A survey on motion prediction and risk assessment for intelligent vehicles

TLDR

The automotive industry is moving toward intelligent vehicles to improve road safety, yet detecting and reacting to dangerous situations requires predicting future traffic evolution and assessing its risk. This paper surveys existing methods for motion prediction and risk assessment in intelligent vehicles. The survey classifies methods based on the semantics used to define motion and risk. It highlights a trade‑off between model completeness and real‑time constraints and notes that risk assessment choice depends on the motion model.

Abstract

Abstract With the objective to improve road safety, the automotive industry is moving toward more “intelligent” vehicles. One of the major challenges is to detect dangerous situations and react accordingly in order to avoid or mitigate accidents. This requires predicting the likely evolution of the current traffic situation, and assessing how dangerous that future situation might be. This paper is a survey of existing methods for motion prediction and risk assessment for intelligent vehicles. The proposed classification is based on the semantics used to define motion and risk. We point out the tradeoff between model completeness and real-time constraints, and the fact that the choice of a risk assessment method is influenced by the selected motion model.