Resilient Machines Through Continuous Self-Modeling
The DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Abstract
Animals sustain the ability to operate after injury by creating qualitatively different compensatory behaviors. Although such robustness would be desirable in engineered systems, most machines fail in the face of unexpected damage. We describe a robot that can recover from such change autonomously, through continuous self-modeling. A four-legged machine uses actuation-sensation relationships to indirectly infer its own structure, and it then uses this self-model to generate forward locomotion. When a leg part is removed, it adapts the self-models, leading to the generation of alternative gaits. This concept may help develop more robust machines and shed light on self-modeling in animals.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Bongard et al. (2006) have created an artificial ''starfish'' that gradually develops an explicit internal self-model.”
From Empirical perspectives from the self-model theory of subjectivity: a brief summary with examples (2007) · cites this paper as Bongard et al. (2006)
In the citing paper
“When part of its leg is removed, it adapts its self-model and generates alternative gaits -it learns to limp.”
From Empirical perspectives from the self-model theory of subjectivity: a brief summary with examples (2007) · cites this paper as Bongard et al. (2006)
In the citing paper
“Their four-legged machine uses actuation-sensation relationships to indirectly infer its own structure and then uses this self-model to generate forward locomotion.”
From Empirical perspectives from the self-model theory of subjectivity: a brief summary with examples (2007) · cites this paper as Bongard et al. (2006)
Citations
Cites
System Identification: Theory for the User
Lennart Ljung, A. (1987) · Cited by 17,690
Thrun, S. (2002) · Communications of the ACM · doi:10.1145/504729.504754 · Cited by 7,994
(1999) · Choice Reviews Online · doi:10.5860/choice.36-5109 · Cited by 2,528
(1987) · Medical Entomology and Zoology · Cited by 2,512
Efficient Bipedal Robots Based on Passive-Dynamic Walkers
Collins, S., Ruina, A., Tedrake, R., & Wisse, M. (2005) · Science · doi:10.1126/science.1107799 · Cited by 1,873
Modelling and Control of Robot Manipulators
Sciavicco, L., & Siciliano, B. (2000) · Advanced Textbooks in Control and Signal Processing · doi:10.1007/978-1-4471-0449-0 · Cited by 1,701
Introduction to Machine Learning
(2019) · Series in Machine Perception and Artificial Intelligence · doi:10.1142/9789811201967_0001 · Cited by 1,639
Evolutionary Robotics: The Biology, Intelligence, and Technology of Self-Organizing Machines
Nolfi, S., & Floreano, D. (2000) · The MIT Press eBooks · doi:10.7551/mitpress/2889.001.0001 · Cited by 1,513
Crick, F., & Koch, C. (2003) · Nature Neuroscience · doi:10.1038/nn0203-119 · Cited by 1,492
RHex: A Simple and Highly Mobile Hexapod Robot
Saranli, U., Buehler, M., & Koditschek, D. E. (2001) · The International Journal of Robotics Research · doi:10.1177/02783640122067570 · Cited by 1,322
Research works printed but not linked: 3
- H. S. Seung, M. Opper, H. Sompolinsky, in Proceedings of the 5th Workshop on Computational Learning Theory (ACM Press, New York, 1992), pp. 287–294.
- J. Bongard, H. Lipson, J. Mach. Learn. Res.6, 1651 (2005).
- R. A. Brooks, in Proceedings of the 1st European Conference on Artificial Life, F. J. Varela, P. Bourgine, Eds. (Springer-Verlag, Berlin, 1992), pp. 3–10.
Cited by
Supersizing the Mind: Embodiment, Action, and Cognitive Extension
Clark, A. (2008) · doi:10.1093/acprof:oso/9780195333213.001.0001 · Cited by 2,201
Learning agile and dynamic motor skills for legged robots
Hwangbo, J., Lee, J., Dosovitskiy, A., Bellicoso, D., Tsounis, V., Koltun, V., & Hutter, M. (2019) · Science Robotics · doi:10.1126/scirobotics.aau5872 · Cited by 1,482
“The first is to improve simulation fidelity either analytically or in a data-driven way; the latter is also known as system identification [27–32].”
