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 501–600 of 861
Computational mental simulation: A review
Polceanu, M., & Buche, C. (2016) · Computer Animation and Virtual Worlds · doi:10.1002/cav.1732 · Cited by 4
“46 We note that these are difficult problems in robotics, and it is interesting that mental simulation is able in these cases to decrease complexity of the original tasks and allow robots to perform better in the real world.”
BackgroundInfluentialLipson, H. (2007) · Springer eBooks · doi:10.1007/978-3-540-77296-5_28 · Cited by 4
Self-citationCharacterizing Programming Systems Allowing Program Self-reference
Case, J., & MoeliusIII, S. E. (2007) · Lecture notes in computer science · doi:10.1007/978-3-540-73001-9_13 · Cited by 4
Exploiting multiple robots to accelerate self-modeling
Bongard, J. (2007) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/1276958.1277006 · Cited by 4
“In the robotics application we showed that a robot could use this technique to diagnose and recover from body damage [8] by inferring the structure of its own body (or changes in its body structure as a result of damage).”
BackgroundMethodInfluentialSelf-citationPlanning to learn: Integrating model learning into a trajectory planner for mobile robots
Greytak, M. B., & Hover, F. S. (2009) · IEEE International Conference on Information and Automation (ICIA) · doi:10.1109/icinfa.2009.5204888 · Cited by 4
“Exploration of the state space can improve the convergence rate by presenting the learning algorithm with novel data; as the robot learns more about its own plant model, it can perform tasks more efficiently and with less error [6].”
BackgroundEvaluation of Internal Models in Autonomous Learning
Smith, S. C., & Herrmann, J. M. (2018) · IEEE Transactions on Cognitive and Developmental Systems · doi:10.1109/tcds.2018.2865999 · Cited by 4
“Another scenario is when a robot is able to indirectly infer its own morphology through self-directed exploration and then use the resulting self-models to synthesise new behaviours [24].”
BackgroundResilient Structures Through Machine Learning And Evolution
Mehanna, R. (2013) · ACADIA quarterly · doi:10.52842/conf.acadia.2013.319 · Cited by 4
Use of Robotics in the Study of Animal Behavior
Patricelli, G. L. (2016) · Elsevier eBooks · doi:10.1016/b978-0-12-809633-8.01240-1 · Cited by 4
Morphology dictates a robot's ability to ground crowd-proposed languagePreprint
Mahoor, Z., Felag, J., & Bongard, J. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1712.05881 · Cited by 4
“…be adjusted to any unforeseen changes through continuous simulations in parallel with reality. is beyond the scope of the current experiment, but [Bongard et al. , 2006] and [Cully et al. , 2015] studied how a physical robot can generate a model of the environment and its self, suggesting this…”
BackgroundSelf-citationA Classical Uncertainty Principle for Organizations
Wood, J., Tung, H., Grayson, J. M., Poppeliers, C., & Lawless, W. F. (2009) · IGI Global eBooks · doi:10.4018/978-1-60566-026-4.ch087 · Cited by 4
Towards Self-constructive Artificial Intelligence: Algorithmic basis (Part I)Preprint
Corbacho, F. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.01989 · Cited by 4
A review paper of bio-inspired environmental adaptive and precisely maneuverable soft robotsPreprint
Shen, M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.03171 · Cited by 4
Biologically Inspired Robot Body Models and Self-Calibration
Hoffmann, M. (2021) · Springer eBooks · doi:10.1007/978-3-642-41610-1_201-1 · Cited by 4
Husbands, P. (2016) · Springer eBooks · doi:10.1007/978-1-4899-7502-7_94-1 · Cited by 4
(2008) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780195333213.005.0001 · Cited by 4
Azadjou, H., Marjaninejad, A., & Valero‐Cuevas, F. J. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.06.04.597044 · Cited by 4
“Alternatively, expert demonstration of the task or expert knowledge are used to fine-tune these systems which often require extensive training in simulation or via interactions with the environment(6; 7; 8; 9; 10; 11; 12; 13; 14).”
BackgroundBoeing, A. (2009) · UWA Profiles and Research Repository (University of Western Australia) · Cited by 4
Creative Adaptation through Learning
Cully, A. (2015) · theses.fr (ABES) · doi:10.70675/f17594caz64c7z42b0z815czd4caac624298 · Cited by 4
“3 and a self-model of the robot, which either can be a standard physics simulator or can be automatically discovered (Bongard et al., 2006).”
