Robots that can adapt like animals
- PMID: 26017452
- DOI: 10.1038/nature14422
Robots that can adapt like animals
Abstract
Robots have transformed many industries, most notably manufacturing, and have the power to deliver tremendous benefits to society, such as in search and rescue, disaster response, health care and transportation. They are also invaluable tools for scientific exploration in environments inaccessible to humans, from distant planets to deep oceans. A major obstacle to their widespread adoption in more complex environments outside factories is their fragility. Whereas animals can quickly adapt to injuries, current robots cannot 'think outside the box' to find a compensatory behaviour when they are damaged: they are limited to their pre-specified self-sensing abilities, can diagnose only anticipated failure modes, and require a pre-programmed contingency plan for every type of potential damage, an impracticality for complex robots. A promising approach to reducing robot fragility involves having robots learn appropriate behaviours in response to damage, but current techniques are slow even with small, constrained search spaces. Here we introduce an intelligent trial-and-error algorithm that allows robots to adapt to damage in less than two minutes in large search spaces without requiring self-diagnosis or pre-specified contingency plans. Before the robot is deployed, it uses a novel technique to create a detailed map of the space of high-performing behaviours. This map represents the robot's prior knowledge about what behaviours it can perform and their value. When the robot is damaged, it uses this prior knowledge to guide a trial-and-error learning algorithm that conducts intelligent experiments to rapidly discover a behaviour that compensates for the damage. Experiments reveal successful adaptations for a legged robot injured in five different ways, including damaged, broken, and missing legs, and for a robotic arm with joints broken in 14 different ways. This new algorithm will enable more robust, effective, autonomous robots, and may shed light on the principles that animals use to adapt to injury.
Comment in
-
Artificial intelligence: Robots with instincts.Nature. 2015 May 28;521(7553):426-7. doi: 10.1038/521426a. Nature. 2015. PMID: 26017437 No abstract available.
Similar articles
-
Artificial intelligence: Robots with instincts.Nature. 2015 May 28;521(7553):426-7. doi: 10.1038/521426a. Nature. 2015. PMID: 26017437 No abstract available.
-
Flocking algorithm for autonomous flying robots.Bioinspir Biomim. 2014 Jun;9(2):025012. doi: 10.1088/1748-3182/9/2/025012. Epub 2014 May 22. Bioinspir Biomim. 2014. PMID: 24852272
-
Developmental perception of the self and action.IEEE Trans Neural Netw Learn Syst. 2014 Jan;25(1):183-202. doi: 10.1109/TNNLS.2013.2271793. IEEE Trans Neural Netw Learn Syst. 2014. PMID: 24806653
-
Fish-inspired robots: design, sensing, actuation, and autonomy--a review of research.Bioinspir Biomim. 2016 Apr 13;11(3):031001. doi: 10.1088/1748-3190/11/3/031001. Bioinspir Biomim. 2016. PMID: 27073001 Review.
-
Softworms: the design and control of non-pneumatic, 3D-printed, deformable robots.Bioinspir Biomim. 2016 Mar 10;11(2):025001. doi: 10.1088/1748-3190/11/2/025001. Bioinspir Biomim. 2016. PMID: 26963596 Review.
Cited by
-
Strong and Anomalous Thermal Expansion Precedes the Thermosalient Effect in Dynamic Molecular Crystals.Sci Rep. 2016 Jul 12;6:29610. doi: 10.1038/srep29610. Sci Rep. 2016. PMID: 27403616 Free PMC article.
-
A review on quantum computing and deep learning algorithms and their applications.Soft comput. 2022 Apr 7:1-20. doi: 10.1007/s00500-022-07037-4. Online ahead of print. Soft comput. 2022. PMID: 35411203 Free PMC article.
-
Machine Learning-Assisted Computational Screening of Metal-Organic Frameworks for Atmospheric Water Harvesting.Nanomaterials (Basel). 2022 Jan 3;12(1):159. doi: 10.3390/nano12010159. Nanomaterials (Basel). 2022. PMID: 35010109 Free PMC article.
-
Insect-Inspired Robots: Bridging Biological and Artificial Systems.Sensors (Basel). 2021 Nov 16;21(22):7609. doi: 10.3390/s21227609. Sensors (Basel). 2021. PMID: 34833685 Free PMC article. Review.
-
Advanced Design of Soft Robots with Artificial Intelligence.Nanomicro Lett. 2024 Jun 13;16(1):214. doi: 10.1007/s40820-024-01423-3. Nanomicro Lett. 2024. PMID: 38869734 Free PMC article. Review.
References
Publication types
MeSH terms
LinkOut - more resources
Full Text Sources
Other Literature Sources