A 3-dimensional real-time traffic simulator considering the interaction among autonomous and human-driven vehicles

Human-driven Vehicles (HVs) and Autonomous Vehicles (AVs) will inevitably coexist in the future, resulting in mixed traffic conditions. Modeling car-following behavior in such mixed traffic is crucial for better understanding the differences in driving behavior between AVs and HVs, thereby facilitating the development of AV driving strategies to enhance traffic safety. In such mixed traffic, the car-following modes typically include AVs following HVs, HVs following HVs and HVs following AVs. Previous studies have compared the driving behavior of HVs following HVs and HVs following AVs, but few have considered the driving behavior of AVs following HVs in the comparison. To bridge this gap, this paper first decomposes car-following events in mixed traffic extracted from a Lyft level-5 dataset into driving primitives using the Hidden Markov Model with Gaussian Mixture Model (GMM-HMM). Then, the Latent Dirichlet Allocation with GMM (GMM-LDA) is introduced to cluster the driving primitives into different car-following behavior patterns. Based on the identified patterns, the differences across the three car-following modes are further explored. The results show that the driving behavior under three car-following modes differs from each other. Specifically, compared to the HVs following HVs mode, in the AVs following HVs mode, AVs tend to maintain car-following behavior patterns with a longer distance gap and adopt a lower speed to ensure safety. This study offers a comprehensive understanding of car-following behavior in mixed traffic, which will facilitate the development of human-like driving strategies for AVs and enhance the safety of mixed traffic.

Previous empirical behavior analysis on Autonomous Vehicles (AV) mainly focused on vehicles with Adaptive Cruise Control (ACC) system due to the lack of high-level AV dataset. Recently released SAE Level-4 AV datasets such as the Waymo Open Dataset provide great opportunities to evaluate their behavioral impact on traffic flow. In this study, we aim to characterize the empirical Car Following (CF) behaviors of the Waymo autonomous vehicle and compare its feature with human-driven Vehicles (HV), and capture such behavioral differences using the IDM CF model. Our main findings include: (a) AV is much safer than HV, based on our analysis using surrogate safety measures, as time headways and jam spacings of the AV are significantly larger than HV; (b) the response time of AV is also significantly larger than that of HV in response to various types of stimuli; (c) despite the short length of trajectories in the Waymo Open Dataset, we have confirmed that these trajectories are suitable for calibrating some of the IDM parameters; and the calibration results of IDM are consistent with our empirical analysis. Moreover, the modelling results, reveal that the proportion of string unstable behavior of AV is less than that of HV; and (d) for HV, there is generally no significant difference between following AV and following HV except a smaller jam spacing when following AV. Overall, we conclude that currently AV behaves in a conservative way to ensure its safety at the cost of traffic efficiency.

Mixed traffic capacity estimation of autonomous vehicles impact based on empirical data

To address the travel delay caused by start-up lag in queued traffic at signalized inter-sections and fill the research gap of unseparated start-up loss characteristics between human-driven vehicles (HDVs) and autonomous vehicles (AVs), this study proposes an analytical start-up loss delay model applicable to both unsaturated and saturated traffic states. The model explicitly quantifies queue-length-dependent cascading propagation effects of start-up loss, and integrates vehicle type-specific parameters based on traffic queue theory and mixed traffic flow field observation data. Conventional models are limited by underestimated delay from neglecting platoon-level start-up loss propagation and failure to account for intrinsic HDV-AV start-up mechanism differences; to resolve these, we first distinguished the two vehicle types’ start-up behaviors (reaction time, acceleration, platoon coordination), then decoupled their start-up loss mechanisms and quantified their delay contributions via theoretical derivation, with validation against field test data and comparison with classical Webster and Clayton models. Field results revealed an order-of-magnitude difference in start-up response: HDVs had an average 2.05 s reaction time with large individual variability, while AVs maintained a stable 0.3–0.5 s response; HDV platoons reached saturated flow at the sixth vehicle, versus the third for AV platoons due to consistent acceleration and shorter headways. Model validation showed that under unsaturated conditions, red light duration significantly affects HDV delay, and the AV mix ratio is exponentially negatively correlated with additional delay. Under saturated conditions, green light duration increases start-up loss delay for both vehicle types, yet the growth rate of AVs (3.1–12.3%) is far lower than that of HDVs (18.2–67.5%), and arranging AVs in the leading position of mixed platoons can further reduce delay. The proposed model improves the accuracy of delay estimation in mixed HDV-AV traffic environments, and provides a theoretical basis for the optimized design of signal control strategies and the efficient management of intersection travel delay.

