mlsanityData to 7 Oct 2026

Robot learning from demonstration

139 papers0 this weekHigh confidence in this grouping: the papers form one clear topicHigh confidence in this grouping: the papers form one clear topic · About

Keywords: demonstration, lfd, demonstrations, learning demonstration, robot

Key facts. Robot learning from demonstration: 139 papers on arXiv since 2018 (data through 7 Oct 2026). 4 of its 139 mapped papers (3%) cite “Uncertainty-Aware Imitation Learning using Kernelized Movement Primitives” (2019, arXiv 1903.02114). 4 of its 139 mapped papers (3%) cite “Towards Orientation Learning and Adaptation in Cartesian Space” (2019, arXiv 1907.03918). 1 new paper 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

1 new since 17 Sep

  1. Learning Geometry-Aware Virtual Fixtures From Sparse Demonstrations

Foundations

Most cited by papers here

  1. Uncertainty-Aware Imitation Learning using Kernelized Movement Primitives2019cited by 4 here
  2. Towards Orientation Learning and Adaptation in Cartesian Space2019cited by 4 here
  3. Benchmark for Skill Learning from Demonstration: Impact of User Experience, Task Complexity, and Start Configuration on Performance2019cited by 3 here
  4. A Linearly Constrained Nonparametric Framework for Imitation Learning2019cited by 2 here
  5. Gaussian-Process-based Robot Learning from Demonstration2020cited by 2 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2018An Algorithmic Perspective on Imitation Learningcited by 6 here
  2. 2019Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observationscited by 2 here
  3. 2019Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrationscited by 2 here
  4. 2021Confidence-Aware Imitation Learning from Demonstrations with Varying Optimalitycited by 2 here
20 more it builds on, not in this chain
  1. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 2 here
  2. 2018Behavioral Cloning from Observationcited by 2 here
  3. 2018HG-DAgger: Interactive Imitation Learning with Human Expertscited by 2 here
  4. 2019Uncertainty-Aware Imitation Learning using Kernelized Movement Primitivescited by 4 here
  5. 2019Towards Orientation Learning and Adaptation in Cartesian Spacecited by 4 here
  6. 2019A Linearly Constrained Nonparametric Framework for Imitation Learningcited by 2 here
  7. 2019Benchmark for Skill Learning from Demonstration: Impact of User Experience, Task Complexity, and Start Configuration on Performancecited by 3 here
  8. 2020Gaussian-Process-based Robot Learning from Demonstrationcited by 2 here
  9. 2020Learning Control Barrier Functions from Expert Demonstrationscited by 2 here
  10. 2020Learning from Suboptimal Demonstration via Self-Supervised Reward Regressioncited by 2 here
  11. 2020Model-Based Inverse Reinforcement Learning from Visual Demonstrationscited by 2 here
  12. 2021CRIL: Continual Robot Imitation Learning via Generative and Prediction Modelcited by 2 here
  13. 2021Learning from Successful and Failed Demonstrations via Optimizationcited by 2 here
  14. 2021What Matters in Learning from Offline Human Demonstrations for Robot Manipulationcited by 2 here
  15. 2021Similarity-Aware Skill Reproduction based on Multi-Representational Learning from Demonstrationcited by 2 here
  16. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 3 here
  17. 2022Continual Learning from Demonstration of Robotics Skillscited by 2 here
  18. 2022Quantifying Demonstration Quality for Robot Learning and Generalizationcited by 2 here
  19. 2022Interactive Imitation Learning in Robotics: A Surveycited by 2 here
  20. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 2 here

The 24 most cited of 100.

Browse

30 of 139, ranked 6–35

  1. 6Continual Learning from Demonstration of Robotics Skills20222
  2. 7Quantifying Demonstration Quality for Robot Learning and Generalization20222
  3. 8Learning from Successful and Failed Demonstrations via Optimization20212
  4. 9Similarity-Aware Skill Reproduction based on Multi-Representational Learning from Demonstration20212
  5. 10Learning from Suboptimal Demonstration via Self-Supervised Reward Regression20202
  6. 11Conditional Neural Expert Processes for Learning Movement Primitives from Demonstration20241
  7. 12Arc-Length-Based Warping for Robot Skill Synthesis from Multiple Demonstrations20241
  8. 13A Survey of Demonstration Learning20231
  9. 14Learning from Few Demonstrations with Frame-Weighted Motion Generation20231
  10. 15Programming-by-Demonstration for Long-Horizon Robot Tasks20231
All 30
  1. 16Task Generalization with Stability Guarantees via Elastic Dynamical System Motion Policies20231
  2. 17Scalable and Efficient Continual Learning from Demonstration via a Hypernetwork-generated Stable Dynamics Model20231
  3. 18Temporal Logic Imitation: Learning Plan-Satisficing Motion Policies from Demonstrations20221
  4. 19Learning from Demonstrations using Signal Temporal Logic20211
  5. 20Learning Forceful Manipulation Skills from Multi-modal Human Demonstrations20211
  6. 21Elaborating on Learned Demonstrations with Temporal Logic Specifications20201
  7. 22Learning from demonstration using products of experts: applications to manipulation and task prioritization20201
  8. 23Towards open and expandable cognitive AI architectures for large-scale multi-agent human-robot collaborative learning20201
  9. 24Extending Policy from One-Shot Learning through Coaching20191
  10. 25Disentangled Relational Representations for Explaining and Learning from Demonstration20191
  11. 26Learning from demonstration with model-based Gaussian process20191
  12. 27A Dataset Schema for Cooperative Learning from Demonstration in Multi-robots Systems20191
  13. 28Imitation learning-based framework for learning 6-D linear compliant motions20181
  14. 29Imitating Human Search Strategies for Assembly20181
  15. 30Learning specifications for reactive synthesis with safety constraints20260
  16. 31GraSP-STL: A Graph-Based Framework for Zero-Shot Signal Temporal Logic Planning via Offline Goal-Conditioned Reinforcement Learning20260
  17. 32Optimizing Neurorobot Policy under Limited Demonstration Data through Preference Regret20260
  18. 33From a Single Demonstration to a General Policy for Contact-Rich Manipulation20260
  19. 34Surface Constraint Policy for Learning Surface-Constrained and Dynamically Feasible Robot Skills20260
  20. 35LOPAL: Local Performance-Aware Active Learning from Imperfect Demonstrations20260