In this section
@article{Cully:2015:10.1038/nature14422,
author = {Cully, A and Clune, J and Tarapore, D and Mouret, J-B},
doi = {10.1038/nature14422},
journal = {Nature},
pages = {503--507},
title = {Robots that can adapt like animals},
url = {http://dx.doi.org/10.1038/nature14422},
volume = {521},
year = {2015}
}
TY - JOUR
AB - As robots leave the controlled environments of factories to autonomouslyfunction in more complex, natural environments, they will have to respond tothe inevitable fact that they will become damaged. However, while animals canquickly adapt to a wide variety of injuries, current robots cannot "thinkoutside the box" to find a compensatory behavior when damaged: they are limitedto their pre-specified self-sensing abilities, can diagnose only anticipatedfailure modes, and require a pre-programmed contingency plan for every type ofpotential damage, an impracticality for complex robots. Here we introduce anintelligent trial and error algorithm that allows robots to adapt to damage inless than two minutes, without requiring self-diagnosis or pre-specifiedcontingency plans. Before deployment, a robot exploits a novel algorithm tocreate a detailed map of the space of high-performing behaviors: This maprepresents the robot's intuitions about what behaviors it can perform and theirvalue. If the robot is damaged, it uses these intuitions to guide atrial-and-error learning algorithm that conducts intelligent experiments torapidly discover a compensatory behavior that works in spite of the damage.Experiments reveal successful adaptations for a legged robot injured in fivedifferent ways, including damaged, broken, and missing legs, and for a roboticarm with joints broken in 14 different ways. This new technique will enablemore robust, effective, autonomous robots, and suggests principles that animalsmay use to adapt to injury.
AU - Cully,A
AU - Clune,J
AU - Tarapore,D
AU - Mouret,J-B
DO - 10.1038/nature14422
EP - 507
PY - 2015///
SN - 0028-0836
SP - 503
TI - Robots that can adapt like animals
T2 - Nature
UR - http://dx.doi.org/10.1038/nature14422
UR - http://arxiv.org/abs/1407.3501v4
VL - 521
ER -
Artificial Intelligence Network
South Kensington Campus
Imperial College London
SW7 2AZ
To reach the elected speaker of the network, Dr Rossella Arcucci, please contact:
To reach the network manager, Diana O'Malley - including to join the network - please contact: