Robotics & Machine Learning Daily News2024,Issue(Nov.15) :174-178.

Patent Issued for Dynamic object relevance determination (USPTO 12128887)

动态物体相关性判定专利(USPTO 12128887)

Robotics & Machine Learning Daily News2024,Issue(Nov.15) :174-178.

Patent Issued for Dynamic object relevance determination (USPTO 12128887)

动态物体相关性判定专利(USPTO 12128887)

扫码查看

摘要

记者从发明人提供的背景资料中获得以下引述:“自主和半自主车辆的规划系统确定车辆应采取的行动”在操作环境中。车辆的动作可以部分地基于避开物体来确定存在于环境中。例如,可以生成绕过并停放v的动作车辆、改变车道以避开道路上的另一车辆等。规划系统可以执行一系列模拟,以确定每个检测到的目标对车辆潜在动作的影响。然而,在具有大量对象的环境中,对每个检测到的对象执行模拟CT的计算成本可能很高,在某些情况下,机载计算机能力是不可能的。

Abstract

Reporters obtained the following quote from the background information supplied by the inventors:“Planning systems in autonomous and semi-autonomous vehicles d etermine actions for a vehicle to takein an operating environment. Actions for a vehicle may be determined based in part on avoiding objectspresent in the env ironment. For example, an action may be generated to go around a double-parked vehicle, to change a lane to avoid another vehicle in the road, or the like. The planning systems may performa series of simulations to determine an effect of e ach detected object on a potential action for the vehicle.However, in environme nts with a large number of objects, performing simulations on each detected object may be computationally costly and, in some cases, impossible with onboard com puting capabilities.”

Key words

Business/Cyborgs/Emerging Technologies/Machine Learning/Zoox Inc.

引用本文复制引用

出版年

2024
Robotics & Machine Learning Daily News

Robotics & Machine Learning Daily News

ISSN:
段落导航相关论文