Transitioning to a driverless city: Evaluating a hybrid system for autonomous and non-autonomous vehicles

We study the problem of smoothing traffic flow in a mixed traffic scenario during the cruising phase of vehicles. We consider a connected vehicle system (CVS) composed of multiple human driving vehicles (HDVs) and multiple autonomous vehicles (AVs). For the HDVs, the human driver behavior is modeled by the widely adopted optimal velocity model. The role of the AV is to guide the traffic flow through regulating its own motion based on available traffic information. To avoid network congestion caused by heavy network resource utilization, each AV intermittently communicates with other vehicles. The intermittent vehicle-to-vehicle communication mechanism (I2CM) is adopted to qualitatively reduce the communication resources occupation. The optimal design of the cruise control for the AVs under I2CM is formulated as an optimal state feedback control problem with a random sparse structure constraint (RSSC). We derive the first analytical expression for the gradient of the cost function with respect to the control law with RSSC. We develop an algorithm that distributively estimates the gradient based on available data. We further design a gradient-based distributed cruise control strategy for the smoothing traffic flow problem under I2CM. We conduct simulations on a CVS system comprising 20 vehicles to evaluate the effectiveness of the proposed cruise control strategy. The results reveal that, on average, each AV contributes to a 15% improvement in the driving smoothness of HDVs relative to the scenario without any AVs. Funding: This research is supported in part by the National Natural Science Foundation of China [Grants 62303131, 72101198, and 62073273], in part by the Science Center Program of the National Natural Science Foundation of China [Grant 62188101], in part by the General Research Fund [Grant 14200720] of the Hong Kong University Grants Committee, and in part by the National Research Foundation Singapore through its Medium-Sized Center for Advanced Robotics Technology Innovation [Grant WP2.7].

To explore the impact of autonomous vehicles (AVs) on human-driven vehicles (HDVs), a solution for AV to coexist harmoniously with HDV during the car following period when AVs are in low market penetration rate (MPR) was provided. An extension car following framework with two possible soft optimization targets was proposed in this article to improve the experience of HDV followers with different following strategies by deep deterministic policy gradient (DDPG) algorithm. The pretreated Next Generation Simulation (NGSIM) dataset was used for the experiments. 1027 car following events with being redefined were extracted from it, in which 600 of the events were used for training and 427 of the events were used for testing. The different driving strategies obtained from the classical car following models were embedded into virtual environment built by OpenAI gym. The reward function combined safety, efficiency, jerk, and stability was used to encourage the agent with DDPG algorithm to maximize it. The final result reveals that disturbance of HDV followers decreases by 2.362% (strategy a), 8.184% (strategy b), and 13.904% (strategy c), respectively. The disturbance of HDV follower decreases by 14.961% (strategy a), 12.020% (strategy b), and 13.425% (strategy c), respectively. HDV followers with different strategies get less jerk in both soft optimizations. AV passengers get a loss on jerk and efficiency, but safety is enhanced. Also, AV car following performs better than HDV car following in both soft and brutal optimizations. Moreover, two possible solutions for harmonious coexistence of HDVs and AVs when AVs are in low MPR are proposed.

The large-scale integration of autonomous vehicles (AVs) has led to fundamental changes in the energy consumption evolution mechanism of new hybrid traffic flows, rendering conventional mapping between traffic flow parameters and energy invalid. This study develops a “flow–speed–density–energy” model for hybrid traffic composed of autonomous and human-driven vehicles (HVs). In this study, energy (kJ/km/h) is mathematically expressed as the product of the energy factor (kJ/km/veh) and traffic flow (veh/h). By constructing flow and energy factor curves with varying penetration rates and platoon intensities, the study derives four–factor diagrams for hybrid traffic flows. The analysis yields several key findings. First, for internal combustion engine vehicles (ICEVs), energy in HV platoons decreases with increasing speed, whereas in AV platoons it first decreases and then rises as flow intensifies under high-speed conditions. Second, energy is inversely correlated with density, reflecting the negative speed–density relationship. Under uncongested conditions, energy increases with flow, while in congested regimes, sharp reductions in the energy factor leads to overall energy decline. Finally, the primary difference between electric vehicles (EVs) and ICEVs lies in the low-speed range, where the energy of ICEVs decreases rapidly with increasing speed, whereas the energy of EVs increases due to the slower decline of the energy factor and faster flow growth. This study addresses the challenges in the operation and energy consumption of hybrid traffic flow at the macroscopic traffic level, providing foundational support for energy management.

The macroscopic evaluation of road traffic characteristics is vital as they will alter significantly with the emergence of Connected and Autonomous Vehicles (CAVs). The macroscopic second-order traffic flow models are emerging as essential tools to observe the evolutionary dynamics of traffic flow. These models are significantly improved to describe the dynamics of traffic flow in view of Human-Driven Vehicles (HDVs). However, proficient macroscopic second-order traffic flow models are indispensable in comprehending and elucidating the descriptions of traffic flow dynamics, particularly in the view of evolving CAVs. Therefore, we propose a macroscopic second-order traffic model that distinguishes CAVs from HDVs by meticulously considering their distinct driving characteristics. The proposed model incorporates lengthways between the vehicles, and the reaction time of the CAVs, and is evaluated on a 20,000 m ring road. The findings show that with smaller lengthways and reaction times of CAVs, traffic evolves quickly during transitions. An increase in average traffic velocity is observed as the reaction time is significantly small. It has been demonstrated that CAVs can significantly limit variations in velocity resulting in smoother flow operations.

