Techniques are described herein for a perceptual system for a vehicle that may detect and track objects in an environment. The perceptual system may include a machine learning model that includes one or more different portions, e.g., different components, sub-processes, etc. In some examples, the techniques may include training a machine learning model end-to-end such that an output of a first portion of the machine learning model is customized to an input for another portion of the machine learning model. Additionally, or alternatively, the perceptual system described herein may utilize temporal data to track objects in the environment of the vehicle, and associate the tracking data with specific objects in the environment detected by the machine learning model. That is, the architecture of the machine learning model may include both a detection portion and a tracking portion in the same loop.
本文描述了可以检测和跟踪环境中的对象的用于车辆的感知系统的技术。感知系统可以包括机器学习模型,该机器学习模型包括一个或多个不同的部分,例如,不同的组件、子过程等。在一些实例中,该技术可以包括端对端地训练机器学习模型,以使机器学习模型的第一部分的输出被定制为用于机器学习模型的另一部分的输入。另外地,或者可替代地,本文描述的感知系统可以利用时间数据来跟踪车辆的环境中的对象,并且将跟踪数据与由机器学习模型检测到的环境中的具体对象相关联。即,机器学习模型的架构可以在相同循环中包括检测部分和跟踪部分两者。
Vehicle perception system with time tracker
具有时间跟踪器的车辆感知系统
2024-07-12
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 / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen |