Interactive Decision-Making Integrating Graph Neural Networks and Model Predictive Control for Autonomous Driving

Greater prosociality toward other human drivers than autonomous vehicles: Human drivers’ discriminatory behavior in mixed traffic

Many traffic accidents are caused by unforeseen and unexpected events in a site that was hidden from the driver's eyes. Road design parameters determining required visibility are based on relationships formulated decades ago. It is worth reviewing them from time to time in the light of technological developments. In this paper, sight distances for stopping and crossing situations are studied in relation to the assumed visual abilities of autonomous vehicles. Current sight distance requirements at unsignalized intersections are based among others on speeds on the major road and on ac-cepted gaps by human drivers entering or crossing from the minor road. Since these requirements vary from country to country, regulations and sight terms of a few selected countries are compared in this study. From the comparison it is remarkable that although the two concepts, i.e. gap acceptance on the minor road and stopping on the major road have different backgrounds, but their outcome in terms of required sight distances are similar. Both distances are depending on speed on the major road: gap sight distances show a linear, while stopping sight distances a parabolic function. In general, European SSD values are quite similar to each other. However, the US and Australian guidelines based on gap acceptance criteria recommend higher sight distances. Human capabilities and limitations are considered in sight field requirements. Autonomous vehicles survey their environment with sensors which are different from the human vision in terms of identifying objects, estimating distances or speeds of other vehicles. This paper compares current sight field requirements based on conventional vehicles and those required for autonomous vehicles. Visibility requirements were defined by three vision indicators: distance, angle of view and resolution abilities of autonomous cars and human drivers. These indicators were calculated separately for autonomous vehicles and human drivers for various speeds on the main road and for intersections with 90° and 60° angles. It was shown that the required sight distances are 10 to 40 meters shorter for autonomous vehicles than for conventional ones.

Merging is, in general, a challenging task for both human drivers and autonomous vehicles, especially in dense traffic, because the merging vehicle typically needs to interact with other vehicles to identify or create a gap and safely merge into. In this paper, we consider the problem of autonomous vehicle control for forced merge scenarios. We propose a novel game-theoretic controller, called the Leader-Follower Game Controller (LFGC), in which the interactions between the autonomous ego vehicle and other vehicles with a priori uncertain driving intentions is modeled as a partially observable leader-follower game. The LFGC estimates the other vehicles’ intentions online based on observed trajectories, and then predicts their future trajectories and plans the ego vehicle’s own trajectory using Model Predictive Control (MPC) to simultaneously achieve probabilistically guaranteed safety and merging objectives. To verify the performance of LFGC, we test it in simulations and with the NGSIM data, where the LFGC demonstrates a high success rate of 97.5% in merging.

Autonomous navigation in dense traffic scenarios remains challenging for autonomous vehicles (AVs) because the intentions of other drivers are not directly observable and AVs have to deal with a wide range of driving behaviors. To maneuver through dense traffic, AVs must be able to reason how their actions affect others (interaction model) and exploit this reasoning to navigate through dense traffic safely. This paper presents a novel framework for interaction-aware motion planning in dense traffic scenarios. We explore the connection between human driving behavior and their velocity changes when interacting. Hence, we propose to learn, via deep Reinforcement Learning (RL), an interaction-aware policy providing global guidance about the cooperativeness of other vehicles to an optimization-based planner ensuring safety and kinematic feasibility through constraint satisfaction. The learned policy can reason and guide the local optimization-based planner with interactive behavior to pro-actively merge in dense traffic while remaining safe in case other vehicles do not yield. We present qualitative and quantitative results in highly interactive simulation environments (highway merging and unprotected left turns) against two baseline approaches, a learning-based and an optimization-based method. The presented results show that our method significantly reduces the number of collisions and increases the success rate with respect to both learning-based and optimization-based baselines.