BackgroundMethodInfluentialInsect‐Inspired Resilient Machines
Chuthong, T., Büscher, T. H., Gorb, S. N., & Manoonpong, P. (2025) · Advanced Intelligent Systems · doi:10.1002/aisy.202500270 · Cited by 3
The Future of Research in Cognitive Robotics: Foundation Models or Developmental Cognitive Models?
Vernon, D. (2025) · Advanced Robotics Research · doi:10.1002/adrr.202500066 · Cited by 3
Yordanova, M., & Hafner, V. V. (2026) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/1343/1/012020 · Cited by 3
“Bongard et al. [21] explored how a four-legged machine could autonomously recover from unexpected damage by continuously updating a self-model of its actuation-sensation relationships, allowing it to indirectly deduce its own structure.”
Evolutionary Machine Learning in Robotics
Medvet, E., Nadizar, G., Pigozzi, F., & Salvato, E. (2023) · Genetic and evolutionary computation · doi:10.1007/978-981-99-3814-8_23 · Cited by 3
An Investigation of Graceful Degradation in Boolean Network Robots Subject to Online Adaptation
Braccini, M., Baldini, P., & Roli, A. (2024) · Communications in computer and information science · doi:10.1007/978-3-031-57430-6_16 · Cited by 3
Cognition-Oriented Multiagent Reinforcement Learning
Qiu, T., Wu, S., Liu, Z., Pu, Z., Yi, J., Zhao, Y., & Luo, B. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3502176 · Cited by 3
“Bongard et al. [40] and Chatila et al. [41] provide insights into how agents can adapt to and understand their surroundings, which is crucial for effective situational cognition.”
Model adaptive gait scheme based on evolutionary algorithm
Gao, H. C., Wang, T., Liang, J., & Zhou, Y. B. (2013) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea.2013.6566387 · Cited by 3
“Bongard with his team from Cornell University has described a robot that can recover from damage autonomously, through continuous self-modeling [8], [9].”
BackgroundAutonomic behaviors in an Ambient Intelligence system
Paola, A. D., Ferraro, P., Gaglio, S., & Re, G. L. (2014) · IEEE Symposium on Computational Intelligence for Human-like Intelligence (CIHLI) · doi:10.1109/cihli.2014.7013381 · Cited by 3
Towards Spatial Perception: Learning to Locate Objects From Vision
Leitner, J., Harding, S., Frank, M., Förster, A., & Schmidhuber, J. (2012) · QUT ePrints (Queensland University of Technology) · doi:10.2390/biecoll-robotdoc2012-08 · Cited by 3
Wehle, M., Weidemann, A., & Boblan, I. W. (2017) · Advances in computational intelligence and robotics book series · doi:10.4018/978-1-5225-1947-8.ch005 · Cited by 4
Body Design and Gait Generation of Chair-Type Asymmetrical Tripedal Low-rigidity Robot
Inoue, S., Kawaharazuka, K., Okada, K., & Inaba, M. (2024) · IEEE International Conference on Soft Robotics (RoboSoft) · doi:10.1109/robosoft60065.2024.10522029 · Cited by 3
“[14] modeled the robot itself by randomly moving its body without knowing its own body structure, and then generated a gait that suited its body.”
BackgroundFast and modular whole-body Lagrangian dynamics of legged robots with changing morphology
Farghdani, S., Abdelrahman, O., & Chhabra, R. (2026) · Nonlinear Dynamics · doi:10.1007/s11071-026-12594-6 · Cited by 3
“Because of its accessible documentation and API, OpenDE is widely used to simulate MLRs dynamics [89, 90].”
Comparison of Sensor-Feedback Prediction Methods for Robust Behavior Execution
Rauch, C., Berghöfer, E., Köhler, T., & Kirchner, F. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40942-4_18 · Cited by 3
Case, J., & Moelius, S. E. (2009) · Cited by 3
On how self-body awareness improves autonomy in social robots
Rodríguez, I., Martínez‐Otzeta, J. M., Lazkano, E., Ruiz, T., & Sierra, B. (2017) · IEEE International Conference on Robotics and Biomimetics (ROBIO) · doi:10.1109/robio.2017.8324661 · Cited by 3
“[5] propose a system able to change their own models of their physical embodiment.”