BackgroundPrinciples of sensorimotor learning
Wolpert, D. M., Diedrichsen, J., & Flanagan, J. R. (2011) · Nature Reviews Neuroscience · doi:10.1038/nrn3112 · Cited by 1,391
“An example from the robotics field illustrates one way in which structural learning can take plac”
BackgroundRahwan, I., Cebrian, M., Obradovich, N., Bongard, J., Bonnefon, J.-F., Breazeal, C., Crandall, J. W., Christakis, N. A., Couzin, I. D., Jackson, M. O., et al. (2019) · Nature · doi:10.1038/s41586-019-1138-y · Cited by 1,364
Self-citationThe grand challenges of Science Robotics
Yang, G.-Z., Bellingham, J., Dupont, P. E., Fischer, P., Floridi, L., Full, R., Jacobstein, N., Kumar, V., McNutt, M., Merrifield, R., et al. (2018) · Science Robotics · doi:10.1126/scirobotics.aar7650 · Cited by 1,177
Robots that can adapt like animals
Cully, A., Clune, J., Tarapore, D., & Mouret, J.-B. (2015) · Nature · doi:10.1038/nature14422 · Cited by 979
Active interoceptive inference and the emotional brain
Seth, A. K., & Friston, K. J. (2016) · Philosophical Transactions of the Royal Society B: Biological Sciences · doi:10.1098/rstb.2016.0007 · Cited by 945
Automated reverse engineering of nonlinear dynamical systems
Bongard, J., & Lipson, H. (2007) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.0609476104 · Cited by 792
Self-citationSim-to-Real: Learning Agile Locomotion For Quadruped Robots
Tan, J., Zhang, T., Coumans, E., Iscen, A., Bai, Y., Hafner, D., Bohez, S., & Vanhoucke, V. (2018) · Robotics: Science and Systems XIV · doi:10.15607/rss.2018.xiv.010 · Cited by 735
Sim-to-Real: Learning Agile Locomotion For Quadruped Robots
Tan, J., Zhang, T., Coumans, E., Iscen, A., Bai, Y., Hafner, D., Bohez, S., & Vanhoucke, V. (2018) · arXiv · doi:10.48550/arxiv.1804.10332 · Cited by 734
Foundations for a new science of learning
Meltzoff, A. N., Kuhl, P. K., Movellan, J., & Sejnowski, T. J. (2009) · Science · doi:10.1126/science.1175626 · Cited by 723
Model learning for robot control: A survey
Nguyen-Tuong, D., & Peters, J. (2011) · Cognitive Processing · doi:10.1007/s10339-011-0404-1 · Cited by 503
“Although model learning can be performed with unsupervised learning in few cases (Bongard et al. 2006; Weber et al. 2000), supervised learning is the most fre-”
BackgroundA scalable pipeline for designing reconfigurable organisms
Kriegman, S., Blackiston, D., Levin, M., & Bongard, J. (2020) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1910837117 · Cited by 461
Self-citationBeing a Beast Machine: The Somatic Basis of Selfhood
Seth, A. K., & Tsakiris, M. (2018) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2018.08.008 · Cited by 371
“Instrumental inference (equivalently, control-oriented inference) prescribes actions that exploit these models for ongoing control and regulation [15, 50, 51].”
Continuous maintenance and the future – Foundations and technological challenges
Roy, R., Stark, R., Tracht, K., Takata, S., & Mori, M. (2016) · CIRP Annals · doi:10.1016/j.cirp.2016.06.006 · Cited by 309
A review on self-healing polymers for soft robotics
Terryn, S., Langenbach, J., Roels, E., Brancart, J., Bakkali-Hassani, C., Poutrel, Q.-A., Georgopoulou, A., George Thuruthel, T., Safaei, A., Ferrentino, P., et al. (2021) · Materials Today · doi:10.1016/j.mattod.2021.01.009 · Cited by 309
Levin, M. (2019) · Frontiers in Psychology · doi:10.3389/fpsyg.2019.02688 · Cited by 297
“…other developing organs, are not hardwired but are able to ascertain the structure of the body and adjust their functional programs accordingly – a strategy that is already being pursued in robotics, including the use of electrophysiological principles (Bongard et al., 2006; Cheney et al., 2014).”
BackgroundEvolutionary Robotics: What, Why, and Where to
Doncieux, S., Bredeche, N., Mouret, J.-B., & Eiben, A. E. (. (2015) · Frontiers in Robotics and AI · doi:10.3389/frobt.2015.00004 · Cited by 275
“…time. www.frontiersin.org March 2015 | Volume 2 | Article 4 | 9 Online versions of evolutionary robotics have been studied in order to address this class of problem (Eiben et al., 2010), both with single robots (Bongard et al., 2006; Bredeche et al., 2010) and multiple robots (Watson et al., 2002).”
BackgroundMethodInfluentialThe Transferability Approach: Crossing the Reality Gap in Evolutionary Robotics
Koos, S., Mouret, J.-B., & Doncieux, S. (2013) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2012.2185849 · Cited by 272
“It is also argued in [7] that accurate quantitative comparisons between two sensor time series is difficult because small initial disparities can quickly lead to very different signals, which can lead to prefer external measures for physical robots [8].”
