Newest papers

Reinforced Iterative Learning Control for elastic joint arms: Guaranteed cross-trajectory generalization under model uncertainties

Y. de Santis, Michele Pierallini, Franco Angelini, Manolo Garabini · 2026 · Control Engineering Practice

DOI: 10.1016/j.conengprac.2026.107166 · cited by 0 works (OpenAlex) · open-access PDF

German

Trajectory-Tracking für konforme Roboter ist aufgrund von nichtlinearen Dynamiken und Modellierungsunsicherheiten herausfordernd, was oft Lernmethoden erfordert, um explizite Parameteridentifikation zu vermeiden. Iterative Learning Control (ILC) gewährleistet theoretisch hohe Präzision und behält die passive Konformität des Roboters. Jedoch erfordert die traditionelle ILC eine separate Lernphase für jede neue Trajectory. Umgekehrt generalisiert Reinforcement Learning (RL) zu neuen Trajectories, leidet jedoch praktisch unter hoher Probenkomplexität und begrenzter Tracking-Präzision.

Machine translation (Meta M2M100); the English original follows.

Abstract

Trajectory tracking for compliant robots is challenging due to nonlinear dynamics and modeling uncertainties, often requiring learning-based methods to avoid explicit parameter identification. Iterative Learning Control (ILC) ensures theoretically high precision and preserves the passive compliance of the robot. However, traditional ILC requires a separate learning phase for each new trajectory. Conversely, Reinforcement Learning (RL) generalizes to new trajectories, but practically suffers from high sample complexity and limited tracking precision. This work proposes Reinforced Iterative Lear

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Iterative learning control, Generalization, Control theory (sociology), Joint (building), Computer science, Control (management)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange