mlsanityData to 7 Oct 2026

TamedPUMA: safe and stable imitation learning with geometric fabrics

arXiv 2503.17432 ↗First posted 21 Mar 2025eess.SY cs.LG cs.ROcited by 0

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

Abstract (arXiv)

Using the language of dynamical systems, Imitation learning (IL) provides an intuitive and effective way of teaching stable task-space motions to robots with goal convergence. Yet, IL techniques are affected by serious limitations when it comes to ensuring safety and fulfillment of physical constraints. With this work, we solve this challenge via TamedPUMA, an IL algorithm augmented with a recent development in motion generation called geometric fabrics. As both the IL policy and geometric fabrics describe motions as artificial second-order dynamical systems, we propose two variations where IL provides a navigation policy for geometric fabrics. The result is a stable imitation learning strategy within which we can seamlessly blend geometrical constraints like collision avoidance and joint limits. Beyond providing a theoretical analysis, we demonstrate TamedPUMA with simulated and real-world tasks, including a 7-DoF manipulator.

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 23 of its 43 references that are in the map. First posted on arXiv 21 Mar 2025.

Builds on

23 of 43 references.

References · 23

  1. 2018An Algorithmic Perspective on Imitation Learningcited by 455
  2. 2018Riemannian Motion Policiescited by 45
  3. 2020ImitationFlow: Learning Deep Stable Stochastic Dynamic Systems by Normalizing Flowscited by 33
  4. 2020Euclideanizing Flows: Diffeomorphic Reduction for Learning Stable Dynamical Systemscited by 32
  5. 2022Learning Model Predictive Controllers with Real-Time Attention for Real-World Navigationcited by 27
  6. 2022ProDMPs: A Unified Perspective on Dynamic and Probabilistic Movement Primitivescited by 25
  7. 2019Bayesian Optimization Meets Riemannian Manifolds in Robot Learningcited by 23
  8. 2024Neural Contractive Dynamical Systemscited by 14
  9. 2022Learning Stable Robotic Skills on Riemannian Manifoldscited by 10
  10. 2020Geometric Fabrics for the Acceleration-based Design of Robotic Motioncited by 7
  11. 2022Model Predictive Control via On-Policy Imitation Learningcited by 6
  12. 2023Efficient Deep Learning of Robust Policies from MPC using Imitation and Tube-Guided Data Augmentationcited by 6
11 more
  1. 2020Optimization Fabricscited by 4
  2. 2021CollisionIK: A Per-Instant Pose Optimization Method for Generating Robot Motions with Environment Collision Avoidancecited by 4
  3. 2023Deep Probabilistic Movement Primitives with a Bayesian Aggregatorcited by 4
  4. 2023PUMA: Deep Metric Imitation Learning for Stable Motion Primitivescited by 3
  5. 2024Fusion Dynamical Systems with Machine Learning in Imitation Learning: A Comprehensive Overviewcited by 3
  6. 2024Geometric Fabrics: a Safe Guiding Medium for Policy Learningcited by 3
  7. 2022Dynamic Optimization Fabrics for Motion Generationcited by 2
  8. 2022A Riemannian Take on Human Motion Analysis and Retargetingcited by 2
  9. 2023Avoidance of Concave Obstacles through Rotation of Nonlinear Dynamicscited by 2
  10. 2021Imitation Learning via Simultaneous Optimization of Policies and Auxiliary Trajectoriescited by 1
  11. 2023Fabrics: A Foundationally Stable Medium for Encoding Prior Experiencecited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Learning Lyapunov-Stable Polynomial Dynamical Systems through Imitation
  2. 2025Elastic Motion Policy: An Adaptive Dynamical System for Robust and Efficient One-Shot Imitation Learning
  3. 2024Globally Stable Neural Imitation Policies
  4. 202423 DoF Grasping Policies from a Raw Point Cloud ↗
  5. 2023End-to-End Stable Imitation Learning via Autonomous Neural Dynamic Policies
  6. 2026Surface Constraint Policy for Learning Surface-Constrained and Dynamically Feasible Robot Skills
  7. 2022A Unified Formulation of Geometry-aware Dynamic Movement Primitives
  8. 2022Generating Stable and Collision-Free Policies through Lyapunov Function Learning