Search

Car-following is an important driving behaviour for intelligent vehicles and has a significant impact on traffic efficiency and traffic safety. Car-following models are widely developed to characterize the human-drivers car-following manoeuvre actions and adopted in traffic simulation and automated vehicle control system development. Car-following models need to be able to represent the drivers behaviour while following preceding vehicles. On the other hand, car-following controllers are an important component of intelligent vehicle systems, both for autonomous vehicles and connected vehicles. However, Adaptive Cruise Control (ACC) as well as Cooperative Adaptive Cruise Control (CACC) do not include human behaviour, which makes their car-following behaviour not human-like or natural for the on-board driver or passenger. To address this problem, in this study, the human-like Wiedemann car-following model is calibrated and verified with our driving simulator data. A human-like car-following nonlinear model predictive control (MPC) controller is developed based on the calibrated car-following model. Three different scenarios are tested to evaluate the performance of the proposed controller, with which the autonomous vehicle is able to have human-like and smooth trajectories at different phases and within different transition zones.

A timely understanding of target vehicles (TVs) lateral behavior is essential for the decision-making and control of host vehicle. Existing physical model-based methods such as motion-based method and multiple centerline-based method are generally constructed based on TV pose and longitudinal velocity, and tend to ignore TV preview driving characteristic and other useful information such as lateral velocity and yaw rate. To address these issues, a driver preview and multiple centerline model-based probabilistic behavior recognition architecture is proposed for timely and accurate TV lateral behavior prediction. Firstly, a driver preview model is used to describe vehicle preview driving characteristic, and TV preview lateral offset and preview lateral velocity are calculated with TV states and road reference information. Then, the preview lateral offset and preview lateral velocity are combined with multiple centerline model for TV lateral behavior reasoning based on the interacting multiple model-based probabilistic behavior recognition algorithm. With this method, TV preview driving characteristic and lateral motion states are combined for precise TV lateral behavior description. Furthermore, to predict short-term lateral behavior, a preview lateral velocity-dependent transition probability matrix model constructed with Gaussian cumulative distribution function is proposed. Simulation and experimental results show that the proposed method considering vehicle preview driving characteristic predicts TV lateral behavior earlier than the conventional method.

Although autonomous vehicles (AV) have been rapidly developed, their control technology is not sufficiently mature for daily use, yet not human-centred enough. Some studies regarding trajectory planning are overly conservative and the vehicle avoids obstacles in an unhuman-like trajectory which causes discomfort to passengers; meanwhile, other studies are overly simplistic, the transport scenario, and vehicle trajectory are disregarded. The potential field (PF) algorithm is one of the most frequently used methods for the trajectory planning of AVs; however, most studies regarding the PF algorithm do not consider driving comfort and smoothness. This paper introduces optimised human-centred dynamic trajectory planning for AVs. The PF algorithm is implemented in a vehicle simulation model, which is integrated with model predictive control (MPC). The reference path is planned by PF algorithm and improved by MPC. The human-centred AV control is proposed in a simulation environment. The proposed planning method achieves a trade-off between safety, driving comfort, and driving smoothness and is validated with several driving simulation scenarios.

Automated driving needs to be comfortable to encourage the broad acceptance and usage of automated vehicles (AVs). However, current research provides limited knowledge on the descriptions and influencing factors of user comfort in automated driving, especially from the perspective of an AV’s driving styles. This paper presents results from an online workshop, in which nine experts with hands-on experience of AVs, and a long track record of research in this context, brainstormed and discussed a series of topics related to user comfort in automated driving. Results showed that a wide range of terms were used to describe user comfort and discomfort, when the attendees considered being driven by either currently available transport modes (e.g., taxi/bus/train) or higher-level AVs (with neither requiring control of the vehicle by the user). All of the terms used for existing vehicles were found to apply to AVs, but additional aspects of comfort/discomfort were revealed for AVs. This suggests that what makes existing transport modes comfortable is not the same as that for higher-level AVs. Regarding the relationship between comfort and discomfort in automated driving, seven and ten categories of terms were identified for comfort and discomfort, respectively, with both the number and the nature of these categories differing across the two states. This suggests that, to ensure user comfort in automated driving, additional factors that affect comfort must be considered, rather than solely mitigating discomfort. By integrating these multiple aspects that affect user comfort, knowledge from the workshop was used to develop a conceptual framework, to explain how AV driving styles, as well as other, non-driving-related factors, affect user comfort, from both a physical and psychological perspective. This work provides an overview of experts’ insights on the factors that affect comfort in automated driving, and will facilitate a more comprehensive definition, and more accurate measurement, of user comfort, facilitating the design of more comfortable and acceptable automated driving for future vehicles.

Reliable trajectory prediction of preceding target vehicles (PTVs) is crucial for the planning and decision making of automated vehicles. However, the future trajectory is affected by the driver's intention and diverse driving styles, which can hardly be predicted precisely, especially when the vehicle performs a lane change maneuver. In this study, we propose a lane crossing and final points generation (CFPG) model-based trajectory prediction approach for PTVs, in which the key influence factors such as the driver's intention and the mixed driving style are included. Firstly, we build a maneuver and stage recognition model upon the long short term memory (LSTM) to infer the current maneuver of the preceding target vehicle. Furthermore, the approach predicts the lane crossing point using a physics-based model combining with a deep conditional generative model trained by a deep neural network. Moreover, a maneuver-based model is adopted to predict the final point according to the prediction interval. In order to avoid the possible cumulative error caused by iteratively generating trajectories in traditional methods, we use a curve fitting method to obtain the predicted trajectory. Lane changing data collected from naturalistic driving scenarios are used to verify the proposed approach, and the results suggest more accurate and reliable prediction trajectories compared with conventional methods.