BackgroundMethodMaye, A., Hsieh, C.-H., Sugihara, G., & Brembs, B. (2007) · PLoS ONE · doi:10.1371/journal.pone.0000443 · Cited by 271
“Recently, a new class of agents was introduced, which incorporated some of these ideas [75].”
BackgroundBongard, J. C. (2013) · Communications of the ACM · doi:10.1145/2492007.2493883 · Cited by 260
Self-citationQuality and Diversity Optimization: A Unifying Modular Framework
Cully, A., & Demiris, Y. (2018) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2017.2704781 · Cited by 258
Joulain, K., Drevillon, J., Ezzahri, Y., & Ordonez-Miranda, J. (2016) · Physical Review Letters · doi:10.1103/physrevlett.116.200601 · Cited by 249
Soft Robotics: Challenges and Perspectives
Iida, F., & Laschi, C. (2011) · Procedia Computer Science · doi:10.1016/j.procs.2011.12.030 · Cited by 246
Body Schema in Robotics: A Review
Hoffmann, M., Marques, H., Arieta, A., Sumioka, H., Lungarella, M., & Pfeifer, R. (2010) · IEEE Transactions on Autonomous Mental Development · doi:10.1109/tamd.2010.2086454 · Cited by 242
“In [97], only orientation sensors are used, but in [98], more modalities are employed and their relevance is also assessed.”
BackgroundThe cybernetic Bayesian brain : from interoceptive inference to sensorimotor contingencies
Seth, A. K. (2015) · MIND Group · doi:10.25358/openscience-84 · Cited by 239
Knowing one's place: a free-energy approach to pattern regulation
Friston, K., Levin, M., Sengupta, B., & Pezzulo, G. (2015) · Journal of The Royal Society Interface · doi:10.1098/rsif.2014.1383 · Cited by 234
Seth, A. K. (2015) · Figshare · doi:10.15502/9783958570108 · Cited by 211
“…as an alternative framework in which closely coupled feedback loops, leveraging invariants in brainbody-world interactions, obviate the need for detailed internal representations of external Figure 6: An evolutionary-robotics experiment demonstrating continuous self-modelling Bongard et al. (2006).”
BackgroundInfluentialA soft robot that adapts to environments through shape change
Shah, D. S., Powers, J. P., Tilton, L. G., Kriegman, S., Bongard, J., & Kramer-Bottiglio, R. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-00263-1 · Cited by 202
“Although many simulation to reality (“sim2real”) methods have been reported [35, 36, 24, 37, 25, 38, 39, 40, 41, 42, 43], none have documented the transfer from simulation to reality of shape-changing robots.”
BackgroundSelf-citationEmbodied Intelligence: A Synergy of Morphology, Action, Perception and Learning
Liu, H., Guo, D., & Cangelosi, A. (2025) · ACM Computing Surveys · doi:10.1145/3717059 · Cited by 200
“To solve this problem, Reference [18] proposes a continuous morphology modeling method.”
The rise of machine consciousness: Studying consciousness with computational models
Reggia, J. A. (2013) · Neural Networks · doi:10.1016/j.neunet.2013.03.011 · Cited by 199
Levin, M. (2022) · Frontiers in Systems Neuroscience · doi:10.3389/fnsys.2022.768201 · Cited by 195
An architecture for ethical robots inspired by the simulation theory of cognition
Vanderelst, D., & Winfield, A. (2018) · Cognitive Systems Research · doi:10.1016/j.cogsys.2017.04.002 · Cited by 153
A Differentiable Physics Engine for Deep Learning in Robotics
Degrave, J., Hermans, M., Dambre, J., & wyffels, F. (2019) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2019.00006 · Cited by 182
“It would form an interesting approach for swarm robotics, similar to previous results in evolutionary robotics (Sims, 1994; Pfeifer and Bongard, 2006; Cheney et al., 2014), but possibly faster.”
ResultEvolution of Adaptive Behaviour in Robots by Means of Darwinian Selection
Floreano, D., & Keller, L. (2010) · PLoS Biology · doi:10.1371/journal.pbio.1000292 · Cited by 153
“A third consists of coevolving the robot and the key parameters of the simulation model and periodically testing the evolved con-trol system with real robots to improve the estimate of the fitness of the robot and simulator [53].”
