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
Items 301–400 of 861
Morphology Independent Learning in Modular Robots
Christensen, D. J., Bordignon, M., Schultz, U. P., Shaikh, D., & Støy, K. (2009) · Springer eBooks · doi:10.1007/978-3-642-00644-9_34 · Cited by 16
“demonstrated learning of locomotion and adaptation to changes in the configuration of a modular robot [1].”
BackgroundAnticipation and Future-Oriented Capabilities in Natural and Artificial Cognition
Pezzulo, G. (2007) · Springer eBooks · doi:10.1007/978-3-540-77296-5_24 · Cited by 16
“Piaget [57] discusses how distinguishing self-produced motion from sensory stimuli which are caused by interaction with objects in the environment leads to develop a body schema; some of these ideas have been also used in robotics [ 7 ].”
MethodSelf-modeling in humanoid soccer robots
Zagal, J. C., Delpiano, J. F., & Ruíz-del-Solar, J. (2009) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2009.03.010 · Cited by 16
“Steps in this direction are already present in the Estimation Exploration algorithm [14].”
BackgroundMethodTowards a "theory of mind" in simulated robots
Kim, K.-J., & Lipson, H. (2009) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/1570256.1570278 · Cited by 16
“To accelerate the learning, we used an active-learning processes where the observer robot actively collects training trajectories based on the disagreement between multiple candidate models, as per the Estimation-Exploration Algorithm (EEA) often used for reverse engineering problems [8][9].”
MethodSelf-citationSynthetic Biology: opportunities for Chilean bioindustry and education
Federici, F., Rudge, T. J., Pollak, B., Haseloff, J. P., & Gutiérrez, R. A. (2013) · Biological Research · doi:10.4067/s0716-97602013000400010 · Cited by 16
“…abstractions (smolke and silver, 2011). the use of forward and reverse engineering approaches in combination with machine learning tools (Bongard et al., 2006; Bongard and Lipson, 2007; Schmidt et al., 2009; Schmidt et al., 2011) could lead to new ways of modeling and understanding…”
Gaining Insight into Quality Diversity
Auerbach, J. E., Iacca, G., & Floreano, D. (2016) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/2908961.2931675 · Cited by 16
“If this is the case, then it seems likely that ability of evolution to produce a diversity of solutions (e.g. self models [2], features [1, 10], motor actions [3]) may be what justifies their existence.”
BackgroundInternal state predictability as an evolutionary precursor of self-awareness and agency
Kwon, J., & Choe, Y. (2008) · IEEE International Conference on Development and Learning (ICDL) · doi:10.1109/devlrn.2008.4640814 · Cited by 16
Towards a resilient networked service system
Wang, J. (2013) · University Library - University of Saskatchewan (University of Saskatchewan) · Cited by 16
Learning Soft Millirobot Multimodal Locomotion with Sim‐to‐Real Transfer
Demir, S. Ö., Tiryaki, M. E., Karacakol, A. C., & Sitti, M. (2024) · Advanced Science · doi:10.1002/advs.202308881 · Cited by 15
Distributed systems – from natural to engineered: three phases of inspiration by nature
Frei, R., & Barata, J. (2010) · International Journal of Bio-Inspired Computation · doi:10.1504/ijbic.2010.033094 · Cited by 15
“Bongard et al. (2006) present a robot which creates a model of itself.”
BackgroundA Fully-distributed Shape-aware Neural Controller for Modular Robots
Nadizar, G., Medvet, E., Walker, K., & Risi, S. (2023) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/3583131.3590419 · Cited by 15
“[4] explored enabling a robot to create a model of itself, but relied on actuating the robot to determine its morphology; depending on the type of damage or robot, self-modeling through actuation-sensation might not always be feasible.”