BackgroundTowards the Mind of a Humanoid: Does a Cognitive Robot Need a Self? - Lessons from Neuroscience
Antonova, E., & Nehaniv, C. L. (2018) · Conference on Artificial Life (ALIFE) · doi:10.1162/isal_a_00079 · Cited by 3
“Increasingly, AI robotics designers are finding they need to include aspects of somatic self by introducing adaptive somatic body self-models (Bongard et al., 2006) and multisensory ego-sphere saliency (Ruesch et al.”
BackgroundHagen, D. A., Marjaninejad, A., & Valero‐Cuevas, F. J. (2020) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros45743.2020.9341268 · Cited by 3
“While it is sometimes possible to derive analytical relationships among tendon tensions, motor rotations, and joint posture given the precise equations for the kinematics and dynamics, in practice it is often impractical or impossible to obtain accurate and time-invariant models of such nonlinear dynamical systems [3]…”
BackgroundThe Walking Robot Control System that is Adaptive to Changes in the Kinematics
Сергеевна, С. А., & Vorotnikov, S. A. (2021) · Mekhatronika Avtomatizatsiya Upravlenie · doi:10.17587/mau.22.601-609 · Cited by 3
Proceedings of the Joint International Resilience Conference, JIRC2020
Comes, T. (2020) · University of Twente Research Information · doi:10.3990/1.9789036550956 · Cited by 3
Fast Adaptation Dynamics Model for Robot’s Damage Recovery
Chen, C., Wang, D., Yu, J., Xiang, P., Lu, H., Wang, Y., & Xiong, R. (2022) · IEEE International Conference on Real-time Computing and Robotics (RCAR) · doi:10.1109/rcar54675.2022.9872230 · Cited by 3
“[5] used the robot’s actuation-sensing relationship to indirectly infer its morphology structure and used this self-model to generate forward motion.”
MethodDie Philosophie der Bio-Robotik
Tamborini, M., & Verlag, F. M. (2024) · Felix Meiner Verlag eBooks · doi:10.28937/978-3-7873-4432-1 · Cited by 3
Automated Optimization of Walking Parameters for the Nao Humanoid Robot
Girardi, L. N., Kooijman, C., Wiggers, A., & Visser, A. (2013) · UvA-DARE (University of Amsterdam) · Cited by 3
HyperNEAT Versus RL PoWER for Online Gait Learning in Modular Robots
d’Angelo, M., Weel, B., & Eiben, A. E. (2014) · Lecture notes in computer science · doi:10.1007/978-3-662-45523-4_63 · Cited by 3
“One of the earliest types is gait control tables as in, for instance, [1] and [19].”
BackgroundSelf-repairing design process applied to a 4-bar linkage mechanism
Bell, C., Farnsworth, M., Knowles, J. A. C., & Tiwari, A. (2015) · Proceedings of the Institution of Mechanical Engineers Part B Journal of Engineering Manufacture · doi:10.1177/0954405415598924 · Cited by 3
“They test their algorithm with application to a hexapod robot and show that it offers significant performance advantages over other robust design methodologies, such as optimised control-based methods.(1) Although the proposed algorithm can maintain certain functionalities, it does not explore the possibility of the m…”
BackgroundMethodA UAS capability description framework: Reactive, adaptive, and cognitive capabilities in robotics
Visnevski, N. A., & Castillo‐Effen, M. (2009) · IEEE Aerospace Conference (AERO) · doi:10.1109/aero.2009.4839601 · Cited by 3
“In this section, we discuss the new and very promising direction in mobile robotics research introduced in [15] and [16].”
BackgroundBiologically Inspired Mobile Robot Control Robust to Hardware Failures and Sensor Noise
DallaLibera, F., Ikemoto, S., Minato, T., Ishiguro, H., Menegatti, E., & Pagello, E. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-20217-9_19 · Cited by 3
“Some advanced self-modeling techniques were presented [3] but they request intensive computation to estimate the current status of the robot from the sensor information.”
MethodCautionary Tales: Lessons Learned About Unanticipated Behaviors in OC Systems
Nelson, P. R., Nguyen, M. H., & Yang, C.-C. J. (2012) · Informatik-Spektrum · doi:10.1007/s00287-012-0596-5 · Cited by 3
“Continuous exploratory behavior and associated self-modeling has been demonstrated to enable a four-legged robot to generate qualitatively different alternative gaits when one leg is removed [6].”