This paper presents the implementation of an autonomous electric vehicle (EV) project in the National Taiwan University of Science and Technology (NTUST) campus in Taiwan. The aim of this work was to integrate two important practices of realizing an autonomous vehicle in a campus environment, including vehicle positioning and path tracking. Such a project is helpful to the students to learn and practice key technologies of autonomous vehicles conveniently. Therefore, a laboratory-made EV was equipped with real-time kinematic GPS (RTK-GPS) to provide centimeter position accuracy. Furthermore, the model predictive control (MPC) was proposed to perform the path tracking capability. Nevertheless, the RTK-GPS exhibited some robust positioning concerns in practical application, such as a low update rate, signal obstruction, signal drift, and network instability. To solve this problem, a multisensory fusion approach using an unscented Kalman filter (UKF) was utilized to improve the vehicle positioning performance by further considering an inertial measurement unit (IMU) and wheel odometry. On the other hand, the model predictive control (MPC) is usually used to control autonomous EVs. However, the determination of MPC parameters is a challenging task. Hence, reinforcement learning (RL) was utilized to generalize the pre-trained datum value for the determination of MPC parameters in practice. To evaluate the performance of the RL-based MPC, software simulations using MATLAB and a laboratory-made, full-scale electric vehicle were arranged for experiments and validation. In a 199.27 m campus loop path, the estimated travel distance error was 0.82% in terms of UKF. The MPC parameters generated by RL also achieved a better tracking performance with 0.227 m RMSE in path tracking experiments, and they also achieved a better tracking performance when compared to that of human-tuned MPC parameters.

Autonomous vehicle control based on receding horizon method

Rapid advancements in vehicle automation technology have enabled autonomous vehicles (AVs) to move beyond simple, structured highway settings and operate increasingly within more complex urban environments. As AVs become more prevalent, they will inevitably share the road with diverse traffic participants, particularly pedestrians. The high uncertainty and dynamic nature inherent in human behavior significantly complicate the AV’s decision-making process. To ensure both safety and efficiency while exhibiting socially acceptable behavior, AVs must make real-time decisions and continuously adapt their strategies in response to surrounding pedestrian behaviors. This poses a major challenge to existing AV decision-making systems. Therefore, this study focuses on developing the decision-making strategies for AVs in urban pedestrian-involved environments, spanning scenarios from simple interactions with a single pedestrian to complex cases involving multiple pedestrians. The core objective is to uncover the underlying interaction dynamics and to improve the AV’s capability to make decisions that are safe, efficient and socially acceptable in dynamic, human-centric contexts. Initially, this study investigates the critical factors influencing the decision making processes of human drivers and pedestrians during vehicle–pedestrian interactions. A series of controlled experiments were conducted using a virtual reality platform designed to collect realistic behavioral data. The data analysis mainly focused on kinematic variables that are easily measurable in real-world deployments. AdaBoost classification and Partial Dependence Plots were employed to identify and visualize the most influential factors affecting pedestrian crossing intentions and driver approaching behaviors. The results indicate that longitudinal distance and vehicle acceleration are the most influential factors in pedestrian decision-making, while pedestrian speed and longitudinal distance also play a crucial role in determining whether the vehicle yields or not. Based on these insights, a simplified mathematical model was developed to relate observable kinematic parameters to pedestrian crossing intentions, providing a practical tool for dynamically inferring crossing intentions during interactions. Additionally, the study explored driver yielding patterns under varying degrees of pedestrian intention clarity. These findings support the development of interpretable and implementable models for real-time decision-making in vehicle–pedestrian interaction scenarios. In addition, this study examines the decision-making strategies of the AVs when interacting with a single pedestrian in unsignalized intersections. A novel framework was proposed that integrates the Partially Observable Markov Decision Process with behavioral game theory to dynamically model interactive behaviors between the AVs and the pedestrian. Both agents were modeled as dynamic-belief-induced quantal cognitive hierarchy models, considering human reasoning limitations and bounded rationality in the decision-making process. Moreover, a dynamic belief updating mechanism allowed the AV to update its understanding of the opponent’s rationality degree in real-time based on observed behaviors and adapt its strategies accordingly. The analysis results indicate that proposed models effectively simulate vehicle-pedestrian interactions and the AV decision-making approach performs well in safety, efficiency, and smoothness. It captures key patterns of the driving behavior operated by real human drivers in virtual reality experiments and even achieves more comfortable navigation compared to our previous virtual reality experimental data. Finally, this study investigates the decision-making strategies of the AVs operating in pedestrian-rich shared spaces. A novel framework was proposed for modeling interactions between the AV and multiple pedestrians. In this framework, a cognitive process modeling approach inspired by the Free Energy Principle was integrated into both the AV and pedestrian models to simulate more realistic interaction dynamics. Specifically, the proposed pedestrian Cognitive-Risk Social Force Model adjusts goal-directed and repulsive forces using a fused measure of cognitive uncertainty and physical risk to produce human-like trajectories. Meanwhile, the AV leverages this fused risk to construct a dynamic, riskaware adjacency matrix for a Graph Convolutional Network within a Soft Actor-Critic architecture, allowing it to make more reasonable and informed decisions. The qualitative and quantitative results indicate that the proposed strategy effectively improves safety, efficiency, and smoothness of AV navigation compared to the state-of-the-art method. In conclusion, this study addresses key challenges in AV decision-making within human-centric urban environments, providing valuable insights as well as practical solutions to support safe, efficient, and socially aware autonomous navigation.