BackgroundMethodApproaches to Probabilistic Model Learning for Mobile Manipulation Robots
Sturm, J. (2013) · Springer tracts in advanced robotics · doi:10.1007/978-3-642-37160-8 · Cited by 15
Regenerative Abilities in Modular Robots Using Virtual Embryogenesis
Thenius, R., Dauschan, M., Schmickl, T., & Crailsheim, K. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-23857-4_24 · Cited by 15
Buschmann, T., & Trimmer, B. A. (2017) · Wiley eBooks · doi:10.1002/9781118873397.ch14 · Cited by 15
A testbed that evolves hexapod controllers in hardware
Heijnen, H., Howard, D., & Kottege, N. (2017) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra.2017.7989128 · Cited by 15
“Recent evolutionary efforts have focused on using a simulator, together with a limited number of hardware evaluations in a co-evolutionary context [13], [14], however they have a focus on system identification and controller recovery following a partial hardware failure, rather than generating mission-specific optimal…”
BackgroundGeneralizing GANs: A Turing Perspective
Groß, R., Gu, Y., Li, W., & Gauci, M. (2017) · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · Cited by 15
Evolutionary Robotics Applied to Hexapod Locomotion: a Comparative Study of Simulation Techniques
Pretorius, C. J., du Plessis, M. C., & Gonsalves, J. W. (2019) · Journal of Intelligent & Robotic Systems · doi:10.1007/s10846-019-00989-0 · Cited by 15
Kano, T., Kanauchi, D., Ono, T., Aonuma, H., & Ishiguro, A. (2019) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2019.00104 · Cited by 15
“Previous studies tackled this problem by using learning techniques (Bongard et al., 2006; Mahdavi and Bentley, 2006; Mostafa et al., 2010; Koos et al., 2013; Christensen et al., 2014; Ren et al., 2014; Rubio et al., 2018, 2019; Yen et al., 2018) and trial-and-error methods (Cully et al.”
MethodModular Robotic Limbs for Astronaut Activities Assistance
Zhao, S., Zhao, J., Sui, D., Wang, T., Zheng, T., Zhao, C., & Zhu, Y. (2021) · Sensors · doi:10.3390/s21186305 · Cited by 15
The enactment of language: Decades of interactions between linguistic and motor processes
Anderson, S. E., & Spivey, M. J. (2009) · Language and Cognition · doi:10.1515/langcog.2009.005 · Cited by 15
Accelerating Self-Modeling in Cooperative Robot Teams
Bongard, J. (2008) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2008.927236 · Cited by 15
Self-citationOnline Gait Learning for Modular Robots with Arbitrary Shapes and Sizes
d’Angelo, M., Weel, B., & Eiben, A. E. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-45008-2_4 · Cited by 14
Filling the reality gap: Using obstacles to promote robust gaits in evolutionary robotics
Glette, K., Johnsen, A. L., & Samuelsen, E. (2014) · doi:10.1109/ices.2014.7008738 · Cited by 14
“On the other hand, the estimation-exploration approach automatically builds a complete simulation model through exploratory actions on the real robot [13].”
BackgroundArora, A. S., & Arora, A. (2019) · International Journal of Intelligent Information Technologies · doi:10.4018/ijiit.2020010101 · Cited by 14
Perceptual Presence in the Kuhnian-Popperian Bayesian Brain
Wiese, W. (2015) · doi:10.15502/9783958570207 · Cited by 14
Footstep planning for humanoid robots
Gorbenko, A., & Popov, V. (2012) · Electronic scientific archive of UrFU (Ural Federal University) · Cited by 13
Optimization of humanoid walking controller: Crossing the reality gap
de Oliveira, M. A. R., Doncieux, S., Mouret, J.-B., & Santos, C. P. (2013) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids.2013.7029963 · Cited by 13
“Several authors proposed to automatically optimize it, for instance by learning a surrogate model of the objective function [10], or to automatically improve an existing simulator [4], [30]”
BackgroundReference Architecture for Self-aware and Self-expressive Computing Systems
Chandra, A., Lewis, P. R., Glette, K., & Stilkerich, S. C. (2016) · Natural computing series · doi:10.1007/978-3-319-39675-0_4 · Cited by 13
The Self-Model Theory of Subjectivity: A Brief Summary with Examples
Metzinger, T. K. (2010) · Humana.mente · Cited by 13
Nall, M. (2020) · Journal of International Crisis and Risk Communication Research · Cited by 13
Machine Behaviour (Originally Published 2019 by Springer Nature)
Rahwan, I., Cebrián, M., Obradovich, N., Bongard, J., Bonnefon, J., Breazeal, C., Crandall, J. W., Christakis, N. A., Couzin, I. D., Jackson, M. O., et al. (2022) · Wiley eBooks · doi:10.1002/9781119815075.ch10 · Cited by 13
Self-citationDesign of a general resilient robotic system based on axiomatic design theory
Zhang, T., Zhang, D., Gupta, M. M., & Zhang, W. (2015) · IEEE International Conference on Advanced Intelligent Mechatronics (AIM) · doi:10.1109/aim.2015.7222511 · Cited by 13
Simultaneous versus incremental learning of multiple skills by modular robots
Rossi, C., & Eiben, A. E. (2014) · Evolutionary Intelligence · doi:10.1007/s12065-014-0109-3 · Cited by 13
“An early approach is based on gait control tables, for instance, [4, 30].”
