A smart solution such as connected transport can help ensure that logistics processes in the harbour run even more smoothly in the future. In connected transport, multiple trucks drive in a group. They are scheduled as a unit and drive at a good and safe distance from each other. The trucks are equipped with Adaptive Cruise Control (ACC), a system that maintains a constant speed and reduces speed automatically if a vehicle in front slows down. Each truck is also equipped with systems that can guide the entire convoy safely across intersections.
Existing inefficient traffic light control causes numerous problems, such as long delay and waste of energy. To improve efficiency, taking real-time traffic information as an input and dynamically adjusting the traffic light duration accordingly is a must. In terms of how to dynamically adjust traffic signals' duration, existing works either split the traffic signal into equal duration or extract limited traffic information from the real data. In this paper, we study how to decide the traffic signals' duration based on the collected data from different sensors and vehicular networks. We propose a deep reinforcement learning model to control the traffic light. In the model, we quantify the complex traffic scenario as states by collecting data and dividing the whole intersection into small grids. The timing changes of a traffic light are the actions, which are modeled as a high-dimension Markov decision process. The reward is the cumulative waiting time difference between two cycles. To solve the model, a convolutional neural network is employed to map the states to rewards. The proposed model is composed of several components to improve the performance, such as dueling network, target network, double Q-learning network, and prioritized experience replay. We evaluate our model via simulation in the Simulation of Urban MObility (SUMO) in a vehicular network, and the simulation results show the efficiency of our model in controlling traffic lights.
I recently had the opportunity to take a ride in a Waymo self-driving car in Chandler, AZ. I had been looking forward to this experience, not only to see how well the technology worked but also what the experience might be like as a passenger. Upon my arrival at the Waymo facility, I had apparently approached the side of the building where the Waymo cars go at the end of their duty cycles to be refueled and inspected. As I drove in, I was more or less surrounded by incoming Waymo vehicles. I relaxed as they navigated their way around me.
When autonomous vehicles are powered by artificial intelligence engines, individuals traveling to or from the world's busiest airports will no longer experience uncertainty. Jen-Hsun Huang, CEO of Nvidia, recently told the WSJDLive Conference that he would like his car to not just drive him to work, but to recognize who he is, set up his conference calls, and handle just about all the functions of a personal assistant. In the near future, personal artificial intelligence engines will read your emails, create travel itineraries, and summon your autonomous vehicle--all without you having to ask. This knowledge, combined with real-time traffic and route data, will allow your personal artificial intelligence engine to pre-summon an autonomous vehicle for your journey to ensure that you arrive on time. In particular, with the introduction of personal artificial intelligence (A.I.) engines and on-demand autonomous vehicles, the uncertainty of traveling to and from major international airports will be eliminated, and travelers will experience effortless commutes.
About 50,000 people are expected to walk across the new Queensferry Crossing this weekend. The new road bridge over the Forth has been closed to traffic in preparation for the official opening ceremony on Monday. The chance to walk the £1.35bn bridge has been described as a "once in a lifetime" experience. The new crossing has no pedestrian walkway. The ballot to choose those taking part attracted 250,000 entries.