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 601–700 of 861
Cognitive architectures and autonomy: Commentary and Response
Duch, W., Tan, A., & Franklin, S. (2012) · Journal of Artificial General Intelligence · doi:10.2478/v10229-011-0016-2 · Cited by 2
Guimarães, A. S. (2008) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · Cited by 2
Self-manipulation and dynamic transitions for a legged robot
Johnson, A. M. (2014) · ScholarlyCommons (University of Pennsylvania) · Cited by 2
Aportaciones y Aplicaciones de Disciplinas Bioinspiradas a la Creatividad Computacional
Quintana, S., & Alberto, C. (2015) · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · Cited by 2
Are Minds Computable?Preprint
Gershenson, C. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1110.3002 · Cited by 2
“Still, there are several examples of adaptive systems that go beyond this limitation (e.g. Braitenberg, 1986; Bongard et al., 2006).”
BackgroundHow to avoid ethically relevant Machine ConsciousnessPreprint
Lodwich, A. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1606.00058 · Cited by 2
Towards the Self-constructive Brain: emergence of adaptive behaviorPreprint
Corbacho, F. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1608.02229 · Cited by 2
Anshar, M. (2017) · UTS ePRESS (University of Technology Sydney) · Cited by 2
Publisher Correction: Mergeable nervous systems for robots
Mathews, N., Christensen, A. L., O’Grady, R., Mondada, F., & Dorigo, M. (2017) · Nature Communications · doi:10.1038/s41467-017-01622-0 · Cited by 2
Neural language representations predict outcomes of scientific researchPreprint
Bagrow, J. P., Berenberg, D., & Bongard, J. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1805.06879 · Cited by 2
“Previous research has shown ways for AI systems to synthesize and predict physical relationships [24, 25, 26].”
BackgroundSelf-citationTaylor, T., & Dorin, A. (2018) · Monash University Research Portal (Monash University) · doi:10.48550/arxiv.1806.01322 · Cited by 2
“The idea of self-repairing machines is present in the work of Eliot, Forster, Campbell [ The Machine ] and Bernal, and this is indeed a theme in current evolutionary robotics research, e.g. (Bongard et al., 2006), (Cully et al., 2015).”
BackgroundLiu, P. (2018) · Bournemouth University Research Online (Bournemouth University) · Cited by 2
On Self-Adaptive Mutation Restarts for Evolutionary Robotics with Real RotorcraftPreprint
Howard, G. D. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1703.10754 · Cited by 2
“To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior speci c permission and/or a fee.”
BackgroundStruk, A. A. (2019) · UWSpace (University of Waterloo) · Cited by 2
To Root Artificial Intelligence Deeply in Basic Science for a New Generation of AIPreprint
Yang, J., & Peng, Y. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2009.05678 · Cited by 2
Husbands, P. (2010) · Springer eBooks · doi:10.1007/978-0-387-30164-8_285 · Cited by 2
Editorial: Novel methods in embodied and enactive AI and cognition
Bonsignorio, F. (2023) · Frontiers in Neurorobotics · doi:10.3389/fnbot.2023.1162568 · Cited by 2
“They are embedded in a physical system (a body) (Pfeifer and Bongard, 2006), emerging bottom-up from the interaction of large numbers of loosely coupled components (Bonsignorio, 2007), and they are usually associated with life.”
BackgroundTechnical Report on: Tripedal Dynamic Gaits for a Quadruped RobotPreprint
Stewart-Height, A., & Koditschek, D. E. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2303.02280 · Cited by 2
“Past work of this kind monitors the robot’s whole body [33], [38], [40] or its legs only [23], [37], [39], and flag a sensed change as a fault.”