MethodMorphological change in machines accelerates the evolution of robust behavior
Bongard, J. (2011) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1015390108 · Cited by 176
“This work suggests that the automated design, manufacture (10), and deployment (8) of adaptive machines should allow for neurological and morphological change at ontogenetic and phylogenetic time scales.”
BackgroundSelf-citationShape Changing Robots: Bioinspiration, Simulation, and Physical Realization
Shah, D., Yang, B., Kriegman, S., Levin, M. G., Bongard, J., & Kramer-Bottiglio, R. K. (2020) · Advanced Materials · doi:10.1002/adma.202002882 · Cited by 172
Self-citationAutoMoDe: A novel approach to the automatic design of control software for robot swarms
Francesca, G., Brambilla, M., Brutschy, A., Trianni, V., & Birattari, M. (2014) · Swarm Intelligence · doi:10.1007/s11721-014-0092-4 · Cited by 171
“…the inclusion of noise in the simulation of sensors and actuators and in the conditions experienced by the robots during the design process; more recently, Bongard et al. (2006) and Koos et al. (2013) alternated simulation with tests on the physical system to correct the simulator nuisances.”
BackgroundPezzulo, G., & Levin, M. (2015) · Integrative Biology · doi:10.1039/c5ib00221d · Cited by 168
Coordinating with the Future: The Anticipatory Nature of Representation
Pezzulo, G. (2008) · Minds and Machines · doi:10.1007/s11023-008-9095-5 · Cited by 167
“Bongard et al. (2006a,b) describes how robots might evolve body schemas by means of interactions and their anticipation.”
BackgroundEvolving embodied intelligence from materials to machines
Howard, D., Eiben, A. E., Kennedy, D. F., Mouret, J.-B., Valencia, P., & Winkler, D. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-018-0009-9 · Cited by 161
A Survey on Policy Search Algorithms for Learning Robot Controllers in a Handful of Trials
Chatzilygeroudis, K., Vassiliades, V., Stulp, F., Calinon, S., & Mouret, J.-B. (2020) · IEEE Transactions on Robotics · doi:10.1109/tro.2019.2958211 · Cited by 160
“Finally, an approach that splits the self-modeling process from the PS is presented in [133].”
MethodChella, A., & Manzotti, R. (2010) · Springer eBooks · doi:10.1007/978-1-4419-1452-1_20 · Cited by 159
Dimaggio, G., Vanheule, S., Lysaker, P. H., Carcione, A., & Nicolò, G. (2009) · Consciousness and Cognition · doi:10.1016/j.concog.2009.06.003 · Cited by 159
Bioelectric networks: the cognitive glue enabling evolutionary scaling from physiology to mind
Levin, M. (2023) · Animal Cognition · doi:10.1007/s10071-023-01780-3 · Cited by 102
“…proto-cognitive capabilities that await discovery, are already generating new capabilities and driving novel research programs (Aubin et al. 2022; Bongard et al. 2006; Davies and Levin 2023; Kriegman et al. 2021b; Levin et al. 2017; Merrild and Rasmussen 2018; Pezzulo 2020; Pezzulo et al. 2021;…”
BackgroundBongard, J., & Levin, M. (2021) · Frontiers in Ecology and Evolution · doi:10.3389/fevo.2021.650726 · Cited by 114
“This definition is related to embodiment and situatedness, two previous pillars supporting the definition of robot (Pfeifer and Bongard, 2006).”
BackgroundSelf-citationTowards an Ethical Robot: Internal Models, Consequences and Ethical Action Selection
Winfield, A. F. T., Blum, C., & Liu, W. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10401-0_8 · Cited by 114
“[2] describe a 4-legged starfish like robot that makes use of explicit internal simulation, both to enable the robot to learn it’s own body morphology and control, and notably allow the robot to recover from physical damage by learning the new morphology following the damage.”
BackgroundExplanatory correlates of consciousness: theoretical and computational challenges.
Seth, A. (2009) · Cognitive Computation · doi:10.1007/s12559-009-9007-x · Cited by 146
“[7], who use artificial evolution techniques (genetic algorithms) to enable a four-legged ‘starfish’ robot to generate autonomously a representation of its own body (Fig.”
BackgroundMethodLearning to Move in Modular Robots using Central Pattern Generators and Online Optimization
Badri–Spröwitz, A., Möckel, R., Maye, J., & Ijspeert, A. J. (2008) · The International Journal of Robotics Research · doi:10.1177/0278364907088401 · Cited by 144
“The most common and obvious approach to control locomotion of a chain-type robot in a specific configuration is a centralized gait control table (Yim 1994 Bongard et al. 2006).”