Accidents involving pedestrians are particularly common at unsignalised intersections and mid-block crosswalks, where vehicles often do not yield to them. Analysing and understanding pedestrian crossing behaviour at such locations is vital for improving road safety. Previous studies have repeatedly shown that pedestrians tend to accept smaller time gaps in conditions with higher vehicle speeds and thus potentially less safe. This has prompted the hypothesis that pedestrians rely on spatial distance to make crossing decisions. However, few studies have investigated the mechanism underpinning this phenomenon. We propose a novel approach to characterise pedestrian crossing behaviour: a psychophysics-based gap acceptance (PGA) model based on visual looming cues and binary choice logit method. Road crossing data collected in a simulated experiment were used to analyse pedestrian behaviour and test the model. Our analysis indicates that, in line with previous studies, higher vehicle speed increased the tendency of gap acceptance, leading to a higher rate of unsafe crossings. Crucially, the PGA model could accurately account for these crossing decisions across experimental scenarios, more parsimoniously than a conventional model. These results explain the speed-induced unsafe behaviour by suggesting that pedestrians apply visual looming, which depends on vehicle speed and distance, to make crossing decisions. This study reinforces the notion that for two vehicles with the same time gap, the one with higher speed can elicit more risky crossing behaviour from pedestrians, potentially resulting in more severe accidents. The practical implications of the results for traffic safety management, modelling and development of automated vehicles are discussed.

This paper presents a hierarchical motion planning approach based on discrete optimization method. Well-coupled longitudinal and lateral planning strategies with adaptability features are applied for better performance of on-road autonomous driving with avoidance of both static and moving obstacles. In the path planning level, the proposed method starts with a speed profile designing for the determination of longitudinal horizon, then a set of candidate paths will be constructed with lateral offsets shifting from the base reference. Cost functions considering driving comfort and energy consumption are applied to evaluate each candidate path and the optimal one will be selected as tracking reference afterwards. Re-determination of longitudinal horizon in terms of relative distance between ego vehicle and surrounding obstacles, together with update of speed profile, will be triggered for re-planning if candidate paths ahead fail the safety checking. In the path tracking level, a pure-pursuit-based tracking controller is implemented to obtain the corresponding control sequence and further smooth the trajectory of autonomous vehicle. Simulation results demonstrate the effectiveness of the proposed method and indicate its better performance in extreme traffic scenarios compared to traditional discrete optimization methods, while balancing computational burden at the same time.

In the design of a path-tracking controller for autonomous vehicles, mediating the conflicting objectives among path-tracking, vehicle stabilisation, and low computational cost is a challenging iss...

Virtual Coupling (VC) is regarded as a breakthrough to the transitional train operation and control for improving the capability and flexibility in railways. It brings benefits as trains under VC are allowed to operate much closer to one another, forming a virtually coupled train set (VCTS). However, the safe and stable spacing between trains in the VCTS is a problem since there are no rigid couplers to connect them into a fixed formation, especially in high-speed scenarios. Due to the close spacing, the interference between trains becomes non-negligible as various maneuvers of the preceding train can significantly affect driving behaviors of the following train; this results in fluctuating spacing and therefore an unstable VCTS. Aiming at minimizing the interference and maintaining constantly safe spacing between trains in the VCTS, this paper presents a distributed model predictive control (DMPC) approach for solving the high-speed VCTS control problem. Particularly, the proposed control method focuses on the feasibility and stability of this problem, with considerations of the coupled constraint of safety braking distance and the individual constraints of speed limit variations and restricted traction/braking performance. To guarantee feasibility and stability, the terminal controller and invariant set of the DMPC are designed. For rigor, sufficient conditions of feasibility and stability are mathematically proved and derived. Based on the data of the Beijing-Shanghai high-speed railway line, numerical experiments are conducted to verify the correctness of derived sufficient conditions and the effectiveness of the proposed control method under interference and disturbances.

In this paper, a novel algorithm is proposed for the motion planning and path following automated cars with the incorporation of a collision avoidance strategy. This approach is aligned with an optimal reinforcement learning (RL) coupled with a new risk assessment approach. For this purpose, a probabilistic function-based collision avoidance strategy is developed, and the proposed RL approach learns the probability distributions of the adjacent and leading vehicles. Subsequently, the nonlinear model predictive control (NMPC) algorithm approximates the optimal steering input and the required yaw moment to follow the safest and shortest path through the optimal RL-based probabilistic risk function framework. Additionally, it is attempted to maintain the travel speed for the ego vehicle stable such that the ride comfort is also offered for the vehicle occupants. For this purpose, the steering system dynamics are also incorporated to provide a thorough understanding of the vehicle dynamics characteristic. Different driving scenarios are employed in the present paper to evaluate the proposed algorithm’s effectiveness.

As Autonomous Vehicles (AV) are becoming a reality, the design of efficient motion control algorithms will have to deal with the unpredictable and interactive nature of other road users. Current AV motion planning algorithms suffer from the freezing robot problem, as they often tend to overestimate collision risks. To tackle this problem and design AV that behave human-like, we integrate a concept from Psychology called Social Value Orientation into the Reinforcement Learning (RL) framework. The addition of a social term in the reward function design allows us to tune the AV behaviour towards the pedestrian from a more reckless to an extremely prudent one. We train the vehicle agent with a state of the art RL algorithm and show that Social Value Orientation is an effective tool to obtain pro-social AV behaviour.