Trajectory Tracking
Trajectory tracking, the precise following of a predefined path by a system, is a crucial problem across robotics and autonomous systems, aiming to improve accuracy, robustness, and efficiency. Current research emphasizes developing advanced control strategies, such as nonlinear model predictive control (NMPC) and adaptive control methods, often integrated with machine learning techniques like deep reinforcement learning (DRL) and neural networks, to handle complex dynamics and uncertainties. These advancements are driving improvements in applications ranging from unmanned aerial vehicles (UAVs) and autonomous driving to soft robotics and assistive devices, impacting fields like precision agriculture, search and rescue, and healthcare.
Papers
Learning Optimal Control and Dynamical Structure of Global Trajectory Search Problems with Diffusion Models
Jannik Graebner, Anjian Li, Amlan Sinha, Ryne Beeson
Custom Non-Linear Model Predictive Control for Obstacle Avoidance in Indoor and Outdoor Environments
Lara Laban, Mariusz Wzorek, Piotr Rudol, Tommy Persson
Robust Generalized Proportional Integral Control for Trajectory Tracking of Soft Actuators in a Pediatric Wearable Assistive Device
Caio Mucchiani, Zhichao Liu, Ipsita Sahin, Elena Kokkoni, Konstantinos Karydis
Trajectory Tracking via Multiscale Continuous Attractor Networks
Therese Joseph, Tobias Fischer, Michael Milford