BackgroundAdaptive Control Strategies for Interlimb Coordination in Legged Robots: A Review
Aoi, S., Manoonpong, P., Ambe, Y., Matsuno, F., & Wörgötter, F. (2017) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2017.00039 · Cited by 136
“, 2013a,b) and classical machine learning control (Bongard et al., 2006; Cully et al., 2015) instead of using CPG models, the CPG concept and modeling have had a large influence on the studies of legged robots.”
BackgroundMethodReset-free Trial-and-Error Learning for Robot Damage Recovery
Chatzilygeroudis, K. I., Vassiliades, V., & Mouret, J.-B. (2017) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2017.11.010 · Cited by 135
“Classic approaches to fault tolerance rely on updating the model of the robot, either directly with selfdiagnosis [37], or indirectly with machine learning [38, 5]; the model is then used for planning and/or control.”
MethodResilient Robots: Concept, Review, and Future Directions
Zhang, T., Zhang, W., & Gupta, M. M. (2017) · Robotics · doi:10.3390/robotics6040022 · Cited by 134
“[22] was the first robot to be named resilient robot.”
BackgroundMethodInfluentialEmbodied Evolution in Collective Robotics: A Review
Bredeche, N., Haasdijk, E., & Prieto, A. (2018) · Frontiers in Robotics and AI · doi:10.3389/frobt.2018.00012 · Cited by 103
“More recently, Bongard et al. (2006) and Cully et al. (2015) addressed resilience by introducing fast online re-optimization to recover from hardware damage.”
InfluentialBadri–Spröwitz, A., Möckel, R., Vespignani, M., Bonardi, S., & Ijspeert, A. J. (2013) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2013.08.011 · Cited by 134
Adaptive Morphology: A Design Principle for Multimodal and Multifunctional Robots
Mintchev, S., & Floreano, D. (2016) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2016.2580593 · Cited by 131
“[100] developed algorithms to infer robot morphology and subsequently generate appropriate walking gaits.”
Computational Models for Neuromuscular Function
Valero‐Cuevas, F. J., Hoffmann, H., Kurse, M. U., Kutch, J. J., & Theodorou, E. A. (2009) · IEEE Reviews in Biomedical Engineering · doi:10.1109/rbme.2009.2034981 · Cited by 130
“, the number of model elements and their connectivity, can be found in [87] and [125]–[127].”
BackgroundAutonomous skill discovery with quality-diversity and unsupervised descriptors
Cully, A. (2019) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/3321707.3321804 · Cited by 130
“To address this issue, a new approach has been proposed, which involves using learning algorithms that enable robots to learn how to overcome new situations, like mechanical damages [1, 4].”
Robot Learning From Randomized Simulations: A Review
Muratore, F., Ramos, F., Turk, G., Yu, W., Gienger, M., & Peters, J. (2022) · Frontiers in Robotics and AI · doi:10.3389/frobt.2022.799893 · Cited by 128
“Bongard et al. (2006) bridged the sim-to-real gap through iterating model generation and selection depending on the short-term state-action history.”
BackgroundBeyond black-box optimization: a review of selective pressures for evolutionary robotics
Doncieux, S., & Mouret, J.-B. (2014) · Evolutionary Intelligence · doi:10.1007/s12065-014-0110-x · Cited by 125
“Bongard et al. [26] propose an extension of the co-evolution approach in which actions are explicitly sought to challenge current candidate models.”
BackgroundMethodEmpirical perspectives from the self-model theory of subjectivity: a brief summary with examples
Metzinger, T. (2007) · Progress in Brain Research · doi:10.1016/s0079-6123(07)68018-2 · Cited by 123
“Bongard et al. (2006) have created an artificial ‘‘starfish’’ that gradually develops an explicit internal self-model.”
BackgroundOpen Issues in Evolutionary Robotics
Silva, F., Duarte, M., Correia, L., Oliveira, S. M., & Christensen, A. L. (2016) · Evolutionary Computation · doi:10.1162/evco_a_00172 · Cited by 106
“Bongard et al. (2006), Bongard (2009), and O’Dowd et al. (2011) have introduced new perspectives on how to cross the reality gap and speed up evolution of controllers on real robots.”