This paper presents a novel integrated approach to deal with the decision making and motion planning for lane-change maneuvers of autonomous vehicle (AV) considering social behaviors of surrounding traffic occupants. Reflected by driving styles and intentions of surrounding vehicles, the social behaviors are taken into consideration during the modelling process. Then, the Stackelberg Game theory is applied to solve the decision-making, which is formulated as a non-cooperative game problem. Besides, potential field is adopted in the motion planning model, which uses different potential functions to describe surrounding vehicles with different behaviors and road constrains. Then, Model Predictive Control (MPC) is utilized to predict the state and trajectory of the autonomous vehicle. Finally, the decision-making and motion planning is then integrated into a constrained multi-objective optimization problem. Three testing scenarios considering different social behaviors of surrounding vehicles are carried out to validate the performance of the proposed approach. Testing results show that the integrated approach is able to address different social interactions with other traffic participants, and make proper and safe decisions and planning for autonomous vehicles, demonstrating its feasibility and effectiveness.

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

Stated preference analysis of autonomous vehicle among bicyclists and pedestrians in Pittsburgh using Bayesian Networks

This thesis presents a work in progress related to the use of Health and Usage Monitoring Systems (HUMS) data to actuate an adaptive control system on an autonomous vehicle operating in an Intelligent Transportation Systems (ITS). The autonomous passenger vehicle has rapidly matured from a speculative concept to a reality that is quickly appearing within our sightlines. Autonomous (also called self-driving, driverless, or robotic) vehicles have long been predicted in science fiction and discussed in popular science media. Recently, major corporations have announced plans to begin selling such vehicles in the near future, and some jurisdictions have passed legislation to allow such vehicles to operate legally on public roads. Autonomous vehicles will be performing intelligent functions (navigation, maneuver, behavior, or task) by perceiving the environment and implementing a responsive action based on HUMS input. Once these vehicles begin to operate on public roads as a norm, safety and reliability becomes a major factor. The implementation or expanded use of HUMS can perceivably render these systems reliable and safe to operate in any environment or mode. This thesis also depicts a notational framework for HUMS in autonomous vehicles operating on ITS networks and future research needed to make this a reality. Keywords: Health and Usage Monitoring System (HUMS), Reliability, Adaptive Systems, Prognostics, Autonomous Vehicle, Intelligent Transportation System