Satellite attitude control through evolving a neural network
Li, S., Yuan, J., Luo, J., & Ma, W. (2010) · IEEE International Conference on Mechatronics and Automation (ICMA) · doi:10.1109/icma.2010.5588493 · Cited by 3
“Attributing to ODE's excellent properties on calculation speed and precision, it has been widely used for modeling and simulating evolvable robots [37][38].”
MethodToward Physically-Adaptive Computing
Zick, K. M., & Hayes, J. P. (2010) · IEEE International Conference on Self-Adaptive and Self-Organizing Systems (SASO) · doi:10.1109/saso.2010.13 · Cited by 3
“For instance, a study of self-modeling robotic systems deals with similar issues of sensing and adapting to a substrate prone to wearout/damage [17].”
BackgroundIida, F., & Bovet, S. (2009) · Springer eBooks · doi:10.1007/978-1-84882-530-7_2 · Cited by 3
“[16, 25, 26]) will clarify more general rules to manage the higher dimension of parameter space in self-organizing processes of embodied systems.”
BackgroundClark, A. (2008) · Oxford University Press eBooks · doi:10.1093/acprof:oso/9780195333213.003.0002 · Cited by 3
Evolving morphology automatically reformulates the problem of designing modular control
Bernatskiy, A., & Bongard, J. (2018) · Adaptive Behavior · doi:10.1177/1059712318762807 · Cited by 3
Self-citationFrom the Perspective of Artificial Intelligence: A New Approach to the Nature of Consciousness
Manzotti, R., & Jeschke, S. (2014) · INTERNATIONAL JOURNAL OF ADVANCED RESEARCH IN ARTIFICIAL INTELLIGENCE · doi:10.14569/ijarai.2014.031201 · Cited by 3
Past Visions of Artificial Futures:
Taylor, T., & Dorin, A. (2018) · Conference on Artificial Life (ALIFE) · doi:10.1162/isal_a_00022 · Cited by 3
“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).”
BackgroundBongard, J. (2023) · Artificial Life and Robotics · doi:10.1007/s10015-023-00872-0 · Cited by 3
“In an attempt to counteract the particular bias of assuming unchanging morphology but changing control policies, Victor Zykov, Hod Lipson, and I studied one form of structural change that is unavoidable for all robots: physical injury and wear and tear [4] (Fig.”
BackgroundSelf-citationIndirect Online Evolution – A Conceptual Framework for Adaptation in Industrial Robotic Systems
Furuholmen, M., Glette, K., Tørresen, J., & Hovin, M. E. (2008) · Lecture notes in computer science · doi:10.1007/978-3-540-85857-7_15 · Cited by 3
“The approach was further tested on a robot in [ 13 ] where it impressingly demonstrated the ability to recover from morphological change and infer updated self-models only after a few cycles.”
MethodLipson, H. (2017) · ACM SIGEVOlution · doi:10.1145/3129161.3129164 · Cited by 3
Self-citationContinuous Adaptation in Robotic Systems by Indirect Online Evolution
Furuholmen, M., Hovin, M. E., Tørresen, J., & Glette, K. (2008) · ECSIS Symposium on Learning and Adaptive Behaviors for Robotic Systems (LAB-RS) · doi:10.1109/lab-rs.2008.13 · Cited by 3
“The approach was further tested on a robot in [ 3 ] where it impressingly demonstrated the ability to recover from morphological change and infer updated self-models only after a few cycles.”
MethodStakeholder decision-making for radioactive waste management advice given in the US and UK
Lawless, W. F., Whitton, J., Poppeliers, C., & Abubucker, C. P. (2008) · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · Cited by 3
A group-theoretic approach to formalizing bootstrapping problems
Censi, A., & Murray, R. M. (2011) · CaltechAUTHORS (California Institute of Technology) · Cited by 3
Advances in evolutionary neural networks with applications in energy systems and the environment
Mason, K. (2018) · Arrow@dit (Dublin Institute of Technology) · doi:10.13025/17684 · Cited by 3
Moving Forward by Moving Backward: Embedding Action Impact over Action SemanticsPreprint
Zeng, K.-H., Weihs, L., Mottaghi, R., & Farhadi, A. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2304.12289 · Cited by 3
“Our paper shares similarities with the concept of System Identifica-tion (Verma et al., 2004; Bongard et al., 2006; Seegmiller et al., 2013; Cully et al., 2015; Banerjee et al., 2020; Lew et al., 2022).”
