Research on the Emergency Obstacle Avoidance Strategy of Intelligent Vehicles Based on a Safety Distance Model

Abstract

Under emergency conditions, the safety distance between vehicles is insufficient, and drivers initiate unreasonable obstacle avoidance, which results in accident risks to vehicles. Therefore, an emergency obstacle avoidance system is needed for intervention to avoid traffic accidents. This paper proposes a coordinated steering and braking obstacle avoidance control strategy based on a safety distance model. The strategy takes into account handling stability and ride comfort. In the emergency braking obstacle avoidance module, the safety distance model and the graded warning mechanism based on the braking process are established. In the emergency steering obstacle avoidance module, a steering safety distance mode with multiple constraints is established, the obstacle avoidance trajectory is planned using the fifthdegree polynomial, and the obstacle avoidance trajectory is tracked using the model predictive control algorithm. The co-simulation results show that the emergency obstacle avoidance strategy proposed in this paper can select the appropriate way to complete obstacle avoidance under different working conditions. In braking obstacle avoidance, the braking deceleration essentially matches the expected value. In steering obstacle avoidance, the maximum error of lateral displacement can be reduced to 0.09 m. The research in this paper can provide a theoretical and practical basis for improving the driving safety, handling stability and ride comfort of intelligent vehicles.

Visual Ranging Based on Object Detection Bounding Box Optimization

“…Visual ranging, which is a research hotspot in the field of computer vision, automatically measures the distance between an object and the camera and has significant research implications [1,2]. It is frequently employed in research areas such as visual navigation [3], traffic safety [4], visual obstacle avoidance [5], and others. The two primary visual ranging techniques are monocular vision measurement and stereo vision measurement [6].…”