基于改进人工势场的无人驾驶动态规划算法研究

无人驾驶决策算法可以分为端到端的决策算法与分层式决策算法，分层式算法由于可解释性强、鲁棒性高而被大多数主机厂采用。规划模块是分层式决策算法中的核心模块，它承接感知与地图模块的信息并输出驾驶轨迹或动作，而人工势场法由于规划效率高、信息提取能力强，被越来越多地应用于无人驾驶决策规划领域。但现阶段的人工势场存在未考虑目的地因素或建立目的地单点引力场导致远距离引力过大、方向错误的问题，无法应对复杂交通环境。针对这些问题，提出一种无人驾驶“行车意图-风险复合场”(Driving Intention & Risk Field, IRF)，根据目的地、车辆、道路边界等要素各自的特点分别建模，并以势场的形式统一在IRF中。创建考虑全局规划的全局引力场，将全局规划路径离散成等距离的路径点，并动态选取感兴趣范围内的路径点进行全局引力场的构建。为了验证模型的性能，搭建IRF-SAC动态规划算法平台，并在CARLA仿真环境分别设置高速公路场景、十字路口场景和环岛场景。研究结果表明:相比于NF-SAC和FSM，IRF-SAC算法在安全性、舒适性、通行效率上均有显著提升；在高速公路场景下，IRF-SAC显示出较强的路径跟踪精度和鲁棒性，最大位移偏差相对于NF-SAC和FSM算法分别下降了44.8%、70.2%；在十字路口场景下，与NF-SAC及FSM算法相比，平均危险系数分别降低12.0%、20.6%，纵向加速度均方根分别降低13.2%、44.9%，行驶时长相较于FSM算法减少了39.2%；在环岛场景下，与NF-SAC及FSM算法相比，平均危险系数分别降低了31.7%、52.9%，纵向加速度均方根分别降低了27.0%、19.0%。     

城市轨道交通列车追踪间隔与牵引能耗优化

针对城市轨道交通高峰小时列车密集追踪运行的特点，将降低列车牵引能耗和提升线路通过能力同时作为优化目标，研究列车运行操纵优化问题.给出移动闭塞条件下列车牵引能耗和最小追踪间隔的计算方式，考虑列车安全、正点运行约束，构建双目标优化模型. 结合 ε -约束法，提出一种基于动态规划的搜索算法求解模型.以亦庄线为优化算例，求解得到一组列车最优操纵Pareto解，体现两优化目标之间的均衡关系：列车进站过程采用两次制动操纵策略可有效压缩最小追踪间隔，为弥补两次制动过程额外消耗的运行时间，列车需付出更多的牵引能耗提升进站以前的运行速度以满足正点运行约束.     

基于遗传算法的远程鱼雷航路规划

简要介绍了远程鱼雷航路规划的基本含义及特性,根据威胁及障碍分布情况构造可能航行的航路集Voronoi图,采用遗传算法进行远程鱼雷航路优化选择。并对算法进行了相应的仿真,仿真结果表明,编码方式提高了优化效率,得到的航路有效地规避了威胁。     

Development of a signal-head-free intersection control logic in a fully connected and autonomous vehicle environment

Establishment of effective cooperation between vehicles and transportation infrastructure improves travel reliability in urban transportation networks. Lack of collaboration, however, exacerbates congestion due mainly to frequent stops at signalized intersections. It is beneficial to develop a control logic that collects basic safety message from approaching connected and autonomous vehicles and guarantees efficient intersection operations with safe and incident free vehicle maneuvers. In this paper, a signal-head-free intersection control logic is formulated into a dynamic programming model that aims to maximize the intersection throughput. A stochastic look-ahead technique is proposed based on Monte Carlo tree search algorithm to determine the near-optimal actions (i.e., acceleration rates) over time to prevent movement conflicts. Our numerical results confirm that the proposed technique can solve the problem efficiently and addresses the consequences of existing traffic signals. The proposed approach, while completely avoids incidents at intersections, significantly reduces travel time (ranging between 59.4% and 83.7% when compared to fixed-time and fully-actuated control strategies) at intersections under various demand patterns.     