MethodPezzulo, G., & Levin, M. G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.08079 · Cited by 3
“…future – and, in parallel, richer models of the self, spanning multiple levels, from representations of bodily structure and internal dynamics to abstract, narrative models that support a continuous sense of identity across time [85,86] as well as models for cooperative social interaction [87–89].”
Efficient Morphology-Control Co-Design via Stackelberg Proximal Policy OptimizationPreprint
Dai, Y., Wang, Y., Ashley, D. R., & Schmidhuber, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.15388 · Cited by 3
“Agents optimized under this paradigm are typically more versatile, robust, and efficient than those optimized for only one aspect (Sims, 1994; Lipson & Pollack, 2000; Bongard et al., 2006; Kriegman et al., 2020).”
GeMuCo: Generalized Multisensory Correlational Model for Body Schema Learning
Kawaharazuka, K., Okada, K., & Inaba, M. (2024) · IEEE Robotics & Automation Magazine · doi:10.1109/mra.2024.3415111 · Cited by 2
“For Change Adaptability , existing methods rarely incorporate information about gradual model changes directly into the models [15], [16].”
MethodRodríguez, M., Urda, P., & Escalona, J. L. (2025) · Vehicle System Dynamics · doi:10.1080/00423114.2025.2516102 · Cited by 2
Behaviour Diversity in a Walking and Climbing Centipede-Like Virtual Creature
Norstein, E. S., Yasui, K., Kano, T., Ishiguro, A., & Glette, K. (2025) · Artificial Life · doi:10.1162/artl_a_00476 · Cited by 2
Leveraging Part‐Based NeRF for Robot Self‐Modeling and Control
Hu, K., Zhang, Y., Wu, Y., & Tan, N. (2025) · SmartBot · doi:10.1002/smb2.70005 · Cited by 2
Morphological Cognition: Classifying MNIST Digits Through Morphological Computation Alone
Mertan, A., & Cheney, N. (2025) · ALIFE · doi:10.1162/isal.a.892 · Cited by 2
“The following work investigates how the form of the morphology creates, affects, or facilitates behavior and how it can be optimized (Sims, 1994; Bongard and Pfeifer, 2002; Bongard et al., 2006).”
InfluentialSelf Model for Embodied Artificial Intelligence
Jiang, S.-Q., Zhang, S.-X., Tao, S.-D., Xi-hong, Z., Qi, T.-L., & Song, X. (2026) · Journal of Computer Science and Technology · doi:10.1007/s11390-026-6289-3 · Cited by 2
Solis, C. U., Morales, J., Montelongo-Vázquez, C. M., & Palomino-Reséndiz, S. I. (2026) · Technologies · doi:10.3390/technologies14060333 · Cited by 2
From bioinspired to biological robots, and back again.
Bongard, J. (2022) · IOP Conference Series Materials Science and Engineering · doi:10.1088/1757-899x/1261/1/012004 · Cited by 2
“As reported in [4], one way to accomplish this is to build and then update internal models before and after damage, and vet candidate control policies internally on self models before attempting them in reality, where inappropriate policies may cause further damage.”
BackgroundSelf-citationTrajectory Tracking Control of Robotic Manipulators by Multi-layer Neural Networks
Zhong, G., Li, Y., & Li, J. (2020) · IEEE Conference on Industrial Electronics and Applications (ICIEA) · doi:10.1109/iciea48937.2020.9248326 · Cited by 2
“In the context of robotic manipulators, they usually have complex dynamics that are also subject to uncertainties [2], [3], [4].”
BackgroundSurvivable Robotic Control through Guided Bayesian Policy Search with Deep Reinforcement Learning
Raza, S. J. A., Dastider, A., & Lin, M. (2021) · IEEE International Conference on Automation Science and Engineering (CASE) · doi:10.1109/case49439.2021.9551472 · Cited by 2
Morphology Choice Affects the Evolution of Affordance Detection in Robots
Pigozzi, F., Woodman, S. J., Medvet, E., Kramer-Bottiglio, R. K., & Bongard, J. (2023) · Genetic and Evolutionary Computation Conference (GECCO) · doi:10.1145/3583131.3590505 · Cited by 2
“Different communities developed different concepts and terminologies: self-modeling in robotics [2, 3, 6], world models [11] in machine learning, intrinsic motivation [27], empowerment [17] and information-driven measures [23] in the cognitive sciences.”
