Using neuroevolution for designing soft medical devices
Soft robots can exhibit better performance in specific tasks compared to conventional robots, particularly in healthcare related tasks. However, the field of soft robotics is still young, and designing them often involves mimicking natural organisms or relying heavily on human experts’ creativity. A...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-03-01
|
| Series: | Biomimetic Intelligence and Robotics |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667379724000639 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832589987372072960 |
|---|---|
| author | Hugo Alcaraz-Herrera Michail-Antisthenis Tsompanas Igor Balaz Andrew Adamatzky |
| author_facet | Hugo Alcaraz-Herrera Michail-Antisthenis Tsompanas Igor Balaz Andrew Adamatzky |
| author_sort | Hugo Alcaraz-Herrera |
| collection | DOAJ |
| description | Soft robots can exhibit better performance in specific tasks compared to conventional robots, particularly in healthcare related tasks. However, the field of soft robotics is still young, and designing them often involves mimicking natural organisms or relying heavily on human experts’ creativity. A formal automated design process is required. The use of neuroevolution-based algorithms to automatically design initial sketches of soft actuators that can enable the movement of future medical devices, such as drug-delivering catheters, is proposed. The actuator morphologies discovered by algorithms like Age-Fitness Pareto Optimisation, NeuroEvolution of Augmenting Topologies (NEAT), and Hypercube-based NEAT (HyperNEAT) were compared based on the maximum displacement reached and their robustness against various control methods. Analysing the results granted the insight that neuroevolution-based algorithms produce better-performing and more robust actuators under diverse control methods. Specifically, the best-performing morphologies were discovered by the NEAT algorithm. |
| format | Article |
| id | doaj-art-8466a923521b4030bfde5df86be4c3b8 |
| institution | Kabale University |
| issn | 2667-3797 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Biomimetic Intelligence and Robotics |
| spelling | doaj-art-8466a923521b4030bfde5df86be4c3b82025-01-24T04:45:57ZengElsevierBiomimetic Intelligence and Robotics2667-37972025-03-0151100205Using neuroevolution for designing soft medical devicesHugo Alcaraz-Herrera0Michail-Antisthenis Tsompanas1Igor Balaz2Andrew Adamatzky3Unconventional Computing Laboratory, University of the West of England, Bristol BS16 1QY, United Kingdom; Corresponding author.Unconventional Computing Laboratory, University of the West of England, Bristol BS16 1QY, United Kingdom; School of Computing & Creative Technologies, University of the West of England, Bristol BS16 1QY, United KingdomLaboratory for Meteorology, Physics and Biophysics, Faculty of Agriculture, University of Novi Sad, Novi Sad 21000, SerbiaUnconventional Computing Laboratory, University of the West of England, Bristol BS16 1QY, United KingdomSoft robots can exhibit better performance in specific tasks compared to conventional robots, particularly in healthcare related tasks. However, the field of soft robotics is still young, and designing them often involves mimicking natural organisms or relying heavily on human experts’ creativity. A formal automated design process is required. The use of neuroevolution-based algorithms to automatically design initial sketches of soft actuators that can enable the movement of future medical devices, such as drug-delivering catheters, is proposed. The actuator morphologies discovered by algorithms like Age-Fitness Pareto Optimisation, NeuroEvolution of Augmenting Topologies (NEAT), and Hypercube-based NEAT (HyperNEAT) were compared based on the maximum displacement reached and their robustness against various control methods. Analysing the results granted the insight that neuroevolution-based algorithms produce better-performing and more robust actuators under diverse control methods. Specifically, the best-performing morphologies were discovered by the NEAT algorithm.http://www.sciencedirect.com/science/article/pii/S2667379724000639NEATHyperNEATAFPOSoft robotActuatorCatheter |
| spellingShingle | Hugo Alcaraz-Herrera Michail-Antisthenis Tsompanas Igor Balaz Andrew Adamatzky Using neuroevolution for designing soft medical devices Biomimetic Intelligence and Robotics NEAT HyperNEAT AFPO Soft robot Actuator Catheter |
| title | Using neuroevolution for designing soft medical devices |
| title_full | Using neuroevolution for designing soft medical devices |
| title_fullStr | Using neuroevolution for designing soft medical devices |
| title_full_unstemmed | Using neuroevolution for designing soft medical devices |
| title_short | Using neuroevolution for designing soft medical devices |
| title_sort | using neuroevolution for designing soft medical devices |
| topic | NEAT HyperNEAT AFPO Soft robot Actuator Catheter |
| url | http://www.sciencedirect.com/science/article/pii/S2667379724000639 |
| work_keys_str_mv | AT hugoalcarazherrera usingneuroevolutionfordesigningsoftmedicaldevices AT michailantisthenistsompanas usingneuroevolutionfordesigningsoftmedicaldevices AT igorbalaz usingneuroevolutionfordesigningsoftmedicaldevices AT andrewadamatzky usingneuroevolutionfordesigningsoftmedicaldevices |