協調センシング下での自動車衝突リスク推定
Automotive Collision Risk Estimation Under Cooperative Sensing
協調センシングを行う自動運転車の衝突リスクを動的確率占有マップと損失関数で評価し、協調によるリスク低減と精度向上を定量化する手法を提案。都市交差点の実データで実証した。
著者: Daniel LaChapelle, Todd Humphreys, Lakshay Narula, Peter Iannucci, Ehsan Moradi-Pari
分類: cs.RO, eess.SP
原文アブストラクト
This paper offers a technique for estimating collision risk for automated ground vehicles engaged in cooperative sensing. The technique allows quantification of (i) risk reduced due to cooperation, and (ii) the increased accuracy of risk assessment due to cooperation. If either is significant, cooperation can be viewed as a desirable practice for meeting the stringent risk budget of increasingly automated vehicles; if not, then cooperation - with its various drawbacks - need not be pursued. Collision risk is evaluated over an ego vehicle's trajectory based on a dynamic probabilistic occupancy map and a loss function that maps collision-relevant state information to a cost metric. The risk evaluation framework is demonstrated using real data captured from two cooperating vehicles traversing an urban intersection.