BackgroundSelf-citationTowards making computers conscious: trends and challenges
Patnaik, L. M. (2023) · Iran Journal of Computer Science · doi:10.1007/s42044-023-00164-7 · Cited by 2
Autonomous Mental Development at the Individual and Collective Levels: Concept and Challenges
Lippi, M., Mariani, S., Martinelli, M., & Zambonelli, F. (2024) · IEEE Access · doi:10.1109/access.2024.3522362 · Cited by 2
“Robotics is the area which first identified the profitability of building robots cables of autonomously building ‘‘by expe-rience’’ a model of their own capabilities and consequently learning to achieve specific goals [13], [78].”
Fault Recovery Through Online Adaptation of Boolean Network Robots
Baldini, P., Braccini, M., & Roli, A. (2025) · Sensors · doi:10.3390/s25185849 · Cited by 3
“In this line of research, previous works have considered the design of an internal state of the robot [9].”
Locomotion control for a modular snake robot over rough terrain
Ye, X., Niu, Y., Wang, H., & Meng, T. (2010) · Environmental Science and Information Application Technology · doi:10.1109/esiat.2010.5567368 · Cited by 2
“Snake’s creep is also very flexible, it has the capability of moving in some extreme environment that is narrow and full of obstacles [8].”
BackgroundZurn, J. B., Motai, Y., & Vento, S. (2011) · Robotica · doi:10.1017/s0263574711000580 · Cited by 2
“8 , 9 Another benefit is that we can learn a great deal about potential malfunction sources using this scheme.”
BackgroundSupercomputers: A Philosophical Perspective
Horne, J. (2015) · Advances in systems analysis, software engineering, and high performance computing book series · doi:10.4018/978-1-4666-7461-5.ch016 · Cited by 2
Middleware Support for Self-aware Computing Systems
Simonjan, J., Dieber, B., & Rinner, B. (2016) · Natural computing series · doi:10.1007/978-3-319-39675-0_11 · Cited by 2
Acting without Central Agent—Considerations for a Self-Model at the Cellular Level
Kippenberger, S., Kleemann, J., Kaufmann, R., & Meißner, M. (2017) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2017.00191 · Cited by 2
“A walking robot equipped with a self-model can compensate the shutdown of a limb by developing a new style of locomotion (Bongard et al., 2006).”
Body Self-Awareness for Social Robots
Rodríguez, I., Astigarraga, A., Ruiz, T., & Lazkano, E. (2017) · International Conference on Control, Artificial Intelligence, Robotics & Optimization (ICCAIRO) · doi:10.1109/iccairo.2017.23 · Cited by 2
“Several robotic systems can be considered as self-aware systems, able to recognize themselves in the mirror [10], able to be aware of their motion [14], or able to change their own models of their physical embodiment [4], to mention some.”
BackgroundSynthesizing Physically-Realistic Environmental Models from Robot Exploration
Bongard, J. (2007) · Springer eBooks · doi:10.1007/978-3-540-74913-4_81 · Cited by 2
“This finding supports the findings in [4], in which only two tilt sensors were used to indirectly recover the topology of a legged robot.”
BackgroundMethodResultInfluentialSelf-citationAdaptive Coupled Oscillators for Modular Robots
Hartono, P., & Nakane, A. (2011) · IEEJ Transactions on Electronics Information and Systems · doi:10.1541/ieejeiss.131.602 · Cited by 2
ROBUSTNESS OF GUIDED SELF-ORGANIZATION AGAINST SENSORIMOTOR DISRUPTIONS
Martius, G. (2013) · Advances in Complex Systems · doi:10.1142/s021952591350001x · Cited by 2
“An interesting study [2] achieved also a resilience to morphological changes by continuous self-modeling with a physics simulation as a highly specialized internal model.”
BackgroundHigh resilience in robotics with a multi-objective evolutionary algorithm
Koos, S., Cully, A., & Mouret, J.-B. (2013) · Genetic and Evolutionary Computation Conference Companion (GECCO Companion) · doi:10.1145/2464576.2464591 · Cited by 2
“[1] designed an algorithm for resilience that makes an important step in this direction.”