BackgroundMethodInfluentialRoombots: Reconfigurable Robots for Adaptive Furniture
Badri–Spröwitz, A., Pouya, S., Bonardi, S., van den Kieboom, J., Möckel, R., Billard, A., Dillenbourg, P., & Ijspeert, A. J. (2010) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2010.937320 · Cited by 122
Self-healing and self-repairing technologies
Frei, R., McWilliam, R. P., Derrick, B., Purvis, A., Tiwari, A., & Serugendo, G. D. M. (2013) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-013-5070-2 · Cited by 122
Fields, C., & Levin, M. (2022) · Entropy · doi:10.3390/e24060819 · Cited by 121
Products as Agents: Metaphors for Designing the Products of the IoT Age
Cila, N., Smit, I., Giaccardi, E., & Kröse, B. (2017) · Proceedings of the 2017 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3025453.3025797 · Cited by 92
“Bongard, Zykov and Lipson have been developing the Starfish, which is the first robot to develop some sort of “self-awareness” [11].”
BackgroundRieffel, J. A., Valero‐Cuevas, F. J., & Lipson, H. (2009) · Journal of The Royal Society Interface · doi:10.1098/rsif.2009.0240 · Cited by 118
“The second possibility lies in continuous self-modelling approaches which seek to coevolve robotic gaits alongside an emerging self-model (Bongard et al. 2006).”
BackgroundSelf-citationValuing One’s Self: Medial Prefrontal Involvement in Epistemic and Emotive Investments in Self-views
D’Argembeau, A., Jedidi, H., Balteau, E., Bahri, M., Phillips, C., & Salmon, E. (2012) · Cerebral Cortex · doi:10.1093/cercor/bhr144 · Cited by 103
“Certain other species—and even some robots (Bongard et al. 2006)—possess rudimentary self-models that allow them to distinguish themselves from their environment, but there is no certainty that they think about themselves in abstract and symbolic ways as humans routinely do (Sedikides and Skowronski 1997; Leary and Bu…”
How morphological development can guide evolution
Kriegman, S., Cheney, N., & Bongard, J. (2018) · Scientific Reports · doi:10.1038/s41598-018-31868-7 · Cited by 114
Self-citationSafe mutations for deep and recurrent neural networks through output gradients
Lehman, J., Chen, J., Clune, J., & Stanley, K. O. (2018) · Proceedings of the Genetic and Evolutionary Computation Conference · doi:10.1145/3205455.3205473 · Cited by 78
“It has long been popular when gradient information with respect to the task is unavailable or difficult to obtain, e.g. in artificial life (Bedau et al., 2000; Langton, 1989) and evolutionary robotics (Nolfi and Floreano, 2000; Bongard et al., 2006; Cully et al., 2015).”
BackgroundOn Proactive, Transparent, and Verifiable Ethical Reasoning for Robots
Bremner, P., Dennis, L. A., Fisher, M., & Winfield, A. F. T. (2019) · Proceedings of the IEEE · doi:10.1109/jproc.2019.2898267 · Cited by 112
“[61] describe a four-legged starfish-like robot that self simulates in order to learn its own morphology and how to control it, i.”
BackgroundModeling Planarian Regeneration: A Primer for Reverse-Engineering the Worm
Lobo, D., Beane, W. S., & Levin, M. G. (2012) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1002481 · Cited by 113
“However, none of the proposed models in the literature are able to explain more than one or two facets of planarian regeneration. There is a tremendous opportunity to integrate existing knowledge of pathways with the anatomical and physiological data to produce novel models of the worm as a system that senses damage”
BackgroundNolfi, S. (2022) · The MIT Press eBooks · doi:10.7551/mitpress/13780.003.0008 · Cited by 111
Corucci, F., Cheney, N., Giorgio-Serchi, F., Bongard, J., & Laschi, C. (2018) · Soft Robotics · doi:10.1089/soro.2017.0055 · Cited by 105
“More-over, increasingly sophisticated techniques that preserve the effectiveness of simulated design once deployed in the real world are being developed, 11,12 which will allow a more direct transposition from simulation to reality.”
Self-citationExperiments in Artificial Theory of Mind: From Safety to Story-Telling
Winfield, A. F. T. (2018) · Frontiers in Robotics and AI · doi:10.3389/frobt.2018.00075 · Cited by 80
“Bongardet al. (2006) describe a 4-legged starfish like robot that makes use of explicit internal simulation, both to enable the robot to learn it’s own body morphology and control, and notably allow the robot to recover from physical damage by learning the new morphology following the damage.”
BackgroundTask-agnostic self-modeling machines
Kwiatkowski, R., & Lipson, H. (2019) · Science Robotics · doi:10.1126/scirobotics.aau9354 · Cited by 104
“We previously used evolutionary algorithms to find the morphology most consistent with the robot’s recorded action-sensation pairs (6), but both approaches make many assumptions.”
