Gaussian-Process-based Robot Learning from Demonstration
On the map: Offline RL and imitation learning from data → Robot learning from demonstration
Abstract (arXiv)
Endowed with higher levels of autonomy, robots are required to perform increasingly complex manipulation tasks. Learning from demonstration is arising as a promising paradigm for transferring skills to robots. It allows to implicitly learn task constraints from observing the motion executed by a human teacher, which can enable adaptive behavior. We present a novel Gaussian-Process-based learning from demonstration approach. This probabilistic representation allows to generalize over multiple demonstrations, and encode variability along the different phases of the task. In this paper, we address how Gaussian Processes can be used to effectively learn a policy from trajectories in task space. We also present a method to efficiently adapt the policy to fulfill new requirements, and to modulate the robot behavior as a function of task variability. This approach is illustrated through a real-world application using the TIAGo robot.
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Placed in Robot learning from demonstration, one of 13 directions in Offline RL and imitation learning from data. Builds on 8 of its 60 references that are in the map. First posted on arXiv 23 Feb 2020.
Builds on
8 of 60 references.
Closest ancestors · 3
Same direction, newest first
- 2019Learning from demonstration with model-based Gaussian process11 Oct
- 2019Towards Orientation Learning and Adaptation in Cartesian Space9 Jul
- 2019Uncertainty-Aware Imitation Learning using Kernelized Movement Primitives5 Mar
Other references · 5
- 2018When Gaussian Process Meets Big Data: A Review of Scalable GPscited by 205
- 2015Distributed Gaussian Processescited by 84
- 2017Kernelized Movement Primitivescited by 37
- 2019Bayesian Gaussian mixture model for robotic policy imitationcited by 8
- 2017Probabilistic Learning of Torque Controllers from Kinematic and Force Constraintscited by 7
Built on by
Citing papers per year: 2020: 1; 2021: 0; 2022: 0; 2023: 1; 2024: 1; 2025: 1; 2026: 1.
5 papers.
- 2023PUMA: Deep Metric Imitation Learning for Stable Motion Primitivescited by 3
- 2024Conditional Neural Expert Processes for Learning Movement Primitives from Demonstrationcited by 3
- 2025The Unreasonable Effectiveness of Discrete-Time Gaussian Process Mixtures for Robot Policy Learningcited by 3
- 2020Task-Adaptive Robot Learning from Demonstration with Gaussian Process Models under Replicationcited by 1
- 2026Learning from Demonstration via Spatiotemporal Tubes for Unknown Euler-Lagrange Systemscited by 0
- 2026Learning from Demonstration via Spatiotemporal Tubes for Unknown Euler-Lagrange Systems1 Jul 2026
- 2025The Unreasonable Effectiveness of Discrete-Time Gaussian Process Mixtures for Robot Policy Learning6 May 2025
- 2024Conditional Neural Expert Processes for Learning Movement Primitives from Demonstration13 Feb 2024
- 2023PUMA: Deep Metric Imitation Learning for Stable Motion Primitives19 Oct 2023
- 2020Task-Adaptive Robot Learning from Demonstration with Gaussian Process Models under Replication15 Oct 2020
Similar, not cited
Close in wording, no citation either way
- 2025Prompt2Auto: From Motion Prompt to Automated Control via Geometry-Invariant One-Shot Gaussian Process Learning
- 2025Generalizing Robot Trajectories from Single-Context Human Demonstrations: A Probabilistic Approach
- 2020Active Preference-Based Gaussian Process Regression for Reward Learning
- 2018Auto-conditioned Recurrent Mixture Density Networks for Learning Generalizable Robot Skills
- 2024Bayesian Optimization for Sample-Efficient Policy Improvement in Robotic Manipulation ↗
- 2021Robot Skill Adaptation via Soft Actor-Critic Gaussian Mixture Models
- 2023Keyframe Demonstration Seeded and Bayesian Optimized Policy Search
- 2024Learning Task Specifications from Demonstrations as Probabilistic Automata