Search

Since vehicles from multiple roads frequently merge at intersections, it formulates a typical traffic bottleneck of modern transportation systems. Proper vehicle coordination and motion plan at road intersections are of importance to guarantee safety as well as improving the traffic throughput, fuel efficiency and so on. In this paper, we try to present a general dedicated intersection coordination framework for autonomous vehicles, where both high- and low-level planners are appropriately designed and integrated. In the high-level planner, two different strategies are formulated to coordinate the autonomous vehicles to generate reference trajectories and feasible “tunnels”, respectively. Especially, a novel space-time-block based resource allocation scheme is presented to describe the feasible tunnels. Furthermore, to avoid collisions with unexpected obstacles such as pedestrians, bicycles or other vehicles with human drivers, a low-level planner is designed to generate practical trajectories based on the solutions from the high-level planner, according to their local on-board observations. Simulations and practical experiments are carried out, to show that our proposed coordination framework can achieve obvious performance advantages in various traffic metrics, including the throughput, fairness in driving maneuvers and driving comfort, etc. We also find that the high-level planner is effective in eliminating possible deadlocks among autonomous vehicles, which is rarely discussed in existing investigations. [ABSTRACT FROM AUTHOR]

In modern transportation systems, the road intersections where multiple roads merge usually become the traffic bottleneck. Existing coordination solutions such as the traffic signs tend to be ineffective. In order to exploit the full potential of the road infrastructure, we try to address the optimal vehicle coordination problem, by which the traffic throughput can be maximized. We first formulate it as a general centralized collision-free traffic scheduling framework. The involved vehicles could cooperate via instructions from the coordination center, by solving the essential non-convex coordination problem. Aiming at the dynamic arrival of vehicles, a corresponding coordination strategy is thus proposed to achieve better quality of service (QoS), including the traffic throughput, and delay. The queue stability on each road can be guaranteed according to the Rate Stability Theorem, and Lyapunov Theorem. We then try to extend the proposed intelligent coordination framework to the multi-collision-set one, by which the traffic throughput can be significantly improved. A spatial domain based solution is given to solve the multi-collision-set coordination problem. Due to the essential non-convex formulation, high accuracy linearization approximate algorithms are also provided. In the numerical results, we show the vehicle maneuvers, and statistical coordination time as the performance evaluation. They validate our analysis, and show the performance advantages achieved by the proposed framework. [ABSTRACT FROM AUTHOR]