A Robust Task-Level Control Architecture for Learned Dynamical Systems
On the map: Offline RL and imitation learning from data → Robot learning from demonstration
Abstract (arXiv)
Dynamical system (DS)-based learning from demonstration (LfD) is a powerful tool for generating motion plans in the operation ('task') space of robotic systems. However, realizing generated motion plans is often compromised by a "task-execution mismatch", where unmodeled dynamics, persistent disturbances, and system latency cause the robot's task-space state to diverge from the desired state. We propose a novel task-level robust control architecture, L1-augmented Dynamical Systems (L1-DS), that explicitly handles the task-execution mismatch in tracking a nominal motion plan generated by any DS-based LfD scheme. Our framework augments any DS-based LfD model with a nominal stabilizing controller and an L1 adaptive controller. Furthermore, we introduce a windowed Dynamic Time Warping (DTW)-based target selector, which enables the nominal stabilizing controller to handle temporal misalignment for improved phase-consistent tracking. We demonstrate the efficacy of our architecture on the LASA and IROS handwriting datasets.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Robot learning from demonstration, one of 13 directions in Offline RL and imitation learning from data. Builds on 16 of its 50 references that are in the map. First posted on arXiv 12 Nov 2025.
Builds on
16 of 50 references.
Closest ancestors · 1
Same direction, newest first
Other references · 15
- 2019Control Barrier Functions: Theory and Applicationscited by 372
- 2021Dynamic Movement Primitives in Robotics: A Tutorial Surveycited by 47
- 2021Hamiltonian-based Neural ODE Networks on the SE(3) Manifold For Dynamics Learning and Controlcited by 38
- 2020ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flowscited by 33
- 2020Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systemscited by 32
- 2020Learning Barrier Functions for Constrained Motion Planning with Dynamical Systemscited by 17
- 2022Learning Riemannian Stable Dynamical Systems via Diffeomorphismscited by 17
- 2020L1-Adaptive MPPI Architecture for Robust and Agile Control of Multirotorscited by 14
- 2023Learning Complex Motion Plans using Neural ODEs with Safety and Stability Guaranteescited by 8
- 2024Learning Deep Dynamical Systems using Stable Neural ODEscited by 8
- 2020An Energy-based Approach to Ensure the Stability of Learned Dynamical Systemscited by 7
- 2023Learning Lyapunov-Stable Polynomial Dynamical Systems through Imitationcited by 4
3 more
- 2015The sensorimotor loop as a dynamical system: How regular motion primitives may emerge from self-organized limit cyclescited by 1
- 2024Adaptive Robust Controller for handling Unknown Uncertainty of Robotic Manipulatorscited by 1
- 2025Humanoid Robot Acrobatics Utilizing Complete Articulated Rigid Body Dynamicscited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024A context-adaptive policy framework for robust and reactive robotic manipulation via uncertainty-aware imitation learning
- 2024Safe Execution of Learned Orientation Skills with Conic Control Barrier Functions
- 2024Fusion Dynamical Systems with Machine Learning in Imitation Learning: A Comprehensive Overview
- 2024An Adaptive Framework for Manipulator Skill Reproduction in Dynamic Environments ↗
- 2024Learning from Demonstration with Implicit Nonlinear Dynamics Models
- 2026Learning from Demonstrations meets Symbolic Control - A Supervisory Control Architecture for Formal Certification of Learned Motion
- 2025Scalable Learning of High-Dimensional Demonstrations with Composition of Linear Parameter Varying Dynamical Systems
- 2024Stabilizing Dynamic Systems through Neural Network Learning: A Robust Approach ↗