mlsanityData to 14 Oct 2026

Cross-Platform Learnable Fuzzy Gain-Scheduled Proportional-Integral-Derivative Controller Tuning via Physics-Constrained Meta-Learning and Reinforcement Learning Adaptation

arXiv 2511.06500 ↗First posted 9 Nov 2025cs.ROcited by 0

On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control

Abstract (arXiv)

Motivation and gap: PID-family controllers remain a pragmatic choice for many robotic systems due to their simplicity and interpretability, but tuning stable, high-performing gains is time-consuming and typically non-transferable across robot morphologies, payloads, and deployment conditions. Fuzzy gain scheduling can provide interpretable online adjustment, yet its per-joint scaling and consequent parameters are platform-dependent and difficult to tune systematically. Proposed approach: We propose a hierarchical framework for cross-platform tuning of a learnable fuzzy gain-scheduled PID (LF-PID). The controller uses shared fuzzy membership partitions to preserve common error semantics, while learning per-joint scaling and Takagi-Sugeno consequent parameters that schedule PID gains online. Combined with physics-constrained virtual robot synthesis, meta-learning provides cross-platform initialization from robot physical features, and a lightweight reinforcement learning (RL) stage performs deployment-specific refinement under dynamics mismatch. Starting from three base simulated platforms, we generate 232 physically valid training variants via bounded perturbations of mass (+/-10%), inertia (+/-15%), and friction (+/-20%). Results and insight: We evaluate cross-platform generalization on two distinct systems (a 9-DOF serial manipulator and a 12-DOF quadruped) under multiple disturbance scenarios. The RL adaptation stage improves tracking performance on top of the meta-initialized controller, with up to 80.4% error reduction in challenging high-load joints (12.36 degrees to 2.42 degrees) and 19.2% improvement under parameter uncertainty. We further identify an optimization ceiling effect: online refinement yields substantial gains when the meta-initialized baseline exhibits localized deficiencies, but provides limited improvement when baseline quality is already uniformly strong.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods. Builds on 17 of its 55 references that are in the map. First posted on arXiv 9 Nov 2025.

Builds on

17 of 55 references.

References · 17

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,897
  3. 2015Continuous control with deep reinforcement learningcited by 3,407
  4. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,498
  5. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,204
  6. 2020Meta-Learning in Neural Networks: A Surveycited by 950
  7. 2018Learning Dexterous In-Hand Manipulationcited by 687
  8. 2017Sim-to-Real Transfer of Robotic Control with Dynamics Randomizationcited by 672
  9. 2021RMA: Rapid Motor Adaptation for Legged Robotscited by 508
  10. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 413
  11. 2018Sim-to-Real: Learning Agile Locomotion For Quadruped Robotscited by 319
  12. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 297
5 more
  1. 2017One-Shot Visual Imitation Learning via Meta-Learningcited by 228
  2. 2022Rapid Locomotion via Reinforcement Learningcited by 168
  3. 2015Safe Controller Optimization for Quadrotors with Gaussian Processescited by 78
  4. 2019A Novel Adaptive Controller for Robot Manipulators based on Active Inferencecited by 12
  5. 2025Disturbance-Aware Adaptive Compensation in Hybrid Force-Position Locomotion Policy for Legged Robotscited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Physics-Informed Policy Optimization via Analytic Dynamics Regularization
  2. 2025A Novel Multi-Timescale Stability-Preserving Hierarchical Reinforcement Learning Controller Framework for Adaptive Control in High-Dimensional Dynamical Systems
  3. 2025Rich State Observations Empower Reinforcement Learning to Surpass PID: A Drone Ball Balancing Study
  4. 2026Tune to Learn: How Controller Gains Shape Robot Policy Learning
  5. 2026Efficient Knowledge Transfer for Jump-Starting Control Policy Learning of Multirotors through Physics-Aware Neural Architectures
  6. 2026High-Precision Formation Control for Heterogeneous Multi-Robot Systems via Hierarchical Hybrid Physics-Informed Deep Reinforcement Learning
  7. 2026Meta-Learning for Rapid Adaptation in Reference Tracking of Uncertain Nonlinear Systems
  8. 2026PPO-EAL: Exact Augmented Lagrangian Proximal Policy Optimization for Safe Robotic Control