BackgroundVisual motion estimation and tracking of rigid bodies by physical simulation
Duff, D. J. (2011) · University of Birmingham Institutional Research Archive (University of Birmingham) · Cited by 2
Environment-driven Distributed Evolutionary Adaptation for Collective Robotic Systems
Montanier, J.-M. (2013) · theses.fr (ABES) · doi:10.70675/2237182bz5ef3z489dz8957z02dcfceade3a · Cited by 2
Micro-Data Reinforcement Learning for Adaptive Robots
Chatzilygeroudis, K. I. (2018) · theses.fr (ABES) · doi:10.70675/7990d9edz7f40z4344z9318z6da4e46000c0 · Cited by 2
“Lastly, recent works (Chatzilygeroudis and Mouret, 2018; Chatzilygeroudis et al., 2018b; Cutler and How, 2015; Saveriano et al., 2017; Bongard et al., 2006; Zhu et al., 2018) showcase that taking advantage of dynamics simulators or inaccurate simple dynamics models can help in reducing the amount…”
BackgroundData-Efficient Robot Learning using Priors from Simulators
Kaushik, R. (2020) · theses.fr (ABES) · doi:10.70675/f4ec9e7bzd1d5z42cdza2c5z8ffd986bd3e8 · Cited by 2
A preference-based approach to machine ethics for automated planning
Jedwabny, M. (2022) · theses.fr (ABES) · doi:10.70675/cdbc9d15zedccz471az9398zed83a64b5068 · Cited by 2
Proprioceptive-visual correspondence enables self-other distinction in humanoid robotsPreprint
Chen, Y., Gao, T., 葛益众, Ban, S., Wang, Y., Xiong, H., Zeng, W., & Zhu, W. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.13222 · Cited by 2
“…which body in the scene is itself, and self-modeling , acquiring a predictive representation of that body and how it changes with action (Bongard et al., 2006; Kwiatkowski & Lipson, 2019), a capacity that recent work has shown can be learned from proprioceptive–visual experience in…”
Tomaszewski, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2608.14894 · Cited by 2
“Robots can learn predictive models of their own morphology or dynamics from sensorimotor interaction and then use those models for adaptation, damage recovery, planning, or behavior synthesis Bongard et al. (2006); Kwiatkowski and Lipson (2019); Kwiatkowski et al. (2022).”
A baseline-realistic objective open-ended kinematics simulator for evolutionary robotics
Konsella, R., Chiarulli, F., Peterson, J. R., & Rieffel, J. A. (2017) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/3067695.3082164 · Cited by 1
“…exist to trying to "cross" the reality gap - beginning with Jakobi’s own modeling of sensor noise [12], and including more sophisticated techniques such as Bongard’s co-evolutionary self-modeling [1], Cully et al. ’s Bayesian-Optimization approach [6], and Mouret’s transferability approach [13].”
MethodDadashova, S. N. (2022) · Alma mater Vestnik Vysshey Shkoly · doi:10.20339/am.07-22.015 · Cited by 1
Towards an Anticipatory Mechanism for Complex Decisions in a Bio-Hybrid Beehive
Mellmann, H., Taliaronak, V., & Hafner, V. V. (2023) · Studies in computational intelligence · doi:10.1007/978-3-031-26651-5_7 · Cited by 1
Riscos, P. D. L., & Corbacho, F. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-1904-7_24 · Cited by 1
Inertial Parameters Identification for Floating-Base Multibody Systems Using Spinning Trajectories
Zhu, H., Xu, Y., Zhou, Z., Gao, Y., & Ding, N. (2025) · IEEE International Conference on Industrial Informatics (INDIN) · doi:10.1109/indin64977.2025.11279608 · Cited by 1
Recursive identity and ethical recognition in humans, robots, and AI
Sawyer, C. H. (2026) · AI & Society · doi:10.1007/s00146-026-02943-9 · Cited by 1
“Robotic systems sustain stability through sensorimotor coupling and internal simulation (Pfeifer and Scheier 2001; Bongard et al. 2006; Tani 1998, 2016).”
InfluentialOmni‐Scale Biomimetic Robotics
Chen, W., & Liu, K. (2026) · Advanced Materials Technologies · doi:10.1002/admt.71047 · Cited by 1
“…robotics, this biological inspiration has driven the development of two dominant control architectures: Central Pattern Generator (CPG) control [ 179, 180 ] and distributed control [ 181, 182 ], both of which reflect a paradigm shift from computation ‑intensive to physically ‑embedded intelligence.”