MethodSelf-citationLearning locomotion over rough terrain using terrain templates
Kalakrishnan, M., Buchli, J., Pástor, P., & Schaal, S. (2009) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2009.5354701 · Cited by 103
Mergeable nervous systems for robots
Mathews, N., Christensen, A. L., O’Grady, R., Mondada, F., & Dorigo, M. (2017) · Nature Communications · doi:10.1038/s41467-017-00109-2 · Cited by 84
“When an MNS robot changes shape or size, there is thus no need for time-consuming processes such as self-discovery 14 , trial-and-error 15 , or hormone-based messaging 16 .”
Biomimetic and bio-inspired robotics in electric fish research
Neveln, I. D., Bai, Y., Snyder, J. B., Solberg, J. R., Curet, O., Lynch, K., & MacIver, M. A. (2013) · Journal of Experimental Biology · doi:10.1242/jeb.082743 · Cited by 101
Fully body visual self-modeling of robot morphologies
Chen, B., Kwiatkowski, R., Vondrick, C., & Lipson, H. (2022) · Science Robotics · doi:10.1126/scirobotics.abn1944 · Cited by 101
Self-citationA linear-encoding model explains the variability of the target morphology in regeneration
Lobo, D., Solano, M., Bubenik, G. A., & Levin, M. (2014) · Journal of The Royal Society Interface · doi:10.1098/rsif.2013.0918 · Cited by 94
“Finally, this new perspective on regeneration can also benefit the engineering and computational fields, inspiring novel mechanisms for resilient self-assembly robotics [161–163] and novel heuristics for evolutionary computation algorithms based on hybrid nonlinear–linear encodings [119].”
BackgroundScalable sim-to-real transfer of soft robot designs
Kriegman, S., Nasab, A. M., Shah, D., Steele, H., Branin, G., Levin, M. G., Bongard, J., & Kramer-Bottiglio, R. K. (2020) · IEEE International Conference on Soft Robotics (RoboSoft) · doi:10.1109/robosoft48309.2020.9116004 · Cited by 100
“[2] 2006 34 2 Hiller and Lipson [8] 2011 1 5 Koos et al.”
BackgroundMethodSelf-citationLevin, M., Pietak, A. M., & Bischof, J. (2019) · Seminars in Cell & Developmental Biology · doi:10.1016/j.semcdb.2018.04.003 · Cited by 82
“Beyond biology, they also serve as a design challenge for fields such as morphogenetic engineering [31, 32], unconventional computation [33–35], and soft robotics [36, 37], which look to the biological world for clues as to designing robust, parallel, fault-tolerant systems.”
BackgroundRoombots-mechanical design of self-reconfiguring modular robots for adaptive furniture
Badri–Spröwitz, A., Billard, A., Dillenbourg, P., & Ijspeert, A. J. (2009) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2009.5152613 · Cited by 97
“This choice of dof was used firstly in modular robots by [12], [13].”
MethodAssessing Transferability From Simulation to Reality for Reinforcement Learning
Muratore, F., Gienger, M., & Peters, J. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2019.2952353 · Cited by 65
A survey on underactuated robotic systems: Bio-inspiration, trajectory planning and control
Liu, P., Huda, M. N., Sun, L. J., & Yu, H. (2020) · Mechatronics · doi:10.1016/j.mechatronics.2020.102443 · Cited by 96
Clawson, W. P., & Levin, M. G. (2022) · Biological Journal of the Linnean Society · doi:10.1093/biolinnean/blac073 · Cited by 96
Evolving a Behavioral Repertoire for a Walking Robot
Cully, A., & Mouret, J.-B. (2015) · Evolutionary Computation · doi:10.1162/evco_a_00143 · Cited by 94
“As argued in many papers, evolutionary computation could bring many benefits to legged robotics, from making it easier to design walking controllers (e.g., Hornby et al., 2005) to autonomous damage recovery (e.g., Bongard et al., 2006; Koos et al., 2013a).”
BackgroundRobotic-assisted surgery in ophthalmology
de Smet, M. D., Naus, G. J. L., Faridpooya, K., & Mura, M. (2018) · Current Opinion in Ophthalmology · doi:10.1097/icu.0000000000000476 · Cited by 83
Levin, M. (2021) · Biochemical and Biophysical Research Communications · doi:10.1016/j.bbrc.2020.10.077 · Cited by 92
Fast damage recovery in robotics with the T-resilience algorithm
Koos, S., Cully, A., & Mouret, J.-B. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913499192 · Cited by 92
“In the “starfish” experiment (Bongard et al., 2006), the following steps are repeated: 1.1. action selection ( exploration ): – each of the 36 possible actions is tested on each of the 16 candidate models to observe the orientation of robot’s body predicted by the model; – the action for which…”
InfluentialLow-cost sensing with ring oscillator arrays for healthier reconfigurable systems
Zick, K. M., & Hayes, J. P. (2012) · ACM Transactions on Reconfigurable Technology and Systems · doi:10.1145/2133352.2133353 · Cited by 88
On-line sensing for healthier FPGA systems
Zick, K. M., & Hayes, J. P. (2010) · ACM/SIGDA International Symposium on Field-Programmable Gate Arrays (FPGA) · doi:10.1145/1723112.1723153 · Cited by 88
“Finally, the general problem of how a system can effectively sense its own physical parameters is being studied in other contexts such as autonomic data centers [10] and selfmodeling robotic systems [3].”