A simple reservation and allocation model of shared parking lots

With increasing auto demands, efficient parking management is by no means less important than road traffic congestion control. This is due to shortages of parking spaces within the limited land areas of the city centers in many metropolises. The parking problem becomes an integrated part of traffic planning and management. On the other hand, it is a fact that many private parking spots are available during daytime in nearby residential compound because those residents drive their cars out to work. These temporarily vacant parking lots can be efficiently utilized to meet the parking demand of other drivers who are working at nearby locations or drivers who come for shopping or other activities. This paper proposes a framework and a simple model for embracing shared use of residential parking spaces between residents and public users. The proposed shared use is a winning strategy because it maximizes the use of private resources to benefit the community as a whole. It also creates a new business model enabled by the fast-growing mobile apps in our daily lives.     

Electric vehicle tour planning

This study extends the orienteering problem with time windows by considering electric vehicles (EV) with limited range. The model can simulate the change in the battery’s state of charge at each point along the routes, and thus can be used to solve the problem of EV tourist trip design with time windows. A land-sea integrated network for Penghu low-carbon islands was tested, and then the optimal green trip designs are obtained using a heuristic method. Some unique properties of the model are also discussed, as well as a number of management or planning implications.     

Coordinated platooning with multiple speeds

In a platoon, vehicles travel one after another with small intervehicle distances; trailing vehicles in a platoon save fuel because they experience less aerodynamic drag. This work presents a coordinated platooning model with multiple speed options that integrates scheduling, routing, speed selection, and platoon formation/dissolution in a mixed-integer linear program that minimizes the total fuel consumed by a set of vehicles while traveling between their respective origins and destinations. The performance of this model is numerically tested on a grid network and the Chicago-area highway network. We find that the fuel-savings factor of a multivehicle system significantly depends on the time each vehicle is allowed to stay in the network; this time affects vehicles’ available speed choices, possible routes, and the amount of time for coordinating platoon formation. For problem instances with a large number of vehicles, we propose and test a heuristic decomposed approach that applies a clustering algorithm to partition the set of vehicles and then routes each group separately. When the set of vehicles is large and the available computational time is small, the decomposed approach finds significantly better solutions than does the full model.     

An analysis of airport–airline vertical relationships with risk sharing contracts under asymmetric information structures

We analyze the double moral hazard problem at the joint venture type airport–airline vertical relationship, where two parties both contribute efforts to the joint venture but neither of them can see the other’s efforts. With the continuous-time stochastic dynamic programming model, we show that by the de-centralized utility maximizations of two parties under very strict conditions, i.e., optimal efforts’ cost being negligible and their risk averse parameters both asymptotically approaching to zero, the vertical contract could be agreed as the optimal sharing rule, which is the linear function of the final state with the slope being the product of their productivity difference and uncertainty (diffusion rate) level index.If both parties’ productivities are same, or the diffusion rate of the underlying process is unity, optimal linear sharing rule do not depend on the final state. If their conditions not dependent on final state are symmetric as well, then risk sharing disappears completely. In numerical examples, we illustrate the complex impact of uncertainty increase and end-of-period load factor improvement on the optimal sharing rule, and the relatively simple impact on total utility levels.     

An intermodal freight transport system for optimal supply chain logistics

Complexity in transport networks evokes the need for instant response to the changing dynamics and uncertainties in the upstream operations, where multiple modes of transport are often available, but rarely used in conjunction. This paper proposes a model for strategic transport planning involving a network wide intermodal transport system. The system determines the spatio-temporal states of road based freight networks (unimodal) and future traffic flow in definite time intervals. This information is processed to devise efficient scheduling plans by coordinating and connecting existing rail transport schedules to road based freight systems (intermodal). The traffic flow estimation is performed by kernel based support vector mechanisms while mixed integer programming (MIP) is used to optimize schedules for intermodal transport network by considering various costs and additional capacity constraints. The model has been successfully applied to an existing Fast Moving Consumer Goods (FMCG) distribution network in India with encouraging results.