Real time object behavior prediction

Abstract

In one embodiment, a method, apparatus, and system may predict behavior of environmental objects using machine learning at an autonomous driving vehicle (ADV). A data processing architecture comprising at least a first neural network and a second neural network is generated, the first and the second neural networks having been trained with a training data set. Behavior of one or more objects in the ADV's environment is predicted using the data processing architecture comprising the trained neural networks. Driving signals are generated based at least in part on the predicted behavior of the one or more objects in the ADV's environment to control operations of the ADV.

Description

technical field [0001] Embodiments of the present disclosure generally relate to operating an autonomous vehicle. More specifically, embodiments of the present disclosure relate to using machine learning algorithms to make predictions in controlling autonomous vehicles. Background technique [0002] Vehicles operating in an autonomous mode (eg, driverless) can relieve the occupants, especially the driver, from some driving-related duties. When operating in autonomous mode, the vehicle can navigate to various locations using on-board sensors, allowing the vehicle to drive with minimal human interaction or in some situations without any passengers. [0003] Safe and reliable autonomous driving technology requires accurate predictions of the behavior of other objects around the autonomous vehicle. Solutions have been developed on how to encode features from the surrounding environment. However, predicting the interaction of objects remains difficult and time-consuming, as it...

AI Technical Summary

Problems solved by technology

However, predicting object interactions remains difficult and time-consuming, as it traditionally involves performing predictions on each of the objects and iteratively computing

Images