BackgroundMethodFrom the Perspective of Artificial Intelligence: A New Approach to the Nature of Consciousness
Manzotti, R., & Jeschke, S. (2016) · Springer eBooks · doi:10.1007/978-3-319-42620-4_41 · Cited by 2
“Putting it all together: According to [54], there are three motivations to pursue artificial consciousness [55] [56] [57]:”
BackgroundUsing simulation as an adaptive source of knowledge for the control of material handling systems
Klaas, A., Laroque, C., Renken, H., & Dangelmaier, W. (2016) · Journal of Simulation · doi:10.1057/jos.2015.26 · Cited by 2
“Another application with a simulation model to adapt strategies is the control of a four-legged robot (Bongard et al , 2006).”
MethodRobot body self-modeling algorithm: a collision-free motion planning approach for humanoids
Shoushtari, A. L. (2016) · SpringerPlus · doi:10.1186/s40064-016-2175-8 · Cited by 2
“The researchers have been designed a resilient robotic system which can adapt itself with changes in its hardware (for example due to the damage) by taking advantage of self-modeling ability (Bongard et al. 2006).”
BackgroundBuche, C., Bigot, N. L., & Polceanu, M. (2016) · Cognitive Systems Research · doi:10.1016/j.cogsys.2016.03.001 · Cited by 2
“The self (Kunze et al., 2011; Bongard et al., 2006; Dautenhahn & Nehaniv, 2002; Alissandrakis et al., 2002; Gray & Breazeal, 2005; Roy et al., 2004; Kennedy et al., 2008, 2009) 2 - Environmental Internal Simulation 2.1 - Virtual environment (Kunze et al., 2011; Polceanu & Buche, 2013b; Svensson et…”
BackgroundMethodInfluentialEvolving neural networks with multiple internal models
Ellefsen, K. O., & Tørresen, J. (2017) · European Conference on Artificial Life · doi:10.1162/isal_a_025 · Cited by 2
Evolving robot empathy towards humans with motor disabilities through artificial pain generation
Anshar, M., & Williams, M. (2018) · AIMS neuroscience · doi:10.3934/neuroscience.2018.1.56 · Cited by 2
Predicting the internal model of a robotic system from its morphology
Duran, A. J., & del Pobil, A. P. (2018) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2018.08.014 · Cited by 2
Objective versus Non-Objective Search in Evolving Morphologically Robust Robot Controllers
Putter, R., & Nitschke, G. (2018) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci.2018.8628627 · Cited by 2
“Specifically, collective robotic systems that must effectively adapt to unforseen morphological change, such as the loss or damage of sensors on one or more robots without significant task performance degradation [6], [7].”
BackgroundDamage Recovery for Simulated Modular Robots Through Joint Evolution of Morphologies and Controllers
Akrour, D., & Djedi, N. (2019) · Journal of Automation Mobile Robotics & Intelligent Systems · doi:10.14313/jamris_1-2019/2 · Cited by 2
“Building resilient robots capable of recovering from damages is a central and challenging question [1, 2].”
BackgroundMethodSim-to-Real: Designing Locomotion Controller for Six-Legged Robot
Yang, C., Gao, Y., Tian, C., & Yao, Q. (2019) · IEEE International Conference on Cyber Technology in Automation, Control, and Intelligent Systems · doi:10.1109/cyber46603.2019.9066720 · Cited by 2
“[21] [22] [23] [24] These approaches can be roughly divided into two classes.”
BackgroundEine notwendige Weiterentwicklung: Mind in Life, kausales Netzwerk, Embodiment
Henningsen, P. (2021) · Psychotherapie: Praxis · doi:10.1007/978-3-662-63324-3_3 · Cited by 2
(2023) · Frontiers research topics · doi:10.3389/978-2-8325-3343-7 · Cited by 2
Mechanism of Duration Perception in Artificial Brains Suggests New Model of Attentional Entrainment
Tehrani-Saleh, A., McAuley, J. D., & Adami, C. (2024) · Neural Computation · doi:10.1162/neco_a_01699 · Cited by 2
The multifunctionality of dreaming and the oblivious avatar : a commentary on Revonsuo & colleagues
Dresler, M. (2015) · Gutenberg Open Science · doi:10.25358/openscience-80 · 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.