The present disclosure relates generally to autonomous vehicles, and more particularly, to computational efficiency implementation of trajectory characterization techniques (e.g., multi-object tracking for autonomous vehicles) for traffic participants (e.g., vehicles, pedestrians, bicycle riders, etc. An exemplary method of generating a control signal to control a vehicle includes obtaining a parameterized characterization of a trajectory of a single object in the same environment as the vehicle; updating, within the framework of a multi-object and multi-hypothesis tracker, a parameterized characterization of the trajectory of the single object based on data received by one or more sensors of the vehicle; and generating a control signal for controlling the vehicle based on the updated object trajectory.
本公开一般涉及自主车辆,更具体地说,涉及高计算效率实现对象为(例如车辆、行人、自行车骑行者等)交通参与者的轨迹表征技术(例如用于自主车辆的多对象追踪)。生成控制车辆的控制信号的示例性方法包括:获得与车辆处于相同环境中的单一对象的轨迹的参数化表征;在多对象和多假设追踪器的框架内,基于由车辆的一个或多个传感器接收的数据,更新所述单一对象的轨迹的参数化表征;以及基于所更新的对象轨迹,生成用于控制车辆的控制信号。
Highly computational efficient traffic participant trajectory characterization
高计算效率的交通参与者轨迹表征
2023-08-08
Patent
Electronic Resource
Chinese
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 |
LSTM model-based vulnerable traffic participant trajectory prediction method
European Patent Office | 2022
|Traffic participant trajectory prediction method in complex heterogeneous environment
European Patent Office | 2023
|VEHICLE TRAJECTORY PREDICTION USING ROAD TOPOLOGY AND TRAFFIC PARTICIPANT OBJECT STATES
European Patent Office | 2021
|Vehicle trajectory prediction using road topology and traffic participant object states
European Patent Office | 2023
|