System and method for autonomous navigation of vehicle
A system and method for performing autonomous navigation of a vehicle are disclosed, which recognize a possibility of collision risk through path estimation of a target vehicle, and generate an autonomous navigation path. The autonomous navigation system for a vehicle includes: a target-vehicle information detection unit configured to detect traveling information of a target vehicle; and a path generation unit configured to estimate movement of the target vehicle on the basis of the information received from the target-vehicle information detection unit, calculate a collision risk value by recognizing a possibility of collision risk between an ego-vehicle and the target vehicle, and generate an autonomous navigation path of the ego-vehicle.
1. An autonomous navigation system for a vehicle, comprising:
a sensor configured to detect traveling information of a target vehicle; and
a processor configured to estimate movement of the target vehicle on the basis of the information received from the sensor, calculate a collision risk value by recognizing a possibility of collision risk between an ego-vehicle and the target vehicle, and generate an autonomous navigation path of the ego-vehicle,
wherein the processor determines a lane change intention of the target vehicle using a lane-change-intention probabilistic model indicating the lane change intention, and estimates a traveling path of the target vehicle, and
wherein the processor changes a lane-change completion time of the target vehicle according to a size of the target vehicle.
2. The autonomous navigation system according to claim 1 , wherein the traveling information of the target vehicle is detected using one of V2X (vehicle-to-everything) communication, a laser scanner, and a radar.
3. The autonomous navigation system according to claim 1 , wherein the sensor detects at least one of a size, a position, a departure angle, and a speed of the target vehicle.
4. The autonomous navigation system according to claim 1 , wherein the lane-change-intention probabilistic model is established by defining weights for reflecting influence of speed of the target vehicle and heading parameters of the target vehicle and the ego-vehicle, and by defining a speed of the target vehicle, a path difference between the target vehicle and the ego-vehicle, and an offset from a center part of a traveling lane.
5. The autonomous navigation system according to claim 1 , wherein the processor searches for the nearest point to a current traveling path of the ego-vehicle measured from the current position of the ego-vehicle, and thus calculates a position, a path-departure angle, and curvature information using road information modeling.
6. An autonomous navigation method for a vehicle, comprising:
detecting traveling information of a target vehicle;
estimating a movement of the target vehicle on the basis of information received from a sensor; and
calculating a collision risk value by recognizing a possibility of collision risk between an ego-vehicle and the target vehicle, and generating an autonomous navigation path of the ego-vehicle,
wherein the step of estimating a movement of the target vehicle includes:
determining a lane change intention of the target vehicle using a lane-change-intention probabilistic model indicating the lane change intention;
generating a lane change flag of the target vehicle; and
estimating a lane change path in consideration of a size of the target vehicle,
wherein the step of estimating a lane change path includes
changing a lane-change completion time of the target vehicle according to the size of the target vehicle.
7. The autonomous navigation method according to claim 6 , wherein the traveling information of the target vehicle includes at least one of a size, a position, a departure angle, and a speed of the target vehicle.
8. The autonomous navigation method according to claim 6 , wherein the lane-change-intention probabilistic model is established by defining weights for reflecting influence of speed of the target vehicle and heading parameters of the target vehicle and the ego-vehicle, and by defining a speed of the target vehicle, a path difference between the target vehicle and the ego-vehicle, and an offset from a center part of a traveling lane.
9. The autonomous navigation method according to claim 6 , wherein the step of estimating a movement of the target vehicle includes:
If a value of the lane-change-intention probabilistic model is greater than a first threshold value, inputting a first value to a lane change flag, and determining that a traveling lane of the target vehicle is changed to a lane of the ego-vehicle;
If a value of the lane-change-intention probabilistic model is less than a second threshold value, inputting a second value to the lane change flag, and determining that a traveling lane of the target vehicle is changed to an opposite lane of the ego-vehicle traveling path; and
If a value of the lane-change-intention probabilistic model is between the first threshold value and the second threshold value, inputting a third value to the lane change flag, and determining that a traveling lane of the target vehicle is unchanged.