mlsanityData to 7 Oct 2026

Learning from Demonstration via Spatiotemporal Tubes for Unknown Euler-Lagrange Systems

arXiv 2607.00534 ↗First posted 1 Jul 2026cs.RO cs.SY eess.SYcited by 0

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

Abstract (arXiv)

We present STT-LfD, a unified Learning from Demonstration (LfD) framework that integrates motion learning with control for unknown Euler-Lagrange systems. Unlike traditional decoupled approaches that track a fixed reference, the proposed method treats demonstrations as a data-driven safety specification. Using heteroscedastic Gaussian Processes, STT-LfD learns Spatiotemporal Tubes (STTs) as an intent envelope that capture time-varying precision requirements of a task. A closed-form feedback controller then enforces these learned constraints while respecting actuator limits, without requiring explicit system identification. The approach preserves the temporal structure of demonstrations, remains computationally efficient, and avoids explicit system identification. Hardware experiments on a mobile robot and a 7-DOF manipulator show that it outperforms baselines in robustness to disturbances and computational speed.

Key facts. No citing papers in the map yet (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 10 of its 23 references that are in the map. First posted on arXiv 1 Jul 2026.

Builds on

10 of 23 references.

Closest ancestors · 2

Same direction, newest first

  1. 2020Gaussian-Process-based Robot Learning from Demonstration23 Feb
  2. 2019Uncertainty-Aware Imitation Learning using Kernelized Movement Primitives5 Mar

Other references · 8

  1. 2020Learning Control Barrier Functions from Expert Demonstrationscited by 88
  2. 2022Interactive Imitation Learning in Robotics: A Surveycited by 51
  3. 2020Control Barrier Functions for Unknown Nonlinear Systems using Gaussian Processescited by 19
  4. 2023Learning Complex Motion Plans using Neural ODEs with Safety and Stability Guaranteescited by 8
  5. 2022Funnel Control Under Hard and Soft Output Constraints (extended version)cited by 1
  6. 2024Spatiotemporal Tubes for Temporal Reach-Avoid-Stay Tasks in Unknown Systemscited by 1
  7. 2025Safe and Stable Neural Network Dynamical Systems for Robot Motion Planningcited by 1
  8. 2025Real-Time Spatiotemporal Tubes for Dynamic Unsafe Setscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Guided Learning from Demonstration for Robust Transferability
  2. 2021Learning Forceful Manipulation Skills from Multi-modal Human Demonstrations
  3. 2026LOPAL: Local Performance-Aware Active Learning from Imperfect Demonstrations
  4. 2018Learning Constraints from Demonstrations
  5. 2025An Alignment-Based Approach to Learning Motions from Demonstrations
  6. 2021Learning from Successful and Failed Demonstrations via Optimization
  7. 2018Learning Generalizable Robot Skills from Demonstrations in Cluttered Environments
  8. 2018Auto-conditioned Recurrent Mixture Density Networks for Learning Generalizable Robot Skills