MethodSelf-Optimization in Continuous-Time Recurrent Neural Networks
Zarco, M., & Froese, T. (2018) · Frontiers in Robotics and AI · doi:10.3389/frobt.2018.00096 · Cited by 13
“One popular approach is self-modeling, for example a multi-legged robot that adapts its controller to its physical body by evaluating its sensory feedback against an internal simulation of its possible body morphology and how that body would interact with its environment (Bongard et al., 2006).”
BackgroundInformative sampling for large unbalanced data sets
Lu, Z., Rughani, A. I., Tranmer, B. I., & Bongard, J. (2008) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/1388969.1389020 · Cited by 13
“In previous applications [4][2][3], virtual data points are created as candidate tests.”
BackgroundSelf-citationKume, A., Matsumoto, E., Takahashi, K., Ko, W., & Tan, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1710.06117 · Cited by 13
“[6] dealt with damage recovery by continuously comparing an updated simulation of the robot with a predetermined undamaged self-model in order to track changes and damages to the body.”
MethodDynamics and Domain Randomized Gait Modulation with Bezier Curves for Sim-to-Real Legged LocomotionPreprint
Rahme, M., Abraham, I., Elwin, M. L., & Murphey, T. D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2010.12070 · Cited by 13
Schillaci, G. (2014) · edoc Publication server (Humboldt University of Berlin) · doi:10.18452/16920 · Cited by 13
Co-evolution framework of swarm self-assembly robots
Li, H., Wei, H., Xiao, J.-Y., & Wang, T. (2014) · Neurocomputing · doi:10.1016/j.neucom.2012.10.047 · Cited by 12
“In addition, there has been some research on control theories relating to self-adaptive frameworks for modular robots in dynamic environments [20,21] and on how to design a controller that adapts to different topologies through continuous self-modeling [22].”
BackgroundSimulation-governed design and tuning of greenhouses for successful bee pollination
Dorin, A., Dyer, A. G., Taylor, T., & Bukovac, Z. (2018) · Conference on Artificial Life (ALIFE) · doi:10.1162/isal_a_00038 · Cited by 12
“We propose, however, to adopt a means of dynamic control similar to that of Bongard et al. (2006) who created robots that incorporate real-world performance feedback into their control systems.”
MethodInformation Optimization and Transferable State Abstractions in Deep Reinforcement Learning
Gomez, D., Quijano, N., & Giraldo, L. F. (2022) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2022.3200726 · Cited by 12
“Otherwise, it would be too costly to learn from scratch the appropriate solution for each problem encountered [3], [4].”
BackgroundDistributed Online Learning of Central Pattern Generators in Modular Robots
Christensen, D. J., Badri–Spröwitz, A., & Ijspeert, A. J. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-15193-4_38 · Cited by 12
“demonstrated learning of locomotion and adaptation to changes in the configuration of a modular robot [1].”
BackgroundEvolving locomotion for a 12-DOF quadruped robot in simulated environments
Klaus, G., Glette, K., & Hovin, M. E. (2013) · Biosystems · doi:10.1016/j.biosystems.2013.03.008 · Cited by 12
Dynamical blueprints: exploiting levels of system-environment interaction
Estevez, N. S., & Lipson, H. (2007) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/1276958.1277009 · Cited by 12
“Bongard), the environment affects the development process, but the development process does not necessarily affect the environment (or affects it on a timescale that is relatively slow) [3].”