Perception in action: a robotic system that can teach itself to melodiously play music by ear
Azadjou, H., Marjaninejad, A., & Valero‐Cuevas, F. J. (2026) · Journal of The Royal Society Interface · doi:10.1098/rsif.2025.0909 · Cited by 1
Damage Adaptation in Seconds for Architected Materials
Avtges, J., Ketchum, J., Young, H., Kim, T., Truby, R. L., & Murphey, T. D. (2026) · Robotics: Science and Systems · doi:10.15607/rss.2026.xxii.158 · Cited by 1
Smart cellular bricks for decentralized shape classification and damage recovery
Moreno, R., Faíña, A., Sudhakaran, S., Walker, K., & Risi, S. (2026) · Nature Communications · doi:10.1038/s41467-026-75166-7 · Cited by 1
“Our system differs fundamentally from prior self-modeling robotics research by achieving distributed morphological understanding with-outrelyingonactuation 13 – 15 ,orexplicitrule-basedcoordination 16,17 .”
Bioinspired multimodal robotics
Ren, Z., Duo, Y., Xu, H., Zhang, Y., Liu, X., Paik, J. K., Ijspeert, A. J., & Wen, L. (2026) · Science Robotics · doi:10.1126/scirobotics.aea7639 · Cited by 1
Energy as a Common Currency for Understanding Embodied Evolution
Xie, Y. H., Zhang, Y., Sun, T., & Iida, F. (2026) · Cyborg and Bionic Systems · doi:10.34133/cbsystems.0680 · Cited by 1
“It contrasts task-centered scoring with energy-centered persistence under constraint and shows how explicit energy accounting enables regulation, structural adaptation, and structural plasticity to be compared under a shared interpretive framework [ 6 , 11 , 19 ].”
From chemistry to cognition: the adaptive origins of consciousness under constraint
Stibel, J. M. (2026) · Frontiers in Neuroscience · doi:10.3389/fnins.2026.1907922 · Cited by 1
“…and acts through closed sensorimotor loops, then purely local arbitration should increasingly fail under uncertainty, conflict, and irreversibility (Bongard et al., 2006; Ortega and Braun, 2013; Kriegman et al., 2020; Doncieux et al., 2015; Dehaene et al., 2017; Butlin et al., 2025; Seth, 2025).”
Zero-Shot Robot Design with Residual Physics
Matthews, D., & Kriegman, S. (2026) · Conference on Artificial Life (ALIFE) · doi:10.1162/isal.a.963 · Cited by 1
The Nature and Structure of Feasible Sets
Valero‐Cuevas, F. J. (2015) · Biosystems & biorobotics · doi:10.1007/978-1-4471-6747-1_9 · Cited by 1
Inference of Other’s Minds with Limited Information in Evolutionary Robotics
Kim, K.-J., & Cho, S. (2020) · International Journal of Social Robotics · doi:10.1007/s12369-020-00660-x · Cited by 1
“This was a reverse-engineering task, and we adopted an estimation–exploration algorithm (EEA) [34, 35] to solve the robotic ToM problem, which has been used for reverse engineering in dynamical systems [34], self-modeling [35] and inference of the tendon networks of human fingers [36].”
MethodClark, A. (2008) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780195333213.003.0003 · Cited by 1
Narahara, T. (2015) · Communications in computer and information science · doi:10.1007/978-3-662-47386-3_26 · Cited by 1
Artificial Evolution of Autonomous Robots and Virtual Creatures
Bredèche, N. (2014) · Springer eBooks · doi:10.1007/978-94-017-9014-7_29 · Cited by 1
Sturm, J., Plagemann, C., & Burgard, W. (2012) · Springer tracts in advanced robotics · doi:10.1007/978-3-642-25116-0_12 · Cited by 1
Modular robot with adaptive connection topology
Hartono, P., & Nakane, A. (2010) · International Conference on Hybrid Intelligent Systems (HIS) · doi:10.1109/his.2010.5600785 · Cited by 1
“Keywords-modular robot, central pattern generator, adaptive topology, simulated annealing I. INTRODUCTION It is known that John von Neumann developed logical ideas for self-replicating of artifacts [1].”