Traffic congestion frequently occurs on slope segments of highways, which are typical bottlenecks. With the development of connected and autonomous vehicle (CAV) technology, CAVs and human-driven vehicles (HDVs) are anticipated to coexist on the same roads in the foreseeable future, thereby transforming the traffic environment from predominantly HDVs to a mixture of CAVs and HDVs. To the best of the authors’ knowledge, no studies address slope bottlenecks on highways in mixed traffic flow. Thus, this paper proposes a traffic flow model for slope bottlenecks incorporating CAV platooning based on cellular automata. A novel traffic flow control strategy for slope bottlenecks is proposed, based on variable speed limits (VSL) and vehicle platooning. Firstly, it divides the upstream section of the slope bottleneck into two zones for implementing VSL and vehicle platooning. Via speed restrictions within the VSL zone, the inflow of vehicles into the vehicle platooning zone is effectively mitigated to create low traffic density. In the vehicle platooning zone, a hybrid vehicle platooning method for mixed scenarios is proposed. Extensive experiments are conducted to validate that the proposed strategy increases the traffic flow of the slope bottleneck, improves the average speed, and alleviates traffic congestion.

This study aims to quantify the impact of discretionary lane-changing (DLC) on following vehicles (FVs) in the target lane using real-world dataset. The Waymo Open Dataset is used to identify the differences between autonomous vehicles (AVs) DLC and human-driven vehicles (HDVs) DLC maneuvers and compare their impacts on the driving volatility. Then, a block maxima (BM) model is applied to estimate crash risks. Finally, multivariate adaptive regression splines (MARS) is adopted to model gap acceptance behaviors of AV and HDV. Compared to HDV DLC, AV DLC leads to lower speed and yaw rate volatility and smaller acceleration rates of FVs. Further, the BM model reveals that the crash risk in AV DLC events is half of that in HDV DLC events. Additionally, MARS show that AV and HDV accept different lead gap. These findings highlight the benefits of mixing AVs in traffic and guide the improvement of AV controllers.

Autonomous vehicles are gradually entering the transportation system. The traffic will become more heterogeneous since both autonomous and human-driven vehicles will share the roads. Cooperative driving, by promoting synchronized actions and shared situational awareness among vehicles, can significantly enhance driving safety. On the other hand, understanding human drivers is a pivotal step for cooperative driving in such mixed traffic environments, which facilitates effective interaction between human drivers and their vehicles. This paper presents a testbed that can be used to conduct research in intelligent and cooperative driving. The testbed consists of driving simulators, custom-designed copilots with an Artificial Intelligence engine, an optimization server, and a cloud database. The copilot is capable of sensing and understanding the human driver, the vehicle and the traffic. It can assist the driver by providing timely alerts on potential risks. Most importantly, it can communicate with other nearby vehicles for cooperative driving. Two case studies are presented to validate and evaluate the testbed. The first case study demonstrates the performance of the copilot in human distraction detection and driving assistance. The second case study focuses on cooperative driving between one human-driven vehicle and two connected autonomous vehicles in a lane-changing scenario. We expect this research testbed to be used in various research projects that involve human-driven vehicles and connected autonomous vehicles.

Random capacity for a single lane with mixed autonomous and human-driven vehicles: Bounds, mean gaps and probability distributions

Liability Design for Autonomous Vehicles and Human-Driven Vehicles: A Hierarchical Game-Theoretic Approach

This study explores the impact of driving behaviors, specifically cautious and aggressive, on the performance of human-driven vehicles (HDVs) and autonomous vehicles (AVs) in traffic flow dynamics. It focuses on various metrics, including level of service (LOS), average speed, traffic volume, queue delays, carbon emissions, and fuel consumption, to assess their effects on overall performance. The findings reveal significant differences between cautious and aggressive AVs, particularly at varying market penetration rates (MPRs). Aggressive autonomous vehicles demonstrate greater traffic efficiency compared to their cautious counterparts. They achieve higher levels of service, improving from poor performance at low MPRs to significantly better performance at higher MPRs and in fully autonomous scenarios. In contrast, cautious AVs often experience poor service ratings at low MPRs, with an improvement in performance only at higher MPRs. Regarding environmental performance, aggressive AVs outperform cautious ones in terms of reduced emissions and fuel consumption. The emissions produced by aggressive AVs are significantly lower than those from cautious AVs, and they further decrease as the MPRs increases. Additionally, aggressive AVs show a considerable reduction in fuel usage compared to cautious AVs. While cautious AVs improve slightly at higher MPRs, they continue to generate higher emissions and consume more fuel than their aggressive counterparts. In conclusion, aggressive AVs offer better traffic efficiency and environmental performance than both cautious AVs. Their ability to improve road efficiency and reduce congestion positions them as a valuable asset for sustainable transportation. Strategically incorporating aggressive AVs into transportation systems could lead to significant advancements in traffic management and environmental sustainability.