BackgroundSelf-citationActive Learning with Adaptive Heterogeneous Ensembles
Lu, Z., Wu, X., & Bongard, J. (2009) · Proceedings · doi:10.1109/icdm.2009.63 · Cited by 12
“In [18], bagging [13] and boosting [14] were combined with QBC, but both ensemble methods require a fair amount of data to start the learning process, which is not desirable considering the cost of labeling data points.”
MethodSelf-citationTowards Multi-Morphology Controllers with Diversity and Knowledge Distillation
Mertan, A., & Cheney, N. (2024) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/3638529.3654013 · Cited by 11
“As opposed to methods like [2, 8, 19] where the system spends time to figure out how to recover from damage, we would be measuring instant (i.e. zero-shot) damage recovery through the robustness of the controller.”
MethodA starfish inspired robot with multi-directional tube feet locomotion
Poungrat, A., & Maneewarn, T. (2017) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2017.8324501 · Cited by 11
“[8] developed a rigid robot that shaped like a starfish to test the learning algorithm based on self modeling such that it can create locomotion gait by itself.”
BackgroundDisgust as a primary emotional system and its clinical relevance
Tolchinsky, A., Ellis, G., Levin, M. G., Kaňková, Š., & Burgdorf, J. S. (2024) · Frontiers in Psychology · doi:10.3389/fpsyg.2024.1454774 · Cited by 11
“The borders of the organism, the available sensors, and directly controllable effectors, are not pre-given but must be discovered dynamically (Bongard et al., 2006).”
BackgroundGeneration of Tactile Maps for Artificial Skin
McGregor, S., Polani, D., & Dautenhahn, K. (2011) · PLoS ONE · doi:10.1371/journal.pone.0026561 · Cited by 11
“…paradigm (introduced in [6]), dimensionality reduction and estimation [7], the information structure approach [8] and model-building work such as [9]; the possibility of implicit (as opposed to explicit) sensorimotor contingency learning has been explored in work such as [10], which uses coupled…”
BackgroundResultExploring new horizons in evolutionary design of robots
Doncieux, S., Bredèche, N., & Mouret, J.-B. (2009) · HAL · Cited by 11
Ophiuroid robot that self-organizes periodic and non-periodic arm movements
Kano, T., Suzuki, S., Watanabe, W., & Ishiguro, A. (2012) · Bioinspiration & Biomimetics · doi:10.1088/1748-3182/7/3/034001 · Cited by 11
“In particular, the latter problem needs to be thoroughly discussed because how to endow robots with ‘resiliency’ is one of important topics in recent robotic studies [25].”
BackgroundOnline Extreme Evolutionary Learning Machines
Auerbach, J. E., Fernando, C., & Floreano, D. (2014) · Conference on Artificial Life (ALIFE) · doi:10.7551/978-0-262-32621-6-ch076 · Cited by 11
“This should allow for a robot to easily adapt to damage (Bongard et al., 2006) or to changes in mor-”
Evolving synthetic pain into an adaptive self-awareness framework for robots
Anshar, M., & Williams, M. (2016) · Biologically Inspired Cognitive Architectures · doi:10.1016/j.bica.2015.10.002 · Cited by 11
“Since then, studies of selfaware robots have continued to grow as reported in Birlo and Tapus (2011) and Bongard, Zykov, and Lipson (2006).”
BackgroundWyjaśnianie za pomocą reprezentacji mentalnych. Perspektywa mechanistyczna
Gładziejewski, P. (2015) · Uniwersytet Mikołaja Kopernika eBooks · doi:10.12775/978-83-231-5693-2 · Cited by 11
Biologically Inspired Motor Control for Underactuated Robots – Trends and Challenges
Iida, F. (2009) · Lecture notes in control and information sciences · doi:10.1007/978-1-84882-985-5_14 · Cited by 11
“To cope with this problem, it is necessary to investigate how we could design more generalized state representations, and furthermore, how the system could generate autonomously an appropriate mechanical model of its own body [25].”
BackgroundLeitner, J., Harding, S., Frank, M., Förster, A., & Schmidhuber, J. (2013) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2013.6706819 · Cited by 11
“used sensory feedback to learn the model of a legged robot [6], but their method uses no high-dimensional sensory information (such as images).”
