Risk assessment of autonomous vehicle based on six-dimensional semantic space
To address the problems of inadequate extraction of risk elements and low robustness of risk scenario as-sessment in autonomous vehicles,a risk assessment framework based on six-dimensional semantic space was pro-posed,which included risk element extraction based on six-dimensional semantic space and risk scenario assessment based on knowledge graph.Formerly,the semantic space was constructed with RGB and IR data mapped,and rich features were extracted using inter-modal correlations for explicit and potential risk elements.Subsequently,risk ele-ments were distilled into a knowledge graph by semantic role annotation and entity fusion,and an inference method was designed by combining node completion and risk level function for accurate risk assessment.Simulations show that the proposed method surpasses current MSMatch and iSQRT-COV-Net in accuracy,false/missed alarm rate,and processing time.
万方数据
维普
