Safe following distance estimation system and estimation method thereof

1. A safe following distance estimation system, adapted for an autonomous vehicle, comprising:

a sensor, sensing at least one of a first longitudinal velocity, a first lateral velocity, image data, and LiDAR data of an adjacent vehicle to generate first sensing data, sensing at least one of a second longitudinal velocity, a second lateral velocity, a wheel velocity, a wheel deflection angle, a yaw rate, and an inclination angle of the autonomous vehicle to generate second sensing data, wherein the adjacent vehicle is adjacent to the autonomous vehicle;

a processor, coupled to the sensor, receiving the first sensing and the second sensing data from the sensor, calculating a first friction parameter between wheels of the adjacent vehicle and a pavement according to pavement material data, calculating a second friction parameter between wheels of the autonomous vehicle and the pavement according to the second sensing data, calculating a safe following distance between the autonomous vehicle and the adjacent vehicle according to the first sensing data from the sensor, the second sensing data from the sensor, the first friction parameter, and the second friction parameter; and

a communication system, coupled to the processor, where the processor receives a high-precision map through the communication system, wherein the processor generates the pavement material data according to the high-precision map,

wherein calculating the safe following distance between the autonomous vehicle and the adjacent vehicle by the processor comprises:

identifying a dynamic specification of the adjacent vehicle according to the first sensing data, wherein the dynamic specification comprises a maximum deceleration of the adjacent vehicle;

calculating a first maximum deceleration of the adjacent vehicle according to the dynamic specification and the first friction parameter of the adjacent vehicle,

calculating a second minimum deceleration of the autonomous vehicle according to the second friction parameter of the autonomous vehicle,

calculating a third maximum acceleration of the autonomous vehicle according to a rolling friction parameter of the autonomous vehicle; and

calculating the safe following distance according to the first maximum deceleration, the second minimum deceleration, and the third maximum acceleration.

2. The safe following distance estimation system according to claim 1 , wherein the pavement material data are input to a lookup table to generate a first friction coefficient corresponding to the first friction parameter, and the lookup table comprises a correspondence between a pavement material and the first friction coefficient.

3. The safe following distance estimation system according to claim 1 , wherein the processor extracts a plurality of features of the adjacent vehicle from the first sensing data, and provides the plurality of features to a vehicle classifier to generate the dynamic specification.

4. The safe following distance estimation system according to claim 1 , further comprising:

a display device, used to display a top view, wherein the top view comprises the autonomous vehicle, the adjacent vehicle, and a first distance between the autonomous vehicle and the adjacent vehicle.

5. The safe following distance estimation system according to claim 4 , wherein the processor compares the first distance with the safe following distance, and the top view shows the first distance in different colors corresponding to different comparison results.

6. The safe following distance estimation system according to claim 4 , wherein the processor compares the first distance with the safe following distance to determine whether the autonomous vehicle passes a safety verification, wherein the safe following distance comprises a longitudinal distance and a lateral distance.

7. A safe following distance estimation method, adapted for an autonomous vehicle, comprising:

sensing, by a sensor, at least one of a first longitudinal velocity, a first lateral velocity, image data, and LiDAR data of an adjacent vehicle to generate first sensing data, and sensing, by the sensor, at least one of a second longitudinal velocity, a second lateral velocity, a wheel velocity, a wheel deflection angle, a yaw rate, and an inclination angle of the autonomous vehicle to generate second sensing data, wherein the adjacent vehicle is adjacent to the autonomous vehicle;

calculating, by a processor, a first friction parameter between wheels of the adjacent vehicle and a pavement according to pavement material data;

calculating, by a processor, a second friction parameter between wheels of the autonomous vehicle and the pavement according to the second sensing data;

calculating, by the processor, a safe following distance between the autonomous vehicle and the adjacent vehicle according to the first sensing data from the sensor, the second sensing data from the sensor, the first friction parameter, and the second friction parameter;

receiving, by the processor, a high-precision map through a communication system; and

generating, by the processor, the pavement material data according to the high-precision map,

wherein calculating the safe following distance between the autonomous vehicle and the adjacent vehicle according to the first sensing data, the second sensing data, the first friction parameter, and the second friction parameter comprises:

identifying a dynamic specification of the adjacent vehicle according to the first sensing data, wherein the dynamic specification comprises a maximum deceleration of the adjacent vehicle;

calculating a first maximum deceleration of the adjacent vehicle according to the dynamic specification and the first friction parameter of the adjacent vehicle;

calculating a second minimum deceleration of the autonomous vehicle according to the second friction parameter of the autonomous vehicle;

calculating a third maximum acceleration of the autonomous vehicle according to a rolling friction parameter of the autonomous vehicle; and

calculating the safe following distance according to the first maximum deceleration, the second minimum deceleration, and the third maximum acceleration.

8. The safe following distance estimation method according to claim 7 , wherein the pavement material data are input to a lookup table to generate a first friction coefficient corresponding to the first friction parameter, and the lookup table comprises a correspondence between a pavement material and the first friction coefficient.

9. The safe following distance estimation method according to claim 7 , wherein identifying the dynamic specification of the adjacent vehicle according to the first sensing data comprises:

extracting a plurality of features of the adjacent vehicle from the first sensing data, and providing the plurality of features to a vehicle classifier to generate the dynamic specification.

10. The safe following distance estimation method according to claim 7 , further comprising:

displaying a top view, wherein the top view comprises the autonomous vehicle, the adjacent vehicle, and a first distance between the autonomous vehicle and the adjacent vehicle.

11. The safe following distance estimation method according to claim 10 , further comprising:

comparing the first distance with the safe following distance, wherein the top view shows the first distance in different colors corresponding to different comparison results.

12. The safe following distance estimation method according to claim 10 , further comprising:

comparing the first distance with the safe following distance to determine whether the autonomous vehicle passes a safety verification, wherein the safe following distance comprises a longitudinal distance and a lateral distance.