosseini Fumiya Iida Recognition of Human Chef’s Intentions for Incremental Learning of Cookbook by Robotic Salad Chef IEEE Access Computer vision hidden Markov model learning by demonstration robotic chef salad chef |
| title | Recognition of Human Chef’s Intentions for Incremental Learning of Cookbook by Robotic Salad Chef |
| title_full | Recognition of Human Chef’s Intentions for Incremental Learning of Cookbook by Robotic Salad Chef |
| title_fullStr | Recognition of Human Chef’s Intentions for Incremental Learning of Cookbook by Robotic Salad Chef |
| title_full_unstemmed | Recognition of Human Chef’s Intentions for Incremental Learning of Cookbook by Robotic Salad Chef |
| title_short | Recognition of Human Chef’s Intentions for Incremental Learning of Cookbook by Robotic Salad Chef |
| title_sort | recognition of human chef x2019 s intentions for incremental learning of cookbook by robotic salad chef |
| topic | Computer vision hidden Markov model learning by demonstration robotic chef salad chef |
| url | https://ieeexplore.ieee.org/document/10124218/ |
| work_keys_str_mv | AT grzegorzsochacki recognitionofhumanchefx2019sintentionsforincrementallearningofcookbookbyroboticsaladchef AT arsenabdulali recognitionofhumanchefx2019sintentionsforincrementallearningofcookbookbyroboticsaladchef AT nargeskhademhosseini recognitionofhumanchefx2019sintentionsforincrementallearningofcookbookbyroboticsaladchef AT fumiyaiida recognitionofhumanchefx2019sintentionsforincrementallearningofcookbookbyroboticsaladchef |