BackgroundDeveloping emotional security among children who have been adopted
Trujillo, K. (2010) · Digital Commons - DU (University of Denver) · Cited by 1
Losey, D. P., McDonald, C. G., & O’Malley, M. K. (2016) · IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob) · doi:10.1109/biorob.2016.7523663 · Cited by 1
Mining Device Data to Auto-commission Buildings
González, L. I. L., & Amft, O. (2016) · ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation (BuildSys) · doi:10.1145/2993422.2996413 · Cited by 1
“For the approach to work devices need to be configured in the BMS, thus creating a causality dilemma, i.e., to find the correct use patterns the BMS need to be correctly configured.”
Switching Adaptability in Human-Inspired Sidesteps: A Minimal Model
Fujii, K., Yoshihara, Y., Tanabe, H., & Yamamoto, Y. (2017) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2017.00298 · Cited by 1
“This control system is biologically plausible than explicit simulation because the system can perform self-modeling (Bongard et al., 2006) to adapt to the situation beyond its framework.”
BackgroundToward Energy Autonomy in Heterogeneous Modular Plant-Inspired Robots through Artificial Evolution
Veenstra, F., Metayer, C., Risi, S., & Støy, K. (2017) · Frontiers in Robotics and AI · doi:10.3389/frobt.2017.00043 · Cited by 1
“The simulator could in turn evolve behaviors for that specific robots configuration in the simulation environment similar to Wagy and Bongard (2015) with potential continuous self-modeling (Bongard et al., 2006).”
MethodHuman–Computer Interaction with Novel and Advanced Materials
Döring, T., Porzel, R., & Malaka, R. (2017) · Wiley eBooks · doi:10.1002/9783527679249.ch26 · Cited by 1
Urban search mobile platform modeling in hindered access conditions
Barankova, I. I., Mikhailova, U. V., Kalugina, O. B., & Баранков, В. (2018) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1015/3/032174 · Cited by 1
A Learning Based Recovery for Damaged Snake-Like Robots
Guan, Z., Huang, J., Jian, Z., liu, L., Cheng, L., & Huang, K. (2018) · Lecture notes in computer science · doi:10.1007/978-3-030-04239-4_3 · Cited by 1
Баумана, М. И. Н. Э., & Воевода, Н. Н. (2019) · Politechnical student journal · doi:10.18698/2541-8009-2018-12-422 · Cited by 1
MODERN STATE OF RESEARCH IN THE THEORY OF TARGETED COLLECTIVE BEHAVIOR OF INTELLECTUAL ROBOTS GROUP
Ауесовна, П. И. (2019) · News of the Kabardin-Balkar Scientific Center of RAS · doi:10.35330/1991-6639-2019-3-89-23-30 · Cited by 1
Strategies for Mastering Uncertainty
Pfetsch, M. E., Abele, E., Altherr, L. C., Bölling, C., Brötz, N., Dietrich, I., Gally, T., Geßner, F., Groche, P., Hoppe, F., et al. (2021) · Springer tracts in mechanical engineering · doi:10.1007/978-3-030-78354-9_6 · Cited by 1
Poth, C. H., Schneider, W. X., Gutmann, M., Rathgeber, B., Syed, T., Birbaumer, N., Matuz, T., Pauen, M., Reisenzein, R., Roberts, R. C., et al. (2013) · J.B. Metzler eBooks · doi:10.1007/978-3-476-05288-9_5 · Cited by 1
Escobar, M.-J., Alexandre, F., Viéville, T., & Palacios, A. G. (2022) · International series on intelligent systems, control and automation: science and engineering · doi:10.1007/978-3-319-40003-7_8 · Cited by 1
Clark, A. (2008) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780195333213.003.0009 · Cited by 1
Evolutionary robotics tutorial
Bredèche, N., Doncieux, S., & Mouret, J.-B. (2019) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/3319619.3323391 · Cited by 1
Zhang, Y., Xia, T., & Huston, D. R. (2022) · Elsevier eBooks · doi:10.1016/b978-0-08-102696-0.00002-6 · Cited by 1
From Robots to Humanoids: Examining an Ethical View of Social Robotics
Ampe-N’DA, L. D., Payne, B. A., Arora, A. S., & Arora, A. (2022) · International Marketing and Management Research · doi:10.1007/978-3-031-04867-8_2 · Cited by 1
Perceptual Presence in the Khunian-Popperian Bayesian Brain
Wiese, W. (2016) · The MIT Press eBooks · doi:10.7551/mitpress/10603.003.0107 · Cited by 1
Pontin, M., & Damian, D. D. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3243440 · Cited by 1
Autonomous Discovery of Robot Structure and Motion Control Through Large Vision Models
Li, X., Liu, L., Zhang, Z., Guo, X., & Cui, J. (2024) · IEEE Conference on Cybernetics and Intelligent Systems · doi:10.1109/cis-ram61939.2024.10673339 · Cited by 1
“This self-discovery not only enhances the robot’s functionality and efficiency but also brings us closer to creating machines that can truly understand and interact with their environments in a dynamic and adaptive manner [2].”
