Review of Learning-Based Longitudinal Motion Planning for Autonomous Vehicles: Research Gaps Between Self-Driving and Traffic Congestion

Self-driving technology companies and the research community are accelerating the pace of use of machine learning longitudinal motion planning (mMP) for autonomous vehicles (AVs). This paper reviews the current state of the art in mMP, with an exclusive focus on its impact on traffic congestion. The paper identifies the availability of congestion scenarios in current datasets, and summarizes the required features for training mMP. For learning methods, the major methods in both imitation learning and non-imitation learning are surveyed. The emerging technologies adopted by some leading AV companies, such as Tesla, Waymo, and Comma.ai, are also highlighted. It is found that: (i) the AV industry has been mostly focusing on the long tail problem related to safety and has overlooked the impact on traffic congestion, (ii) the current public self-driving datasets have not included enough congestion scenarios, and mostly lack the necessary input features/output labels to train mMP, and (iii) although the reinforcement learning approach can integrate congestion mitigation into the learning goal, the major mMP method adopted by industry is still behavior cloning, whose capability to learn a congestion-mitigating mMP remains to be seen. Based on the review, the study identifies the research gaps in current mMP development. Some suggestions for congestion mitigation for future mMP studies are proposed: (i) enrich data collection to facilitate the congestion learning, (ii) incorporate non-imitation learning methods to combine traffic efficiency into a safety-oriented technical route, and (iii) integrate domain knowledge from the traditional car-following theory to improve the string stability of mMP.

Research Paper on Performance Analysis and Recommendations of Traffic Congestion Strategies in Cities of Haryana

This experimental study uses national regulations and survey reports to identify short, medium, and long-term traffic congestion strategies in Haryana's cities. The current study looked into a variety of successful road congestion mitigation techniques, ranging from expanded road capacity to the use of roadways, to see which ones were the most cost-effective. Using an examination of quantitative regression, interviews with transportation policy and decision makers, and alternate matrix criteria, I ranked each traffic congestion mitigation approach from least to most cost efficient based on three cost factors. I discovered that ramp measuring was both the most cost-effective and the most difficult method. Meanwhile, I discovered that expanding transit capacity was the least cost-effective of the solutions I looked into.

Joint Scheduling of Vessel Traffic and Pilots in Seaport Waters

In the busiest seaports, vessel traffic and vessel pilotage management play a crucial role in congestion mitigation. The management of vessel traffic and pilotage involves scheduling the vessels for sailing into and out of a seaport and scheduling the pilots for navigating the vessels in the port waters. In this paper, we study the integrated vessel traffic and pilot scheduling problem of a seaport. We manage the vessel traffic by optimizing the utilization of the navigation channels and the utilization of the anchorage areas in the terminal basin and incorporate the decision of pilot scheduling into the decision of vessel traffic management for congestion mitigation and vessel service enhancement. We formulate the problem on a time–space network with vessel- and pilot-dependent arc costs and develop an integer programming model that minimizes the sum of the berthing and departure tardiness cost of vessels, the cost of unsatisfied vessel service requests, and the pilot dispatching cost. For solving the model, we enumerate feasible vessel paths a priori and develop a Lagrangian relaxation algorithm that decomposes the problem into a vessel and pilot path assignment subproblems. Computational performance of the Lagrangian relaxation algorithm is tested on problem instances generated based on the physical layout and operational data of the Waigaoqiao Port in Shanghai.