Browsing by Subject "trajectory"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Collision-Free Path Planning for Automated Vehicles Risk Assessment via Predictive Occupancy Map
    (IEEE, 2020-11) Shen, Dan; Chen, Yaobin; Li, Lingxi; Chien, Stanley; Electrical and Computer Engineering, School of Engineering and Technology
    Vehicle collision avoidance system (CAS) is a control system that can guide the vehicle into a collision-free safe region in the presence of other objects on road. Common CAS functions, such as forward-collision warning and automatic emergency braking, have recently been developed and equipped on production vehicles. However, these CASs focus on mitigating or avoiding potential crashes with the preceding cars and objects. They are not effective for crash scenarios with vehicles from the rear-end or lateral directions. This paper proposes a novel collision avoidance system that will provide the vehicle with all-around (360-degree) collision avoidance capability. A risk evaluation model is developed to calculate potential risk levels by considering surrounding vehicles (according to their relative positions, velocities, and accelerations) and using a predictive occupancy map (POM). By using the POM, the safest path with the minimum risk values is chosen from 12 acceleration-based trajectory directions. The global optimal trajectory is then planned using the optimal rapidly exploring random tree (RRT*) algorithm. The planned vehicle motion profile is generated as the reference for future control. Simulation results show that the developed POM-based CAS demonstrates effective operations to mitigate the potential crashes in both lateral and rear-end crash scenarios.
  • Thumbnail Image
    Item
    Predicting Hazardous Driving Events Using Multi-Modal Deep Learning Based on Video Motion Profile and Kinematics Data
    (IEEE, 2018-11) Gao, Z.; Liu, Y.; Zheng, J. Y.; Yu, R.; Wang, X.; Sun, P.; Computer and Information Science, School of Science
    As the raising of traffic accidents caused by commercial vehicle drivers, more regulations have been issued for improving their safety status. Driving record instruments are required to be installed on such vehicles in China. The obtained naturalistic driving data offer insight into the causal factors of hazardous events with the requirements to identify where hazardous events happen within large volumes of data. In this study, we develop a model based on a low-definition driving record instrument and the vehicle kinematic data for post-accident analysis by multi-modal deep learning method. With a higher camera position on commercial vehicles than cars that can observe further distance, motion profiles are extracted from driving video to capture the trajectory features of front vehicles at different depths. Then random forest is used to select significant kinematic variables which can reflect the potential crash. Finally, a multi-modal deep convolutional neural network (DCNN) combined both video and kinematic data is developed to identify potential collision risk in each 12-second vehicle trip. The analysis results indicate that the proposed multi-modal deep learning model can identify hazardous events within a large volumes of data at an AUC of 0.81, which outperforms the state-of-the-art random forest model and kinematic threshold method.