BackgroundSoftNeRF: A Self-Modeling Soft Robot Plugin for Various Tasks
Shan, J., Li, Y., Feng, Q., Li, D., Han, L., & Wang, H. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10801344 · Cited by 1
“This capability is vital for planning and controlling robot motion [5], [6].”
Motor Skew and the Ontology of Embodiment
Sawyer, C. (2025) · Human Studies · doi:10.1007/s10746-025-09812-2 · Cited by 1
“In early experiments by Bongard et al. (2006), robots evolved to adapt to simulated limb damage or deformation, but the goal remained the restoration of locomotor efficiency—a return to symmetrical function.”
DiCesare, C. A. (2020) · OhioLink ETD Center (Ohio Library and Information Network) · Cited by 1
Experimental Philosophy of Imagination and Creativity
Stuart, M. T. (2026) · Oxford University Press eBooks · doi:10.1093/9780197694855.003.0008 · Cited by 1
PSO-based leg-loss identification method for legged robots
Chattunyakit, S., Kobayashi, Y., & Emaru, T. (2018) · Journal of Research and Applications in Mechanical Engineering · Cited by 1
Evolving Locomotion for a Simulated 12-DOF Quadruped Robot
Klaus, G., Glette, K., & Hovin, M. E. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-28792-3_13 · Cited by 1
Managing contextual artificial neural networks with a service-based mediatorPreprint
Fish, G. (2012) · arXiv (Cornell University) · doi:10.48550/arxiv.1204.0262 · Cited by 1
“…introduces a concept for a mediator framework for such systems and seeks to show several architectures which would support it, potential benefits in combining the signals of disparate networks for formalized, high level logic and signal processing, and its possible academic and industrial uses.”
BackgroundShape Recognition Through Dynamic Motor Representations
Misra, N., & Choe, Y. (2007) · Springer eBooks · doi:10.1007/978-3-540-73267-9_9 · Cited by 1
“More recent works have specifically looked at the role of action in perception and perceptual organization [48, 49], information flow [50], and the role of internal models in action selection and behavior [ 51 ].”
BackgroundTowards Natural And Robust Human-Robot Interaction Using Sketch And Speech
Shah, D. C. (2012) · eCommons (Cornell University) · Cited by 1
Combined structure and motion extraction from visual data using evolutionary active learning
Kaipa, K. N., Bongard, J., & Meltzoff, A. N. (2009) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/1569901.1569919 · Cited by 1
“The EEA has been applied to several other learning problems [5], [4], [2].”
MethodSelf-citationAbstract of: “Fast Damage Recovery in Robotics with the T-Resilience Algorithm”
Koos, S., Cully, A., & Mouret, J.-B. (2014) · Conference on Artificial Life (ALIFE) · doi:10.1162/978-0-262-32621-6-ch026 · Cited by 1
Automated reverse engineering of agent behaviors
Li, W. (2016) · White Rose eTheses Online (University of Leeds, The University of Sheffield, University of York) · Cited by 1
Learning Task Models for Robotic Manipulation of Nonrigid Objects
Langsfeld, J. D. (2017) · University Libraries (University of Maryland) · doi:10.13016/m2gk30 · Cited by 1
Zero Shot Learning on Simulated RobotsPreprint
Kwiatkowski, R., & Lipson, H. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.01994 · Cited by 1
“[2] worked on a quadrapedal walking robot, however notably a quadraped with a less intuitive motor layout.”