BackgroundArtificial intelligence: neither Utopian nor apocalyptic impacts soon
Naudé, W. A. (2020) · Economics of Innovation and New Technology · doi:10.1080/10438599.2020.1839173 · Cited by 87
Behavioral repertoire learning in robotics
Cully, A., & Mouret, J.-B. (2013) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/2463372.2463399 · Cited by 85
“In particular, learning low-level sensorimotor behaviors is essential to allow robots to pursue their mission in all situations, for instance after mechanical damage [3].”
BackgroundThe Evolution of Representation in Simple Cognitive Networks
Marstaller, L., Hintze, A., & Adami, C. (2013) · Neural Computation · doi:10.1162/neco_a_00475 · Cited by 70
“Representations can be updated during the lifetime or over the course of evolution and thus are able to handle even new sensory input (Bongard et al., 2006).”
BackgroundAn algorithmic information theory of consciousness
Ruffini, G. (2017) · Neuroscience of Consciousness · doi:10.1093/nc/nix019 · Cited by 63
“As an example, we refer to Bongard et al. (2006), where a four-legged robot uses actuation–sensation relationships to model its own physical structure, which it then uses to generate locomotion, or to the recent Deep Reinforcement Learning re-sults, where deep learning and reinforcement learning…”
Manoonpong, P., Pasemann, F., & Wörgötter, F. (2007) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2007.07.004 · Cited by 78
“[15] presented an active process that allows a robot to generate successful motor patterns for locomotion, before and after damage, through autonomous and continuous self-modeling (internal model).”
BackgroundEctopic eyes outside the head in Xenopus tadpoles provide sensory data for light-mediated learning
Blackiston, D. J., & Levin, M. (2013) · Journal of Experimental Biology · doi:10.1242/jeb.074963 · Cited by 62
“Indeed, a promising recent direction in this field is the development of cybernetic devices that are not pre-programmed with a description of their own structure but must discover their morphology dynamically (Bongard et al., 2006).”
BackgroundAdvanced Design of Soft Robots with Artificial Intelligence
Cao, Y., Xu, B., Li, B., & Fu, H. C. (2024) · Nano-Micro Letters · doi:10.1007/s40820-024-01423-3 · Cited by 77
Taylor, S. J. E., Khan, A., Morse, K. L., Tolk, A., Yılmaz, L., Zander, J., & Mosterman, P. J. (2015) · SIMULATION · doi:10.1177/0037549715590594 · Cited by 75
“Bongard et al.(65) compare their robots to animals that can sustain the ability to operate after injury by creating qualitatively different compensatory behaviors.”
Background
Metadata
- Authors
- Bongard, J., Zykov, V., & Lipson, H.
- Affiliations
- Cornell University (US)
- Corresponding author
- Bongard, Josh
- Venue
- Science
- Published
- 2006-11-17
- Volume
- 314
- Issue
- 5802
- Pages
- 1118-1121
- ISSN
- 0036-8075 (ISSN-L)
- 1095-9203
- OpenAlex
- W2001685400
- Cited by
- 709
- References
- 31
- Citations by year
- 2026: 24 · 2025: 22 · 2024: 31 · 2023: 22 · 2022: 32 · 2021: 36 · 2020: 39 · 2019: 39 · 2018: 37 · 2017: 53 · 2016: 43 · 2015: 40 · 2014: 33 · 2013: 48 · 2012: 33
- FWCI
- 26.07
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- Science (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Robotic Locomotion and Control
- Life Sciences › Neuroscience › Cognitive Neuroscience › Embodied and Extended Cognition
- Physical Sciences › Engineering › Biomedical Engineering › Prosthetics and Rehabilitation Robotics
- Keywords
- self-modeling, four-legged robot, legged locomotion, gait adaptation, structural inference, autonomous recovery, robustness
- MeSH terms
- Algorithms, Animals, Computer Simulation, Robotics
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.