This paper presents the hardware in the loop of control the position of electro hydraulic servo system based on Data Acquisition Card (NI-6014) and hybrid Model Predictive Controller (MPC). The realization of hybrid MPC depends on using Data Card and Matlab/ Simulink as the core of the control system. In addition, this paper discusses the using of Cuckoo Search Algorithm (CSA) for optimal tuning of the traditional controller parameters as a part of hybrid MPC controller. The experimental implementation of the studied system has been investigated using REXROTH components. The Electro Hydraulic Servo System mechanism (EHSS) plays an important role in industrial applications, especially in flight simulators, aircraft landing gear system, material testing machine and hydraulic press machines. The key reason of applying hydraulic systems on these applications is that it can give a high torque and high force. The theoretical and experimental results demonstrate that the values of performance criteria (settling, rise times and system overshoots) are the minimum in case of realization hybrid MPC position control over using traditional and MPC controllers. It also introduced that the integral time absolute error for various types of test signals (Multistep, sinusoidal and square signals) are a minimum values in case of using the proposed strategy in compared with the traditional and MPC controllers. In addition, hybrid MPC achieved the required physical limits of the actuator. As a general conclusion, one can conclude that the hybrid model predictive control has the priority of applying it in the field of electro hydraulic servo system due to the mentioned advantages.

Despite the many advancements in traffic safety, vehicle overtaking still poses significant challenges to both human drivers and autonomous vehicles, especially, how to evaluate the safety of passing a leading vehicle efficiently and reliably on a two-lane road. However, few realistic attempts in this field have been made in the literature to provide practical solutions without prior knowledge of the state of the environment and simplifications of vehicle models. These model simplifications make many of the proposed solutions in the literature unusable in real scenarios. Considering the dangers that can arise from performing a defective overtake and the substantial risk of vehicle crashes during high-speed maneuvers, in this paper we propose a system based on model predictive control to accurately estimate the safety of starting a vehicle overtake in addition to vehicle control during the maneuver that aims to ensure a collision-free overtake using a complete and realistic model of the vehicle’s dynamics. The system relies on a stereoscopic vision approach and machine learning techniques (YOLO and DeepSORT) to gather information about the environment such as lane width, lane center, and distance from neighboring vehicles. Furthermore, we propose a set of scenarios to test the performance of the proposed system based on accurate modeling of the environment under a range of traffic conditions and road architecture. The simulation result shows the high performance of the proposed system in ending collisions during overtaking and providing optimal pathing that minimizes travel time.

Human drivers naturally adapt their behaviour depending on the traffic conditions, such as the current weather and road type. Autonomous vehicles need to do the same, in a way that is both safe and efficient in traffic composed of both conventional and autonomous vehicles. In this paper, we demonstrate the applicability of a reconfigurable vehicle controller agent for autonomous vehicles that adapts the parameters of a used car‐following model at runtime, so as to maintain a high degree of traffic quality (efficiency and safety) under different weather conditions. We follow a dynamic software product line approach to model the variability of the car‐following model parameters, context changes and traffic quality, and generate specific configurations for each particular context. Under realistic conditions, autonomous vehicles have only a very local knowledge of other vehicles' variables. We investigate a distributed model predictive controller agent for autonomous vehicles to estimate their behavioural parameters at runtime, based on their available knowledge of the system. We show that autonomous vehicles with the proposed reconfigurable controller agent lead to behaviour similar to that achieved by human drivers, depending on the context.

Cellular networking infrastructure supports various types of services including vehicular networking. This means that employing advanced technologies within sixth generation (6G) communications will enforce more refinements on autonomous vehicles and subsequently on the whole smart transportation sector. Nowadays, vehicles communicate with each other or with the network as individual machines that relate to each other through sharing various data about landscape and platform status. The traffic flow at any street is an interaction of sets of factors, such as street capacities, vehicle trajectories, spatiotemporal congestion, etc. Autonomous vehicles will use sensors and network data in evaluating the safest and fastest route to follow. Similarly, autonomous vehicles will share their platform health indicators to reduce the impact of accidental crashes and support of power dispatching in vehicle-to-grid (V2G) networking. However, this type of automation reflects the early phases of network connected vehicles and may not leverage all possible use cases. For example, the emergence of blockchain-based networks will transform vehicular networking with distributed lodger models and dynamic creation of block spots that record all events. This sophisticated trace identification of data initiators and users will provide autonomous vehicles with more accurate and instant changes in street traffic flow. This issue of the Vehicular Networking Series includes four articles, which are briefly summarized here.