MethodArtificial intelligence and consciousness
Chella, A., Perconti, P., & Plebe, A. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-29258-3.00038-0 · Cited by 11
Information, complexity, brains and reality (Kolmogorov Manifesto)Preprint
Ruffini, G. (2007) · arXiv (Cornell University) · doi:10.48550/arxiv.0704.1147 · Cited by 11
“In this case, the cognitive agents were robots programmed to modify models of their own bodies (and, extrapolating, their environment) from past experience and in this way improve locomotive performance [1, 5].”
BackgroundHabra, T., Dallali, H., Cardellino, A., Natale, L., Tsagarakis, N., Fisette, P., & Ronsse, R. (2016) · Computational methods in applied sciences · doi:10.1007/978-3-319-30614-8_7 · Cited by 10
Inference of other’s internal neural models from active observation
Kim, K.-J., & Cho, S. (2015) · Biosystems · doi:10.1016/j.biosystems.2015.01.005 · Cited by 10
Physical Scaffolding Accelerates the Evolution of Robot Behavior
Buckingham, D., & Bongard, J. (2017) · Artificial Life · doi:10.1162/artl_a_00236 · Cited by 10
“Elements of → c (genes) in the range [0, 1] were mapped linearly into CTRNN parameters with the following ranges: connection weights 2 [−5, 5], input neuron biases 2 [−10, 0], hidden and output neuron biases2 [−5, 5], gains2 [1, 5], and time constants2 [1, 2].”
BackgroundMethodSelf-citationWinfield, A. F. T., & Hafner, V. V. (2019) · Springer eBooks · doi:10.1007/978-3-319-91554-8_73 · Cited by 10
Bonardi, S., Vespignani, M., Möckel, R., van den Kieboom, J., Pouya, S., Badri–Spröwitz, A., & Ijspeert, A. J. (2014) · Robotics: Science and Systems · doi:10.15607/rss.2014.x.004 · Cited by 10
“Some authors [19, 1, 11] used evolutionary methods and co-evolution to make the robot discover its own morphology, or used genetic algorithms to evolve possible gaits for given structures [9].”
BackgroundJeschke, S. (2015) · Springer eBooks · doi:10.1007/978-3-658-11755-9_14 · Cited by 10
Self-awareness and Self-expression: Inspiration from Psychology
Lewis, P. R., Chandra, A., & Glette, K. (2016) · Natural computing series · doi:10.1007/978-3-319-39675-0_2 · Cited by 8
Abstraction as a Mechanism to Cross the Reality Gap in Evolutionary Robotics
Scheper, K. Y. W., & de Croon, G. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-43488-9_25 · Cited by 10
“Work was not restricted to the evolution of the brain but was also used to evolve the physical body of the robot in a form of co-evolution [4,17].”
BackgroundWhen Robots Tell Each Other Stories: The Emergence of Artificial Fiction
Winfield, A. F. T. (2018) · Springer eBooks · doi:10.1007/978-3-319-64714-2_4 · Cited by 10
Fault Tolerant Control in Shape-Changing Internal Robots
Balasubramanian, L., Wray, T., & Damian, D. D. (2020) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra40945.2020.9196989 · Cited by 10
Chella, A., & Manzotti, R. (2012) · Atlantis thinking machines · doi:10.2991/978-94-91216-62-6_14 · Cited by 10
Towards Efficient Evolutionary Design of Autonomous Robots
Krčah, P. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-85857-7_14 · Cited by 10
“[1] has recently proposed a method of automatic recovery from unexpected damage for physical robots, through adaptive self-modelling.”
MethodFine, P., Paolo, E. A. D., & Izquierdo, E. J. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-74913-4_21 · Cited by 10
“[3], in which a robot’s locomotion exploits a model of its body which is automatically constructed and refined through a predictive algorithm).”
BackgroundAre Robots Present? From Motor Simulation to “Being There”
Riva, G., Gaggioli, A., & Mantovani, F. (2008) · CyberPsychology & Behavior · doi:10.1089/cpb.2007.0265 · Cited by 10
“It is not a self-producing and self-maintaining system that actively regulates its own boundary conditions so as to ensure its continued viability” (pp. 417–18).”
