Vehicle trajectory prediction helps automated vehicles and advanced driver-assistance systems have a better understanding of traffic environment and perform tasks such as criticality assessment in ...advance. In this study, an integrated vehicle trajectory prediction method is proposed by combining physics- and maneuver-based approaches. These two methods were combined for the reason that the physics-based trajectory prediction method could ensure accuracy in the short term with the consideration of vehicle running dynamic parameters, and the maneuver-based prediction approach has a long-term insight into future trajectories with maneuver estimation. In this study, the interactive multiple model trajectory prediction (IMMTP) method is proposed by combining the two predicting models. The probability of each model in the interactive multiple models could recursively adjust according to the predicting variance of each model. In addition, prediction uncertainty is considered by employing unscented Kalman filters in the physics-based prediction model. To the maneuver-based method, random elements for uncertainty are introduced to the trajectory of each maneuver inferred by using the dynamic Bayesian network. The approach is applied and analyzed in the lane-changing scenario by using naturalistic driving data. Comparison results indicate that IMMTP could achieve a more accurate prediction trajectory with a long prediction horizon.
There are still some problems need to be solved though there are a lot of achievements in the fields of automatic driving. One of those problems is the difficulty of designing a car-following ...decision-making system for complex traffic conditions. In recent years, reinforcement learning shows the potential in solving sequential decision optimization problems. In this article, we establish the reward function R of each driver data based on the inverse reinforcement learning algorithm, and r visualization is carried out, and then driving characteristics and following strategies are analyzed. At last, we show the efficiency of the proposed method by simulation in a highway environment.
Road parameter cognition is essential for intelligent and connected vehicles (ICVs) operating on unstructured roads because it can influence their path planning and motion control. A method is ...presented for the extraction of longitudinal slopes and lateral slopes and the roughness of unstructured roads using multi‐frame three‐dimensional point clouds. First, a segmentation method based on the multiple features is proposed to extract and divide the regions of interest into blocks with different slopes, which is valuable for further study on ground segmentation. Second, a parameter cognition method is proposed to estimate the slope and roughness of unstructured roads. Last but not least, a multi‐frame fusion method is proposed to improve cognition accuracy. Experimental tests on unstructured roads demonstrate that the proposed algorithm has satisfactory performance in terms of the accuracy of recognizing road slopes and roughness.
It is necessary for automated vehicles (AVs) and advanced driver assistance systems (ADASs) to have a better understanding of the traffic environment including driving behaviors. This study aims to ...build a driving behavior awareness (DBA) model that can infer driving behaviors such as lane change. In this study, a dynamic Bayesian network DBA model is proposed, which includes three layers, namely, the observation, hidden and behavior layer. To enhance the performance of the DBA model, the network structure is optimized by employing a distributed genetic algorithm (GA). Using naturalistic driving data in Beijing, the comparison between the optimized model and other non-optimized models such as the hidden Markov model (HMM) and HMM with a mixture of Gaussian outputs (GM-HMM) indicates that the optimized model could estimate driving behaviors earlier and more accurately.
Situational assessment (SA) is one of the key parts for the application of intelligent alternative-energy vehicles (IAVs) in the sustainable transportation. It helps IAVs understand and comprehend ...traffic environments better. In SA, it is crucial to be aware of uncertainty-risks, such as sensor failure or communication loss. The objective of this study is to assess traffic situations considering uncertainty-risks, including environment predicting uncertainty. According to the stochastic environment model, collision probabilities between multiple vehicles are estimated based on integrated trajectory prediction under uncertainty, which combines the physics- and maneuver-based trajectory prediction models for accurate prediction results in the long term. The SA method considers the probabilities of collision at different predicting points, the masses, and relative speeds between the possible colliding objects. In addition, risks beyond the prediction horizon are considered with the proposition of infinite risk assessments (IRAs). This method is applied and proved to assess risks regarding unexpected obstacles in traffic, sensor failure or communication loss, and imperfect detections with different sensing accuracies of the environment. The results indicate that the SA method could evaluate traffic risks under uncertainty in the dynamic traffic environment. This could help IAVs’ plan motion trajectories and make high-level decisions in uncertain environments.
