日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

自動運転アーキテクチャarXiv:1802.04112

インフラ支援型自動運転:分散知能アーキテクチャの提案

Infrastructure Enabled Autonomy: A Distributed Intelligence Architecture for Autonomous Vehicles

シェア:XThreadsFacebookLINEはてブBluesky

自動運転の責任と負担を自動車メーカー・道路インフラ・サードパーティで分担するため、車両・路側エッジコンピュータ・車内サードパーティ計算機に運転機能を分割する分散知能アーキテクチャを提案した論文。

著者: Swaminathan Gopalswamy, Sivakumar Rathinam

分類: cs.CY, cs.DC, cs.MA, cs.RO

原文アブストラクト

Multiple studies have illustrated the potential for dramatic societal, environmental and economic benefits from significant penetration of autonomous driving. However, all the current approaches to autonomous driving require the automotive manufacturers to shoulder the primary responsibility and liability associated with replacing human perception and decision making with automation, potentially slowing the penetration of autonomous vehicles, and consequently slowing the realization of the societal benefits of autonomous vehicles. We propose here a new approach to autonomous driving that will re-balance the responsibility and liabilities associated with autonomous driving between traditional automotive manufacturers, infrastructure players, and third-party players. Our proposed distributed intelligence architecture leverages the significant advancements in connectivity and edge computing in the recent decades to partition the driving functions between the vehicle, edge computers on the road side, and specialized third-party computers that reside in the vehicle. Infrastructure becomes a critical enabler for autonomy. With this Infrastructure Enabled Autonomy (IEA) concept, the traditional automotive manufacturers will only need to shoulder responsibility and liability comparable to what they already do today, and the infrastructure and third-party players will share the added responsibility and liabilities associated with autonomous functionalities. We propose a Bayesian Network Model based framework for assessing the risk benefits of such a distributed intelligence architecture. An additional benefit of the proposed architecture is that it enables "autonomy as a service" while still allowing for private ownership of automobiles.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

MINISFORUM(ミニPC)

MINISFORUM(ミニPC)の公式広告バナーMINISFORUM公式ストアを見る ↗
PR本紙発行元 EmplifAI