An Approach to Utilize FMEA for Autonomous Vehicles to Forecast Decision Outcome

Abstract

Abstract. Every autonomous vehicle has an analytic framework which monitors the decision making of the vehicle to keep it safe. By tweaking the FMEA (Failure Mode Effect Analysis) framework and applying this to the decision system will make significant increase in the quality of the decisions, especially in series of decision and its overall outcome. This will avoid collisions and better quality of decision.The proposed methodology uses this approach to identify the risks associated with the best alternative selected. The FMEA requires to be running at real time. It has to keep its previous experiences in hand to do quick/split time decision making. This paper considers a case study of FMEA framework applied to autonomous driving vehicles to support decision making. It shows a significant increase in the performance in the execution of FMEA over GPU. It also brings out a comparison of CUDA to TPL and sequential execution.

Infrastructure-Based Pedestrian Risk Tagging Methodology to Support AV Risk Assessment

“…These standards are defined as regulations to develop risk assessments for AV validation during the development lifecycle [13,14]. Ensuring the operational AV's safety levels requires the consideration of all potential hazardous (or riskrelated) events to devise a corresponding safety goal that allows the AV to be validated during the development lifecycle [15,16]. This existing process-based risk assessment method uses a qualitative approach using experts' opinions and a database of lessons learnt [4,7,[17][18][19].…”

“…The pedestrian occurrence heatmap (Heatmaprz) is defined as (15). With the pedestrian occurrence data and the total pedestrian detected, the probability of pedestrian P(occ) occurring in each sub-region can be calculated as (16).…”