mlsanityData to 7 Oct 2026

Robots that can adapt like animals

arXiv 1407.3501 ↗First posted 13 Jul 2014cs.RO cs.AI cs.LGcited by 203

Not on the map. Why?

Abstract (arXiv)

As robots leave the controlled environments of factories to autonomously function in more complex, natural environments, they will have to respond to the inevitable fact that they will become damaged. However, while animals can quickly adapt to a wide variety of injuries, current robots cannot "think outside the box" to find a compensatory behavior when damaged: they are limited to their pre-specified self-sensing abilities, can diagnose only anticipated failure modes, and require a pre-programmed contingency plan for every type of potential damage, an impracticality for complex robots. Here we introduce an intelligent trial and error algorithm that allows robots to adapt to damage in less than two minutes, without requiring self-diagnosis or pre-specified contingency plans. Before deployment, a robot exploits a novel algorithm to create a detailed map of the space of high-performing behaviors: This map represents the robot's intuitions about what behaviors it can perform and their value. If the robot is damaged, it uses these intuitions to guide a trial-and-error learning algorithm that conducts intelligent experiments to rapidly discover a compensatory behavior that works in spite of the damage. Experiments reveal successful adaptations for a legged robot injured in five different ways, including damaged, broken, and missing legs, and for a robotic arm with joints broken in 14 different ways. This new technique will enable more robust, effective, autonomous robots, and suggests principles that animals may use to adapt to injury.

Key facts. Cited by 203 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Jul 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 32; 2022: 42; 2023: 54; 2024: 24; 2025: 24; 2026: 27.

203 papers.

Sort:

By area:

  1. 2023Human-Timescale Adaptation in an Open-Ended Task Spacecited by 136
  2. 2022Walk These Ways: Tuning Robot Control for Generalization with Multiplicity of Behaviorcited by 113
  3. 2023Motif: Intrinsic Motivation from Artificial Intelligence Feedbackcited by 99
  4. 2024Evolutionary Computation in the Era of Large Language Model: Survey and Roadmapcited by 89
  5. 2023LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimizationcited by 86
  6. 2021Differentiable Quality Diversitycited by 71
  7. 2021Robot Learning from Randomized Simulations: A Reviewcited by 56
  8. 2022Deep Surrogate Assisted Generation of Environmentscited by 40
  9. 2021Modelling Behavioural Diversity for Learning in Open-Ended Gamescited by 39
  10. 2021On the Importance of Environments in Human-Robot Coordinationcited by 37
  11. 2021Hierarchical Few-Shot Imitation with Skill Transition Modelscited by 37
  12. 2022Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learningcited by 37
38 more
  1. 2023Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biasedcited by 37
  2. 2023Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learningcited by 36
  3. 2021Discovering Diverse Multi-Agent Strategic Behavior via Reward Randomizationcited by 35
  4. 2021Illuminating Diverse Neural Cellular Automata for Level Generationcited by 35
  5. 2022Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimalitycited by 35
  6. 2022Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learningcited by 32
  7. 2021Unsupervised Behaviour Discovery with Quality-Diversity Optimisationcited by 30
  8. 2023pyribs: A Bare-Bones Python Library for Quality Diversity Optimizationcited by 29
  9. 2021Human irrationality: both bad and good for reward inferencecited by 25
  10. 2021Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systemscited by 24
  11. 2022Covariance Matrix Adaptation MAP-Annealingcited by 24
  12. 2023Evolutionary Reinforcement Learning: A Surveycited by 24
  13. 2022Continuously Discovering Novel Strategies via Reward-Switching Policy Optimizationcited by 23
  14. 2022Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discoverycited by 23
  15. 2022Surrogate modeling for Bayesian optimization beyond a single Gaussian processcited by 22
  16. 2021Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolutioncited by 20
  17. 2021Dynamics-Aware Quality-Diversity for Efficient Learning of Skill Repertoirescited by 20
  18. 2023Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learningcited by 20
  19. 2021Discovering Diverse Solutions in Deep Reinforcement Learning by Maximizing State-Action-Based Mutual Informationcited by 18
  20. 2022Multi-Objective Quality Diversity Optimizationcited by 18
  21. 2023Generating Behaviorally Diverse Policies with Latent Diffusion Modelscited by 18
  22. 2023Multi-Robot Coordination and Layout Design for Automated Warehousingcited by 17
  23. 2023Curious Replay for Model-based Adaptationcited by 16
  24. 2023QDax: A Library for Quality-Diversity and Population-based Algorithms with Hardware Accelerationcited by 16
  25. 2023B2Opt: Learning to Optimize Black-box Optimization with Little Budgetcited by 15
  26. 2023Policy Space Diversity for Non-Transitive Gamescited by 15
  27. 2023Diversifying AI: Towards Creative Chess with AlphaZerocited by 15
  28. 2022Accelerated Quality-Diversity through Massive Parallelismcited by 14
  29. 2023Adaptive Coordination in Social Embodied Rearrangementcited by 14
  30. 2024Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Expertscited by 14
  31. 2021Sparse Reward Exploration via Novelty Search and Emitterscited by 13
  32. 2024Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Criticscited by 13
  33. 2022Heterogeneous Multi-agent Zero-Shot Coordination by Coevolutioncited by 12
  34. 2022Learning General World Models in a Handful of Reward-Free Deploymentscited by 12
  35. 2024CaDRE: Controllable and Diverse Generation of Safety-Critical Driving Scenarios using Real-World Trajectoriescited by 11
  36. 2022SafeAPT: Safe Simulation-to-Real Robot Learning using Diverse Policies Learned in Simulationcited by 10
  37. 2022PI-ARS: Accelerating Evolution-Learned Visual-Locomotion with Predictive Information Representationscited by 10
  38. 2022Training Diverse High-Dimensional Controllers by Scaling Covariance Matrix Adaptation MAP-Annealingcited by 10

50 most cited of 203 All 203 (JSON)