Managing Autonomous Mobility on Demand Systems for Better Passenger Experience
University of California, Irvine(加州大学尔湾分校)
Wen Shen, Cristina Lopes
发表信息:
Proceedings of the 18th International Conference on Principles and Practice of Multi-Agent Systems (PRIMA 2015). pp 20-35. Lecture Notes in Computer Science, vol 9387. Springer
Autonomous mobility on demand systems, though still in their infancy, have very promising prospects in providing urban population with sustainable and safe personal mobility in the near future. While much research has been conducted on both autonomous vehicles and mobility on demand systems, to the best of our knowledge, this is the first work that shows how to manage autonomous mobility on demand systems for better passenger experience. We introduce the Expand and Target algorithm which can be easily integrated with three different scheduling strategies for dispatching autonomous vehicles. We implement an agent-based simulation platform and empirically evaluate the proposed approaches with the New York City taxi data. Experimental results demonstrate that the algorithm significantly improve passengers' experience by reducing the average passenger waiting time by up to 29.82% and increasing the trip success rate by up to 7.65%.
Passenger Mobility Prediction via Representation Learning for Dynamic Directed and Weighted Graph
Beihang University(北京航空航天大学);The University of Queensland(昆士兰大学);Didichuxing(滴滴出行);University of Leeds(利兹大学)
近年来,乘车服务越来越普遍,因为它们为乘客提供了巨大的便利。作为一个基本问题,及时预测不同地区的乘客需求对于有效的交通流控制和路线规划至关重要。由于空间和时间模式都是不可或缺的乘客需求预测,相关研究已经从纯时间序列发展到用于建模历史乘客需求数据的图结构数据,其中通过经由不同关系边(例如,起点-目的地关系、地理距离等)。因此,时空乘客需求记录自然地在构造的图中携带动态模式,其中边还编码关于方向和体积的重要信息(即,两个连接区域之间的乘客需求的权重)。然而,现有的基于图的解决方案未能同时考虑动态、有向和加权(DDW)图的这三个关键方面,导致在学习用于乘客需求预测的图表示时表现力有限。因此,我们提出了一种新的时空图注意力网络,即Gallat(Graph prediction with all attention)作为解决方案。在Gallat中,通过全面结合DDW图的这三个内在属性,我们构建了三个注意力层,以充分捕获所有历史时隙中不同区域之间的时空依赖关系。此外,该模型采用一个子任务进行预训练,使其能够更快地获得准确的结果。我们在真实世界的数据集上评估了所提出的模型,我们的实验结果表明,Gallat优于最先进的方法。
Real-Time Communication-Aware Ride-Sharing Route Planning for Urban Air Mobility: A Multi-Source Hybrid Attention Reinforcement Learning Approach
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen(科学与工程学院,香港中文大学(深圳));Xidian University State Key Laboratory of Integrated Services Network(西安电子科技大学集成服务网络国家重点实验室);Department of Computer Science and Engineering, Kyung Hee University(庆北大学计算机科学与工程系)
Heterogeneous Vertiport Selection Optimization for On-Demand Air Taxi Services: A Deep Reinforcement Learning Approach
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen(香港中文大学(深圳)科学与工程学院);Shanghai AI Laboratory(上海人工智能实验室);State Key Laboratory of Integrated Services Networks, Xidian University(西安电子科技大学集成服务网络国家重点实验室);Nokia Bell Labs(诺基亚贝尔实验室)