The difficulty of vehicle trajectory prediction mainly lies in the shared spatial-temporal relationships among vehicles. To address this task effectively, extracting the spatial-temporal details that affect the inter-vehicle motion, such as motion intentions and interactions, is crucial. This paper proposes a Mamba-driven differential Transformer model with an intention coupling decoder (ICMDT). Differential Transformer determines final attention scores by calculating the difference between two independent softmax attention maps, effectively suppressing the noise in spatial-temporal features. ICMDT integrates the strengths of differential Transformer and Mamba, concentrating on encoding spatial-temporal features while eliminating redundant information. It also enhances global information aggregation and spatial interaction modeling. Additionally, an intention coupling decoder is proposed to align motion intentions with spatial-temporal features, achieving connections between features and intention query instances. This decoder facilitates accurate multi-modal trajectory predictions. ICMDT has demonstrated superior performance across four real-world datasets, surpassing multiple metrics. For instance, improvements of 45.92% to 57.89% in long-term prediction (3∼5s) are achieved using the RMSE metric, which is quite promising. Notably, our experiments reveal that the intention coupling decoder consistently enhances the prediction accuracy of several leading prediction models, providing new insights for the future development of vehicle trajectory prediction algorithms.

Accurate trajectory prediction plays a crucial role in optimizing the performance of Internet of Vehicles (IoV) systems, reducing data transmission overhead, and enhancing communication network security. However, the expanding sensing range in IoV has led to increasingly complex spatial-temporal interactions, posing significant challenges for future trajectory prediction endeavors. Currently, predominant approaches involve constructing spatial-temporal interactions through various attention mechanisms. Nevertheless, these methods often yield numerous redundant interactions, potentially resulting in unstable predictions and diffuse interactions. Consequently, there is a pressing need to enhance the application of these methods in trajectory prediction within IoV contexts. Motivated by these challenges, our work introduces a sparse spatial-temporal Transformer (SSTT) to predict vehicle trajectories. SSTT consists of two main Transformer modules: the sparse spatial Transformer and the local-global temporal Transformer. We integrate a learnable sparse plugin into the former to minimize extraneous information in spatial interactions. This plugin enables SSTT to focus more effectively on critical interactive neighbor vehicles by optimizing attention weight distribution, thereby enhancing optimization convergence and prediction accuracy. For the latter, local time windows are employed to capture temporal local correlations and extend the attentional receptive field. Experimental results conducted on three real-world datasets demonstrate that SSTT achieves state-of-the-art performance, and even when only 15% of the training data is used, it can still outperform SOAT baselines. This study presents novel ideas and methodologies for advancing trajectory prediction techniques within the IoV paradigm. The code and our model will be available at GitHub.

Vehicle trajectory prediction (VTP) poses unique spatial-temporal modeling challenges, as a human-like prediction requires considering fine-grained interactions. Prior models have often used various attention mechanisms to extract key spatial-temporal interactions from the foreground, thus missing background information processing. However, this may result in the model’s insufficient generalization ability in a specific modality. Here this paper presents VCIFormer, a velocity-aware complementary interaction Transformer designed to enhance vehicle trajectory prediction by capturing complex spatial-temporal interactions between foreground and background with context awareness. VCIFormer combines inverse attention with traditional spatial-temporal attention as a complementary mechanism, applying bidirectional optimization to capture foreground and background attention flows. An adaptive visual mask is also developed to align attention allocation with human visual patterns at varying velocities. It enables the model to prioritize critical regions analogous to human driving behavior. Moreover, a context-aware encoder, consisting of a surround-aware module and a motion-enhancement module, is incorporated to provide additional interaction cues and spatial information. VCIFormer is evaluated on six real-world datasets (NGSIM, HighD, RounD, ExiD, Argoverse, and nuScenes) and attains state-of-the-art performance in critical metrics. For example, in comparison to baseline models, there are significant improvements in ADE and FDE by 2.84-18.18% and 9.88-13.33% on the NGSIM, HighD, RounD, and ExiD datasets, respectively. In sum, compared with previous architectures, VCIFormer presents a more effective combination of spatial-temporal interaction layers and context awareness for VTP.

