The invention provides an obstacle behavior prediction method based on feature interaction and an automatic driving vehicle, relates to the technical field of artificial intelligence, in particular to the technical field of deep learning, image processing and computer vision, and can be applied to the field of automatic driving. A specific embodiment of the method comprises the following steps: acquiring obstacles around a vehicle and driving environment information; extracting obstacle features and driving environment features from the obstacle and driving environment information; performing feature interaction on the obstacle features and the driving environment features to obtain interaction features; and inputting the interaction characteristics into a decoder for motion prediction to obtain future behavior states of obstacles around the vehicle. According to the embodiment, the interaction expression capability is enhanced, and the prediction precision is improved.
本公开提供了一种基于特征交互的障碍物行为预测方法及自动驾驶车辆,涉及人工智能技术领域,具体为深度学习、图像处理和计算机视觉技术领域,可应用于自动驾驶领域。该方法的一具体实施方式包括:获取车辆周边的障碍物与驾驶环境信息;从障碍物与驾驶环境信息中提取障碍物特征和驾驶环境特征;对障碍物特征和驾驶环境特征进行特征交互,得到交互特征;将交互特征输入至解码器进行运动预测,得到车辆周边的障碍物的未来行为状态。该实施方式增强交互的表达能力,进而提升预测精度。
Obstacle behavior prediction method based on feature interaction and autonomous vehicle
基于特征交互的障碍物行为预测方法及自动驾驶车辆
2023-04-11
Patent
Elektronische Ressource
Chinesisch
IPC: | B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion |
Obstacle recognition method based on autonomous vehicle and autonomous vehicle
Europäisches Patentamt | 2022
|Obstacle prediction system for autonomous driving vehicles
Europäisches Patentamt | 2024
|Obstacle trajectory prediction method and device for autonomous vehicle, and electronic equipment
Europäisches Patentamt | 2023
|Modifying autonomous vehicle behavior prediction based on behavior prediction errors
Europäisches Patentamt | 2024
|