Search Results

Connected and automated vehicles (CAVs) promise to reshape two areas of the mobility industry: the transportation and driving experience. The connected feature of the vehicle uses communication protocols to provide awareness of the surrounding world while the automated feature uses technology to minimize driver dependency. Constituting a subset of connected technologies, vehicle-to-infrastructure (V2I) technologies provide vehicles with real-time traffic light information, or Signal Phase and Timing (SPaT) data. In this paper, the vehicle and SPaT data are combined with a reinforcement learning (RL) method as an effort to minimize the vehicle’s energy consumption. Specifically, this paper explores the implementation of the deep deterministic policy gradient (DDPG) algorithm. As an off-policy approach, DDPG utilizes the maximum Q-value for the state regardless of the previous action performed.

A neural network-based computer vision system is developed to estimate position of an excavator manipulator in real time. A camera is used to capture images of a manipulator, and the images are down-sampled and used to train a neural network. Then, the trained neural network can estimate the position of the excavator manipulator in real time. To study the feasibility of the proposed system, a webcam is used to capture images of an excavator simulation model and the captured images are used to train a neural network. The simulation results show that the developed neural network-based computer vision system can estimate the position of the excavator manipulator with an acceptable accuracy.

This paper presents an application of artificial neural networks in adaptive helicopter hover training of novice student pilots. The design of the adaptive trainer utilizes the hypothesis that novices can be trained to fly a helicopter system automatically (with no human interaction) if the helicopter system adapts to the learning curve of the student. Two different techniques based on the above approach are presented. In the first technique, the helicopter system actively enforces optimality by augmenting the novice's control inputs by amounts necessary to satisfy desired performance criteria. The second technique uses relaxed performance criteria that are not initially optimal, but approach optimality in a graded fashion, based on the learning curve of the student. Adaptive neuro-controllers, together with a critic model, are used to implement the adaptive helicopter system.