Zagal, J. C., & Lipson, H. (2009) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/1570256.1570297 · Cited by 10
Self-citationOnline Gait Learning for Modular Robots with Arbitrary Shapes and Sizes
Weel, B., d’Angelo, M., Haasdijk, E., & Eiben, A. E. (2017) · Artificial Life · doi:10.1162/artl_a_00223 · Cited by 10
“Another classic approach is based on gait control tables as in, for instance, [3] and [41].”
MethodGaussian processes for flexible robot learning.
Plagemann, C. (2008) · FreiDok plus (Universitätsbibliothek Freiburg) · Cited by 10
Fault Recovery in Swarm Robotics Systems using Learning Algorithms
Oladiran, O. O. (2019) · White Rose eTheses Online (University of Leeds, The University of Sheffield, University of York) · Cited by 10
On the Origins of Self-ModelingPreprint
Kwiatkowski, R., Hu, Y., Chen, B., & Lipson, H. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2209.02010 · Cited by 10
“Bongard et al.1 worked on a quadrupedal walking robot, however notably a quadruped with a less intuitive motor layout.”
BackgroundSelf-citationRegulation Priorities for Artificial Intelligence Foundation ModelsPreprint
Gaske, M. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4417565 · Cited by 10
Gu, J., Ye, Z., Rae-Grant, T., Wang, S., Zhao, D. X., Hester, J. D., Webster‐Wood, V. A., & Yao, L. (2025) · Nature Communications · doi:10.1038/s41467-025-63373-7 · Cited by 9
“Similarly, other morphing robots have typically been optimized for speci fi c tasks such as locomotion on different terrains or in water 5,47 .”
Create Adaptive Systems through “DNA” Guided Cellular Formation
Zouein, G., Chen, C., & Jin, Y. (2010) · Springer eBooks · doi:10.1007/978-0-85729-224-7_20 · Cited by 9
“In (Bongard et al. 2006), Lipson’s group further investigated adaptability through means other than reconfiguration through a technique called continuous self-modeling.”
Evolving morphological robustness for collective robotics
Putter, R., & Nitschke, G. (2017) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci.2017.8285267 · Cited by 9
“This study contributes to an open problem in evolutionary robotics, that is to evolve robot controllers that can continue to appropriately function given unforseen morphological change to the robot such as sensor damage or malfunction [17], [18].”
BackgroundDeane, G. (2022) · Artificial Life · doi:10.1162/artl_a_00368 · Cited by 9
“For instance, Bongard et al. (2006) built an artificial “starfish,” a four-legged robot that infers the structure of its body and uses this model to move.”
BackgroundIndividual and Collective Self-Development: Concepts and Challenges
Lippi, M., Mariani, S., Martinelli, M., & Zambonelli, F. (2022) · Annals of Computer Science and Information Systems · doi:10.15439/2022f301 · Cited by 9
“building robots capable of self-development [12].”
Free Gait Generation of Quadruped Robots via Impulse-Based Feasibility Analysis
Sun, H., Yang, J., Jia, Y., & Wang, C. (2023) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2023.3279523 · Cited by 9
“Generation of the free gait schedule. approaches to achieving resilient behavior and fault tolerance in robots include remodeling [31], reconfiguration [32], and other similar methodologies.”
BackgroundSelf identification and control of four-leg robot based on biological evolutionary mechanisms
Liang, J., & Xue, C. (2010) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea.2010.5515714 · Cited by 9
Improving RL power for on-line evolution of gaits in modular robots
Jelisavcic, M., Carlo, M. D., Haasdijk, E., & Eiben, A. E. (2016) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci.2016.7850166 · Cited by 9
“An early approach is based on gait control tables where a control table is an array of control sequences for an actuators with transitional conditions between sequences [10], [11].”
BackgroundReBot: A Novel Under-Actuated Resilient Robot
Liu, J., Liu, C., Zhang, B., Yuan, C., Qian, Z., & Zhang, W. (2018) · International Conference on Mechatronics and Machine Vision in Practice (M2VIP) · doi:10.1109/m2vip.2018.8600825 · Cited by 9
“Self-reconfiguration robots are based on the architecture of fully autonomous active modules and besides, they only change configurations by changing the connectivity of a set of autonomous active modules only; see the work in [3].”
