Vehicle Trajectory Prediction by Knowledge-Driven LSTM Network in Urban Environments

Table 1

Prediction rules used in this study.

ID	SWRL rules
Rule #1	TargetVehicle (target), currentRoadState (target, “ApprJunction”), isOnSegment (target, Seg), connectToJunction (Seg, Junc), intersection (Junc), hasTrafficLight (Junc, TL), (hasLightColor (TL, “red”), hasLightColor (TL, “yellow”)), connectToStopLine (Seg, SL), distToStopLine (SL, DL), DL < 10.
	legalToGo (target, SS)
Rule #2	TargetVehicle (target), currentRoadState (target, “ApprJunction”), isOnSegment (target, Seg), connectToJunction (Seg, Junc), intersection (Junc), hasTrafficLight (Junc, TL), hasLightColor (TL, “green”), connectToStopLine (Seg, SL), distToStopLine (SL, DL), DL = < 20.
	LegalToGo (target, acc)
Rule #3	TargetVehicle (target), currentVelocity (target, V), hasFrontObstacle (target, FO), distToObstacle (FO, DF), (DF/V) < 3, (DF/V) ≥ 2.
	SafeToGo (target, dec)