Hsi-Yuan Chen

Hsi-Yuan Chen, Zachary I. Bell, Patryk Deptula et al.

Autonomous agents are often tasked with operating in an area where feedback is unavailable. Inspired by such applications, this paper develops a novel switched systems-based control method for uncertain nonlinear systems with temporary loss of state feedback. To compensate for intermittent feedback, an observer is used while state feedback is available to reduce the estimation error, and a predictor is utilized to propagate the estimates while state feedback is unavailable. Based on the resulting subsystems, maximum and minimum dwell time conditions are developed via a Lyapunov-based switched systems analysis to relax the constraint of maintaining constant feedback. Using the dwell time conditions, a switching trajectory is developed to enter and exit the feedback denied region in a manner that ensures the overall switched system remains stable. A scheme for designing a switching trajectory with a smooth transition function is provided. Simulation and experimental results are presented to demonstrate the performance of control design.

Yanlin Zhou, Fan Lu, George Pu et al.

We propose a deep reinforcement learning (DRL) methodology for the tracking, obstacle avoidance, and formation control of nonholonomic robots. By separating vision-based control into a perception module and a controller module, we can train a DRL agent without sophisticated physics or 3D modeling. In addition, the modular framework averts daunting retrains of an image-to-action end-to-end neural network, and provides flexibility in transferring the controller to different robots. First, we train a convolutional neural network (CNN) to accurately localize in an indoor setting with dynamic foreground/background. Then, we design a new DRL algorithm named Momentum Policy Gradient (MPG) for continuous control tasks and prove its convergence. We also show that MPG is robust at tracking varying leader movements and can naturally be extended to problems of formation control. Leveraging reward shaping, features such as collision and obstacle avoidance can be easily integrated into a DRL controller.