MethodSelf-citationThe Evolution of Behaviours in Swarms of Robots
Holland, J. (2019) · Arrow@dit (Dublin Institute of Technology) · doi:10.13025/16755 · Cited by 1
Data-Efficient Robot Learning using Priors from Simulators
Kaushik, R. (2020) · HAL · Cited by 1
Jones, O. P. H. (2020) · White Rose eTheses Online (University of Leeds, The University of Sheffield, University of York) · Cited by 1
Introduction: BRAINBOUND Versus EXTENDED
(2008) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780195333213.002.0010 · Cited by 1
(2008) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780195333213.002.0007 · Cited by 1
A proposal to improve research in AI algorithm and data governancePreprint
Braga, J., Regateiro, F. S., Stiubiener, I., & Braga, J. C. (2022) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/sr7kt · Cited by 1
Uma proposta para impulsionar as pesquisas em governança de algoritmos de IA e dadosPreprint
Braga, J., Regateiro, F. S., Stiubiener, I., & Braga, J. C. (2022) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/xcpsd · Cited by 1
Glamour muscles: why having a body is not what it means to be embodiedPreprint
Beaulieu, S., & Kriegman, S. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2307.08598 · Cited by 1
“Recovering function erased by mechanical injury through exaptation of viable parts has a rich history in robotics [14, 51, 59].”
BackgroundBrains as output/input systems
Brembs, B. (2013) · doi:10.59350/a7061-xkb13 · Cited by 1
Bio-Inspired Adaptive Control of Robotic Manipulators for Grasping in Orbital Space Missions
Ogundipe, C. (2024) · Carleton University's Institutional Repository (MacOdrum Library, Carleton University) · doi:10.22215/etd/2024-15987 · Cited by 1
Evolutionary Gait Reconfiguration in Damaged Legged RobotsPreprint
Farghdani, S., & Chhabra, R. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.19968 · Cited by 1
“Bongard’s seminal work introduced a self-modeling robot that inferred its structure via actuation-sensation feedback to recover locomotion [11].”
Adaptive GR(1) Specification Repair for Liveness-Preserving Shielding in Reinforcement LearningPreprint
Georgescu, T.-A., Goodall, A. W., Alrajeh, D., Belardinelli, F., & Uchitel, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2511.02605 · Cited by 1
“…, 0 finite set of actions, 𝑃 : 𝑆 × 𝐴 → Δ ( 𝑆 ) is the probabilistic transition function, with Δ ( 𝑆 ) denoting the set of distributions over 𝑆 , 𝑅 : 𝑆 × 𝐴 → R is the reward function, and 𝛾 is the discount The agent’s policy 𝜋 : 𝑆 → Δ ( 𝐴 ) is a probabilistic function optimal policy 𝜋…”
Information Theoretic Models of Social Interaction
Salge, C. (2013) · University of Hertfordshire Research Archive (University of Hertfordshire) · doi:10.18745/th.13887 · Cited by 1
Extensión de la representación de un yo para una arquitectura de sistema autónomo
Gordillo-Dagallier, L. (2016) · Archivo Digital UPM (Universidad Politécnica de Madrid) · Cited by 1
Optimisation de la locomotion de robots bas coût à pattes
Passault, G. (2016) · theses.fr (ABES) · doi:10.70675/94ead768z1485z48a8za556z0722342cd784 · Cited by 1
Swarm-Inspired Generation of Collective Behaviors in Graph Dynamical SystemsPreprint
Chen, J., Chen, S., Gong, C., Fan, L., & Xu, C. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.24958 · Cited by 1
Damage recovery for robot controllers and simulators evolved using bootstrapped neuro-simulation
Leonard, B. A. (2019) · Nelson Mandela University Research Repository · Cited by 1
Pretorius, C. (2019) · Nelson Mandela University Research Repository · Cited by 1
Toward Recursive Self-Improvement in Physical AIPreprint
Luo, M., Bai, Z., Xu, S., Li, Y., Li, K., Qian, M., Lu, W., Zhang, R., Zou, Y., Luo, Z., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.29677 · Cited by 2
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.