2026/02/07 by Armin Attarzadeh, Mohammad Ali Ghaemifar, Mohammadali Ghaemifar +2
Computer Science · Engineering · #Bounded function #Control theory (sociology) #Controller (irrigation) #Flexibility (engineering) #Joint (building) #Prosthetics and Rehabilitation Robotics #Reinforcement learning #Robot Manipulation and Learning #Stability (learning theory) #Teleoperation #Teleoperation and Haptic Systems #cs.SY #eess.SY
paper · pdf · doi:10.6084/m9.figshare.31287676
7 pages, 6 figures. Source code available at: https://github.com/ArminAttarzadeh/DRL-Controller-Gain-Tuner
openalex publication_date 2026/02/07 · openalex created_date 2026/02/08 · arxiv created 2026/08/04 · arxiv updated 2026/08/05 · openalex updated_date 2026/08/05
Bilateral teleoperation systems that include joint flexibility better reflect real robotic systems used in surgery, space, and rehabilitation. However, joint flexibility together with time-varying communication delays makes it difficult to maintain stable and coordinated motion between the master and slave robots. To address this, we propose a hybrid control method that combines a stable Proportional-plus-Damping (P+d) controller with a model-free deep reinforcement learning agent based on the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm. The P+d controller provides basic stability under bounded delays, while the learning agent adjusts and tunes the remote-side proportional and damping gains in real time to reduce vibrations and improve tracking. Stability is guaranteed for bounded time-varying delays using Lyapunov–Krasovskii analysis. The approach provides a practical solution for teleoperation systems facing both joint flexibility and uncertain network delays. Code is publicly available at github.com/ArminAttarzadeh/DRL-Controller-Gain-Tuner