BackgroundSelf-engineering – Technological Challenges
Roy, R., & Brooks, S. (2020) · Lecture notes in networks and systems · doi:10.1007/978-3-030-46817-0_2 · Cited by 9
“Once it learnt how to move the system was able to adapt and continue moving when a limb was removed [39].”
BackgroundAction-selection and crossover strategies for self-modeling machines
Bongard, J. (2007) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/1276958.1277004 · Cited by 9
“In the same way that evolutionary algorithms rely on the latent variation in populations of candidate solutions, the EEA is able to better model target systems by relying on model populations, rather than a single model.”
BackgroundMethodInfluentialSelf-citationAgile legged locomotion in reconfigurable modular robots
Yu, C., Matthews, D., Wang, J., Gu, J., Blackiston, D. J., Rubenstein, M., & Kriegman, S. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2519129123 · Cited by 8
“Compared to other legged robots that adapt to damage but contain a single point of failure (37, 38), the modular bodies described above have a greater capacity to survive large unforeseen changes to their structure because their structure contains self - sufficient submachines, any subset of which…”
Ultrastable neuroendocrine robot controller
Pitonakova, L. (2012) · Adaptive Behavior · doi:10.1177/1059712312462249 · Cited by 8
“There is a relatively new branch of robotics interested in adaptation through body and forward action-reaction modelling advocated, for example, by Bongard, Zykov, and Lipson (2006), Moriguchi and Lipson (2011) and Hild, Kubisch, and Höfer (2011).”
BackgroundInformational embodiment: Computational role of information structure in codes and robots
Pitti, A., Austin, M., Nakajima, K., & Kuniyoshi, Y. (2025) · Physics of Life Reviews · doi:10.1016/j.plrev.2025.03.018 · Cited by 8
Adaptive Informative Sampling for Active Learning
Lu, Z., Wu, X., & Bongard, J. (2010) · SIAM International Conference on Data Mining · doi:10.1137/1.9781611972801.78 · Cited by 8
“In previous applications [6][4][5], virtual data points are created as candidate tests.”
BackgroundSelf-citationBody models in humans, animals, and robots: mechanisms and plasticity
Hoffmann, M. (2021) · Oxford University Press eBooks · doi:10.1093/oso/9780198851721.003.0010 · Cited by 8
Mobile GPGPU Acceleration of Embodied Robot Simulation
Jones, S., Studley, M., & Winfield, A. F. T. (2015) · Communications in computer and information science · doi:10.1007/978-3-319-18084-7_8 · Cited by 8
“Bongard et al in [1] use a process of continuous self modelling to give a robot the ability to autonomously detect and compensate for damage.”
MethodSelf-aware Object Tracking in Multi-Camera Networks
Esterle, L., Simonjan, J., Nebehay, G., Pflugfelder, R. P., Domínguez, G. F., & Rinner, B. (2016) · Natural computing series · doi:10.1007/978-3-319-39675-0_13 · Cited by 8
Marjaninejad, A., Tan, J., & Valero‐Cuevas, F. J. (2020) · Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) · doi:10.1109/embc44109.2020.9176089 · Cited by 8
“nd showed the feasibility of adaptation on-the-go to the changes in the tendon stiffness values. However, we want to underline that other adaptive learning methods can also be used (e.g., [34], [35], [43]). 3) Functional task of locomotion: In this section, we study the results for the functional task of locomotion fo…”
Who Am I?: Towards Social Self-Awareness for Intelligent Agents
Subagdja, B., Tay, H. Y., & Tan, A. (2020) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2020/606 · Cited by 8
“Works on embodied robotic agents focus on the discovery of a robot’s own motion dynamic [Bongard et al. , 2006; Hart and Scas-selati, 2012; Stoytchev, 2011], recognize and analyze oneself based on mirror image projection [Hart and Scasselati, 2012; Stoytchev, 2011], or control and adapt its own…”
Cognitive Networking With Regards to NASA's Space Communication and Navigation Program
Ivancic, W. D., Paulsen, P. E., Vaden, K. R., & Ponchak, D. S. (2013) · Cited by 8
The Small Loop Problem: A Challenge for Artificial Emergent Cognition
Georgeon, O. L., & Marshall, J. B. (2012) · Advances in intelligent systems and computing · doi:10.1007/978-3-642-34274-5_27 · Cited by 8
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.