Fast and accurate long-term trajectory prediction of surrounding vehicles (SVs) is critical to autonomous driving systems. In high-density traffic flows, strongly correlated vehicle behaviors require considering the interactions among multiple SVs when predicting their future trajectories. However, existing interactive prediction methods, most based on Long Short-Term Memory (LSTM), are suffering from slow prediction because they analyze SVs one by one and analyze trajectory sequence node by node. This paper presents a fast interactive trajectory prediction method called Structural Transformer which learns both spatial and temporal dependencies among multiple SVs in parallel. Specifically, our model first removes the internal states and loops of LSTM and replaces with a weighted self-reference mapping to realize parallel computation. Then, it embeds the relative spatial information of multiple SVs into trajectory states and reorganizes the self-reference mapping with neighbor-only interaction masks to achieve interactive prediction. Results on the NGSIM dataset show satisfyingly speed and accuracy performance on long-term trajectory prediction of multiple SVs. The longitudinal and lateral errors are reduced to 2.67m and 0.25m over 5s time horizon. The computational time of each step is only 12ms on a 2080ti GPU, which is over 4 times faster than the Structural LSTM.

Haptic guidance in a shared steering assistance system has drawn significant attention in intelligent vehicle fields, owing to its mutual communication ability for vehicle control. By exerting continuous torque on the steering wheel, both the driver and support system can share lateral control of the vehicle. However, current haptic guidance steering systems demonstrate some deficiencies in assisting lane changing. This study explored a new steering interaction method, including the design and evaluation of an intention-based haptic shared steering system. Such an intention-based method can support both lane keeping and lane changing assistance, by detecting a driver's lane change intention. By using a deep learning-based method to model a driver's decision timing regarding lane crossing, an adaptive gain control method was proposed for realizing a steering control system. An intention consistency method was proposed to detect whether the driver and the system were acting towards the same target trajectories and to accurately capture the driver's intention. A driving simulator experiment was conducted to test the system performance. Participants were required to perform six trials with assistive methods and one trial without assistance. The results demonstrated that the supporting system decreased the lane departure risk in the lane keeping tasks and could support a fast and stable lane changing maneuver.

The lane-change decision-making module of automated and connected vehicles (ACVs) is one of the most crucial and challenging issues to be addressed. Motivated by human beings’ underlying driving paradigm and the convolutional neural network’s (CNN) dramatic capability of extracting features and learning strategies, this article proposes a CNN-based lane-change decision-making method via the dynamic motion image representation. Human drivers take proper driving maneuvers after they subconsciously construct the dynamic traffic scene representation in their brains, so this study first proposes the dynamic motion image representation method to reveal informative traffic situations in the motion-sensitive area (MSA), which provides a full view of surrounding cars. Then, this article develops a CNN model to extract the underlying features and learn driving policies from labeled datasets of MSA motion images. Besides, a safety-constrained layer is added to avoid vehicle collisions. We build a simulation platform based on the simulation of urban mobility (SUMO) to collect traffic datasets and test our proposed method. In addition, real-world traffic datasets are also involved to further investigate the proposed method’s performance. The rule-based strategy and reinforcement learning (RL)-based method are used to compare with our approach. All results demonstrate that the proposed method performs lane-change decision-making much better than prevailing methods, which suggests our scheme has huge potential to accelerate the deployment of ACVs and is worth further study.

Ground traffic lights are essential for maintaining traffic efficiency and safety at intersections. However, unsignallised intersections are still frequent in actual traffic environments. With the development of new forms of vehicular communication, in‐vehicle traffic lights can assist drivers at unsignallised intersections. The authors proposed two types of in‐vehicle traffic lights to assist drivers; these corresponded to two‐way and all‐way stop‐controlled intersections. They adopted gap acceptance theory and a first‐come‐first‐served strategy to determine passing priority for the two types of intersections, respectively. They then conducted a driving simulator experiment involving 23 participants, to investigate driver behaviours elicited by the proposed system. They prepared four experimental conditions with combinations of in‐vehicle traffic lights and auditory warnings. The authors’ experimental results indicated that in‐vehicle traffic lights were associated with significantly longer post‐encroachment times and a significantly shorter maximum brake stroke. In terms of eye‐gaze behaviours, the percentage of gaze concentration to the road centre area and mean glance durations were deemed acceptable for the avoidance of visual distraction, when in‐vehicle traffic lights were presented via a head‐up display. Therefore, their analysis of driver behaviours indicates that in‐vehicle traffic lights can effectively provide driver assistance at unsignallised intersections.