Neuro-Cognitive Locomotion with Dynamic Attention on Topological Structure
This paper discusses a mechanism for integrating locomotion with cognition in robots. We demonstrate an attentional ability model that can dynamically change the focus of its perceptual area by integrating attention and perception to generate behavior. The proposed model considers both internal sens...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Machines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-1702/11/6/619 |
| _version_ | 1827736632609996800 |
|---|---|
| author | Azhar Aulia Saputra János Botzheim Naoyuki Kubota |
| author_facet | Azhar Aulia Saputra János Botzheim Naoyuki Kubota |
| author_sort | Azhar Aulia Saputra |
| collection | DOAJ |
| description | This paper discusses a mechanism for integrating locomotion with cognition in robots. We demonstrate an attentional ability model that can dynamically change the focus of its perceptual area by integrating attention and perception to generate behavior. The proposed model considers both internal sensory information and also external sensory information. We also propose affordance detection that identifies different actions depending on the robot’s immediate possibilities. Attention is represented in a topological structure generated by a growing neural gas that uses 3D point-cloud data. When the robot faces an obstacle, the topological map density increases in the suspected obstacle area. From here, affordance information is processed directly into the behavior pattern generator, which comprises interconnections between motor and internal sensory neurons. The attention model increases the density associated with the suspected obstacle to produce a detailed representation of the obstacle. Then, the robot processes the cognitive information to enact a short-term adaptation to its locomotion by changing its swing pattern or movement plan. To test the effectiveness of the proposed model, it is implemented in a computer simulation and also in a medium-sized, four-legged robot. The experiments validate the advantages in three categories: (1) Development of attention model using topological structure, (2) Integration between attention and affordance in moving behavior, (3) Integration of exteroceptive sensory information to lower-level control of locomotion generator. |
| first_indexed | 2024-03-11T02:13:09Z |
| format | Article |
| id | doaj.art-1849f1a592b641a88179e72b4181bb07 |
| institution | Directory Open Access Journal |
| issn | 2075-1702 |
| language | English |
| last_indexed | 2024-03-11T02:13:09Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Machines |
| spelling | doaj.art-1849f1a592b641a88179e72b4181bb072023-11-18T11:20:41ZengMDPI AGMachines2075-17022023-06-0111661910.3390/machines11060619Neuro-Cognitive Locomotion with Dynamic Attention on Topological StructureAzhar Aulia Saputra0János Botzheim1Naoyuki Kubota2Graduate School of System Design, Tokyo Metropolitan University, 6-6 Asahigaoka, Hino 191-0065, Tokyo, JapanDepartment of Artificial Intelligence, Faculty of Informatics, Eötvös Loránd University, Pázmány Péter sétány 1/A, H-1117 Budapest, HungaryGraduate School of System Design, Tokyo Metropolitan University, 6-6 Asahigaoka, Hino 191-0065, Tokyo, JapanThis paper discusses a mechanism for integrating locomotion with cognition in robots. We demonstrate an attentional ability model that can dynamically change the focus of its perceptual area by integrating attention and perception to generate behavior. The proposed model considers both internal sensory information and also external sensory information. We also propose affordance detection that identifies different actions depending on the robot’s immediate possibilities. Attention is represented in a topological structure generated by a growing neural gas that uses 3D point-cloud data. When the robot faces an obstacle, the topological map density increases in the suspected obstacle area. From here, affordance information is processed directly into the behavior pattern generator, which comprises interconnections between motor and internal sensory neurons. The attention model increases the density associated with the suspected obstacle to produce a detailed representation of the obstacle. Then, the robot processes the cognitive information to enact a short-term adaptation to its locomotion by changing its swing pattern or movement plan. To test the effectiveness of the proposed model, it is implemented in a computer simulation and also in a medium-sized, four-legged robot. The experiments validate the advantages in three categories: (1) Development of attention model using topological structure, (2) Integration between attention and affordance in moving behavior, (3) Integration of exteroceptive sensory information to lower-level control of locomotion generator.https://www.mdpi.com/2075-1702/11/6/619dynamic attentiontopological map modelaffordance detectionneuro-cognitive locomotion |
| spellingShingle | Azhar Aulia Saputra János Botzheim Naoyuki Kubota Neuro-Cognitive Locomotion with Dynamic Attention on Topological Structure Machines dynamic attention topological map model affordance detection neuro-cognitive locomotion |
| title | Neuro-Cognitive Locomotion with Dynamic Attention on Topological Structure |
| title_full | Neuro-Cognitive Locomotion with Dynamic Attention on Topological Structure |
| title_fullStr | Neuro-Cognitive Locomotion with Dynamic Attention on Topological Structure |
| title_full_unstemmed | Neuro-Cognitive Locomotion with Dynamic Attention on Topological Structure |
| title_short | Neuro-Cognitive Locomotion with Dynamic Attention on Topological Structure |
| title_sort | neuro cognitive locomotion with dynamic attention on topological structure |
| topic | dynamic attention topological map model affordance detection neuro-cognitive locomotion |
| url | https://www.mdpi.com/2075-1702/11/6/619 |
| work_keys_str_mv | AT azharauliasaputra neurocognitivelocomotionwithdynamicattentionontopologicalstructure AT janosbotzheim neurocognitivelocomotionwithdynamicattentionontopologicalstructure AT naoyukikubota neurocognitivelocomotionwithdynamicattentionontopologicalstructure |