mlsanityData to 7 Oct 2026

Task Generalization with Stability Guarantees via Elastic Dynamical System Motion Policies

arXiv 2309.01884 ↗First posted 5 Sep 2023cs.RO cs.LG cs.SYcited by 10

On the map: Offline RL and imitation learning from data → Robot learning from demonstration

Abstract (arXiv)

Dynamical System (DS) based Learning from Demonstration (LfD) allows learning of reactive motion policies with stability and convergence guarantees from a few trajectories. Yet, current DS learning techniques lack the flexibility to generalize to new task instances as they ignore explicit task parameters that inherently change the underlying trajectories. In this work, we propose Elastic-DS, a novel DS learning, and generalization approach that embeds task parameters into the Gaussian Mixture Model (GMM) based Linear Parameter Varying (LPV) DS formulation. Central to our approach is the Elastic-GMM, a GMM constrained to SE(3) task-relevant frames. Given a new task instance/context, the Elastic-GMM is transformed with Laplacian Editing and used to re-estimate the LPV-DS policy. Elastic-DS is compositional in nature and can be used to construct flexible multi-step tasks. We showcase its strength on a myriad of simulated and real-robot experiments while preserving desirable control-theoretic guarantees. Supplementary videos can be found at https://sites.google.com/view/elastic-ds

Key facts. Cited by 10 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 19 of its 63 references that are in the map. First posted on arXiv 5 Sep 2023.

Builds on

19 of 63 references.

Closest ancestors · 1

Same direction, newest first

  1. 2022Temporal Logic Imitation: Learning Plan-Satisficing Motion Policies from Demonstrations9 Jun

Other references · 18

  1. 2023Segment Anythingcited by 8,158
  2. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  3. 2016Generative Adversarial Imitation Learningcited by 1,576
  4. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 517
  5. 2018An Algorithmic Perspective on Imitation Learningcited by 455
  6. 2017One-Shot Visual Imitation Learning via Meta-Learningcited by 225
  7. 2018Task-Free Continual Learningcited by 219
  8. 2017Vision-Based Multi-Task Manipulation for Inexpensive Robots Using End-To-End Learning from Demonstrationcited by 100
  9. 2021BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D Modelscited by 87
  10. 2021Bridging Multi-Task Learning and Meta-Learning: Towards Efficient Training and Effective Adaptationcited by 50
  11. 2022PaCo: Parameter-Compositional Multi-Task Reinforcement Learningcited by 40
  12. 2022Modular Lifelong Reinforcement Learning via Neural Compositioncited by 39
6 more
  1. 2018K for the Price of 1: Parameter-efficient Multi-task and Transfer Learningcited by 34
  2. 2022TaSIL: Taylor Series Imitation Learningcited by 21
  3. 2021Learning Stable Vector Fields on Lie Groupscited by 12
  4. 2022Learning Task-Parameterized Skills from Few Demonstrationscited by 8
  5. 2020The State of Industrial Robotics: Emerging Technologies, Challenges, and Key Research Directionscited by 7
  6. 2022Inferring Versatile Behavior from Demonstrations by Matching Geometric Descriptorscited by 6

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3; 2025: 6.

10 papers.

  1. 2023Transfer Learning in Robotics: An Upcoming Breakthrough? A Review of Promises and Challengescited by 17
  2. 2024The Art of Imitation: Learning Long-Horizon Manipulation Tasks from Few Demonstrationscited by 9
  3. 2025Elastic Motion Policy: An Adaptive Dynamical System for Robust and Efficient One-Shot Imitation Learningcited by 4
  4. 2025The Unreasonable Effectiveness of Discrete-Time Gaussian Process Mixtures for Robot Policy Learningcited by 3
  5. 2024Distributionally Robust Policy and Lyapunov-Certificate Learningcited by 2
  6. 2025Flow with the Force Field: Learning 3D Compliant Flow Matching Policies from Force and Demonstration-Guided Simulation Datacited by 2
  7. 2025Trajectory Adaptation using Large Language Modelscited by 1
  8. 2025KoopMotion: Learning Almost Divergence Free Koopman Flow Fields for Motion Planningcited by 1
  9. 2024A context-adaptive policy framework for robust and reactive robotic manipulation via uncertainty-aware imitation learningcited by 0
  10. 2025A Robust Task-Level Control Architecture for Learned Dynamical Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Generalizing Robot Trajectories from Single-Context Human Demonstrations: A Probabilistic Approach
  2. 2025Scalable Learning of High-Dimensional Demonstrations with Composition of Linear Parameter Varying Dynamical Systems
  3. 2026SPECTRA: Context-Conditioned Spectral Movement Primitives for Robot Skill Generalization
  4. 2024An Adaptive Framework for Manipulator Skill Reproduction in Dynamic Environments ↗
  5. 2018Auto-conditioned Recurrent Mixture Density Networks for Learning Generalizable Robot Skills
  6. 2023Learning Lyapunov-Stable Polynomial Dynamical Systems through Imitation
  7. 2024Fusion Dynamical Systems with Machine Learning in Imitation Learning: A Comprehensive Overview
  8. 2021Robot Skill Adaptation via Soft Actor-Critic Gaussian Mixture Models