Generative Adversarial Networks (GAN) have been widely used in traffic data imputation to improve the accuracy of data imputation. However, existing GAN-based models often suffer from mode collapse and cannot fully reflect the complex characteristics of real-world traffic, which affects the quality of data imputation. To address these challenges, we incorporate the Diffusion Model (DM) into the GAN framework, integrating the traffic dynamics modeling process within the Diffusion-GAN network. Based on this, we propose a Diffusion-TGAN speed data imputation model to generate individual vehicle speeds. Combined with the generated vehicle speed, the group trajectory reconstruction result is further given. The model uses the forward process of DM to generate condition vectors to guide the training of GAN generator. Subsequently, the discriminator of GAN takes the traffic dynamics constraints into account during adversarial training. Traffic dynamics modeling aims to make the generated speed data consistent with the real traffic characteristics. Experiments on multiple data sets show that the proposed model effectively imputes in the spatio-temporal speed data, and reduces the RMSE of the speed considering the position by 23.4% compared with the common GAN model, and reduces the RMSE by 39.7% in the trajectory reconstruction respectively. The code and our model are available at GitHub.

In a mixed traffic environment of human and autonomous driving, it is crucial for an autonomous vehicle to predict the lane change intentions and trajectories of vehicles that pose a risk to it. However, due to the uncertainty of human intentions, accurately predicting lane change intentions and trajectories is a great challenge. Therefore, this paper aims to establish the connection between intentions and trajectories and propose a dual Transformer model for the target vehicle. The dual Transformer model contains a lane change intention prediction model and a trajectory prediction model. The lane change intention prediction model is able to extract social correlations in terms of vehicle states and outputs an intention probability vector. The trajectory prediction model fuses the intention probability vector, which enables it to obtain prior knowledge. For the intention prediction model, the accuracy can be improved by designing the multi-head attention. For the trajectory prediction model, the performance can be optimized by incorporating intention probability vectors and adding the LSTM. Verified on NGSIM and highD datasets, the experimental results show that this model has encouraging accuracy. Compared with the model without intention probability vectors, the impact of the model on NGSIM dataset and highD dataset in RMSE is improved by 57.27% and 58.70% respectively. Compared with two existed models, evaluation metrics of the intention prediction can be improved by 7.40-10.09% on NGSIM dataset and 2.17-2.69% on highD dataset within advanced prediction time 1s. This method provides the insights for designing advanced perceptual systems for autonomous vehicles.

Intelligent connected vehicle platoon technology can reduce traffic congestion and vehicle fuel. However, attacks on the data transmitted by the platoon are one of the primary challenges encountered by the platoon during its travels. The false data injection (FDI) attack can lead to road congestion and even vehicle collisions, which can impact the platoon. However, the complexity of the cellular - vehicle to everything (C-V2X) environment, the single source of the message and the poor data processing capability of the on board unit (OBU) make the traditional detection methods’ success rate and response time poor. This study proposes a platoon state information fusion method using the communication characteristics of the platoon in C-V2X and proposes a novel platoon intrusion detection model based on this fusion method combined with sequential importance sampling (SIS). The SIS is a measured strategy of Monte Carlo integration sampling. Specifically, the method takes the status information of the platoon members as the predicted value input. It uses the leader vehicle status information as the posterior probability of the observed value to the current moment of the platoon members. The posterior probabilities of the platoon members and the weights of the platoon members at the last moment are used as input to update the weights of the platoon members at the current moment and obtain the desired platoon status information at the present moment. Moreover, it compares the status information of the platoon members with the desired status information to detect attacks on the platoon. Finally, the effectiveness of the method is demonstrated by simulation.

With the connected vehicle (CV) can interact with the infrastructure and can be used as a moving sensor to bring more real-time and higher precision input for intersection signal control. However, such connectivity also brings network security risks.To protect the signal security of intersections, this paper designs a realistic signal attack model based on forged trajectory injection to simulate the potential attack that a smart attacker may launch, the key track points of queued vehicles were extracted, the traffic wave velocity of queued vehicles was used as the distance index to transform forged track recognition into an outlier detection problem, and a forged track detection algorithm based on hierarchical clustering was proposed. Experimental results show that under different attack targets and permeability, the highest detection rate is 95%, and the lowest is 67%. This method does not require training, learning and high computation power of edge equipment. Therefore, it has a certain potential for intersection signal timing using CV trajectory.