The camera is one of the important sensors to realise the intelligent driving environment. It can realise lane detection and tracking, obstacle detection, traffic sign detection, identification and ...discrimination and visual simultaneous localisation and mapping. The visual sensor model, quantity and installation location are different on different intelligent driving hardware experimental platform as well as the visual sensor information processing module, thus a number of intelligent driving system software modules and interfaces are different. In this study, the software architecture of the autonomous vehicle based on the driving brain is used to adapt to different types of visual sensors. The target segment is extracted by the image segmentation algorithm, and then the segmentation of the region of interest is carried out. According to the input feature calculation results, the obstacle search is done in the second segmentation region, the output of the accessible road area. As driving information is complete, the authors will increase or reduce one or more visual sensors, change the visual sensor model or installation location, which will no longer directly affect the intelligent driving decision, they make the multi-vision sensors adapted to the requirements of different intelligent driving hardware test platforms.
Multi-modal fusion can take advantage of the LiDAR and camera to boost the robustness and performance of 3D object detection. However, there are still of great challenges to comprehensively exploit ...image information and perform accurate diverse feature interaction fusion. In this paper, we proposed a novel multi-modal framework, namely Point-Pixel Fusion for Multi-Modal 3D Object Detection (PPF-Det). The PPF-Det consists of three submodules, Multi Pixel Perception (MPP), Shared Combined Point Feature Encoder (SCPFE), and Point-Voxel-Wise Triple Attention Fusion (PVW-TAF) to address the above problems. Firstly, MPP can make full use of image semantic information to mitigate the problem of resolution mismatch between point cloud and image. In addition, we proposed SCPFE to preliminary extract point cloud features and point-pixel features simultaneously reducing time-consuming on 3D space. Lastly, we proposed a fine alignment fusion strategy PVW-TAF to generate multi-level voxel-fused features based on attention mechanism. Extensive experiments on KITTI benchmarks, conducted on September 24, 2023, demonstrate that our method shows excellent performance.
Vision-based segmentation methods rely heavily on image quality, and mining environments are full of dust, which greatly reduces visibility. Efficient and accurate segmentation of dusty regions in ...mining environments can improve the performance of unmanned vehicle environment perception. In this article, a dust segmentation method based on a novel density-aware nested U-structure convolutional neural network (DAUnet) is proposed. Compared with existing dust segmentation methods, our method has three advantages. First, we introduce the residual channel-spatial attention (RCSA) block. The block contains two attention layers and a residual structure, which can extract features more efficiently. Second, we introduce the difference expansion layer. This structure filters the predicted dust probabilities, eliminates pixels with lower probabilities, and then maps similar probability values to larger probability intervals, thus improving the network performance. Finally, for dust visualization, we use the predicted probabilities to reflect the dust density, which results in a smoother transition between the dust edges and the background. In addition, most of the current dust datasets are generated by simulation tools, and there is a lack of open-source real-world datasets. Therefore, we constructed the MineDust (MD) dataset based on a real open-pit mining environment. This dataset consists of dust-state images under different weather conditions and complex scenes. Experiments demonstrate that our algorithm can achieve 79.64% mIoU, which outperforms many existing segmentation methods.
Predicting pedestrian intention is a desirable capability for the safety of intelligent vehicles (IVs).Recently, deep learning-based methods have achieved decisive progress in improving prediction ...accuracy. However, the majority of these methods concentrate on drab lighting environments while disregarding the importance of rich pedestrian interactions. To handle above challenges, this paper proposes a pedestrian intention prediction framework which can model complex spatio-temporal interactions with multi-illumination environments. Firstly, a multi-illumination image generation method based on generative adversarial network is constructed to reduce the impact of complex lighting. Secondly, an interaction model based on 3D convolution and dense neural network structure is conducted to capture spatial-temporal pedestrians interaction. In addition, the pre-fusion and post-fusion quantify the improvement of different fusion methods on pedestrian intention prediction. Results on JAAD dataset show that the proposed prediction framework can effectively predict pedestrian intentions.
In intelligent driving, situational assessment (SA) is an important technology, which helps to improve the cognitive ability of intelligent vehicles in the environment. Uncertainty analysis is very ...significant in situation assessment. This article proposes an SA method based on uncertainty risk analysis. Under uncertain conditions, according to the random environment model and Gaussian distribution model, the collision probability between multiple vehicles is estimated by comprehensive trajectory prediction. The proposed method considers collision probabilities of different prediction points within and outside the prediction range and obtains long-term accurate prediction results. The method is suitable for the situation risk assessment of sensor systems in the presence of unexpected dynamic obstacles, sensor failures or communication losses in traffic, and different environmental sensing accuracy. The experimental results show that in the dynamic traffic environment, the proposed scenario assessment method can not only accurately predict and assess the situation risks within the prediction range, but also provide accurate scenario risk assessment outside the prediction range.