Search for: All records

Traffic congestion results from the spatio-temporal imbalance of demand and supply. With the advances in connected technologies, incentive mechanisms for collaborative routing have the potential to provide behavior-consistent solutions to traffic congestion. However, such mechanisms raise privacy concerns due to their information-sharing and execution-validation procedures. This study leverages secure Multi-party Computation (MPC) and blockchain technologies to propose a privacy-preserving incentive mechanism for collaborative routing in a vehicle-to-everything (V2X) context, which consists of a collaborative routing scheme and a route validation scheme. In the collaborative routing scheme, sensitive information is shared through an off-chain MPC protocol for route updating and incentive computation. The incentives are then temporarily frozen in a series of cascading multi-signature wallets in case vehicles behave dishonestly or roadside units (RSUs) are hacked. The route validation scheme requires vehicles to create position proofs at checkpoints along their selected routes with the assistance of witness vehicles using an off-chain threshold signature protocol. RSUs will validate the position proofs, store them on the blockchain, and unfreeze the associated incentives. The privacy and security analysis illustrates the scheme’s efficacy. Numerical studies reveal that the proposed incentive mechanism with tuned parameters is both efficient and implementable. 

Smart cities seek to leverage data from advanced information, communication, and sensor technologies (ICSTs) for achieving their transportation-related sustainability goals. However, the multi-source, multi-timescale nature of these disparate data sets introduces many challenges to community decision-makers, hindering the use of these technologies in an efficient, effective, and holistic manner. Here, using statistical and machine learning methods, we present a visualization platform developed for the City of Peachtree Corners, GA, comprising nine integrated data sets. This platform can capture dynamic interactions between data from different sources and has the potential to support decision-makers in developing different solution options for contemporary transportation-related problems in a smart city environment. 

Current commercial adaptive cruise control (ACC) systems consist of an upper-level planner controller that decides the optimal trajectory that should be followed, and a low-level controller in charge of sending the gas/break signals to the mechanical system to actually move the vehicle. We find that the low-level controller has a significant impact on the string stability (SS) even if the planner is string stable: (i) a slow controller deteriorates the SS, (ii) slow controllers are common as they arise from insufficient control gains, from a “weak” gas/brake system or both, and (iii) the integral term in a slow controller causes undesired overshooting which affects the SS. Accordingly, we suggest tuning up the proportional/feedforward gain and ensuring the gas/brake is not “weak”. The study results are validated both numerically and empirically with data from commercial cars. 

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.