Vehicle control device and method
The disclosure relates to a technology regarding a vehicle control device and method, in a vehicle follow-up control context, comprising receiving surrounding vehicle detection information received from a sensor of a host vehicle, generating cut-in state information for separately predicting a cut-in state using a cut-in probability calculation model based on the surrounding vehicle detection information, and calculating a required acceleration for a follow-up target of the host vehicle selected according to the cut-in state information.
1 . A vehicle control device controlling a vehicle in a vehicle follow-up control context, comprising:
a processor configured to:
receive surrounding vehicle detection information received from a sensor of a host vehicle;
generate cut-in state information for separately predicting a cut-in state using a cut-in probability calculation model based on the surrounding vehicle detection information;
calculate a required acceleration for a follow-up target of the host vehicle selected according to the cut-in state information; and
control the host vehicle to drive according to the required acceleration,
wherein the cut-in probability calculation model includes a first probability calculation model calculating a first probability value by estimating a probability that a hidden observed value is to be emitted by inputting transverse position information and transverse velocity information included in the surrounding vehicle detection information as an input value, and a second probability calculation model generating cut-in state information by operating the first probability value and a pre-calculated state transition probability value.
2 . The vehicle control device of claim 1 , wherein the surrounding vehicle detection information includes transverse position information, transverse velocity information, heading angle information, and lane information about a surrounding vehicle.
3 . The vehicle control device of claim 1 , wherein the cut-in state information includes N preset states divided with respect to a state in which a surrounding vehicle performs cut-in to a lane of the host vehicle, wherein N is a natural number of 2 or more.
4 . The vehicle control device of claim 3 , wherein the N preset states include a lane keeping state in which the surrounding vehicle maintains a lane, a cut-in ready state in which the surrounding vehicle prepares to change a lane to a host lane, a cut-in keeping state in which the surrounding vehicle is changing the lane to the host lane, and a cut-in ending state in which the surrounding vehicle finishes the lane change to the host lane.
5 . The vehicle control device of claim 4 , wherein when the cut-in state corresponds to the cut-in ready state, the processor selects a preceding vehicle of the host vehicle as a follow-up target, and calculates any one of a first required acceleration for the follow-up target and a second required acceleration calculated to control the host vehicle to drive at a constant velocity or to decelerate as the required acceleration.
6 . The vehicle control device of claim 4 , wherein when the cut-in state corresponds to the lane keeping state, the processor calculates the required acceleration by selecting a preceding vehicle of the host vehicle as the follow-up target.
7 . The vehicle control device of claim 4 , wherein when the cut-in state is the cut-in keeping state or the cut-in ending state, the processor calculates the required acceleration by selecting the surrounding vehicle for which the cut-in state is determined as the follow-up target.
8 . A vehicle control method controlling a vehicle in a vehicle follow-up control context, the vehicle control method comprising:
receiving surrounding vehicle detection information received from a sensor of a host vehicle;
generating cut-in state information for separately predicting a cut-in state using a cut-in probability calculation model based on the surrounding vehicle detection information;
calculating a required acceleration for a follow-up target of the host vehicle selected according to the cut-in state information; and
controlling the host vehicle to drive according to the required acceleration,
wherein the cut-in probability calculation model includes a first probability calculation model calculating a first probability value by estimating a probability that a hidden observed value is to be emitted by inputting transverse position information and transverse velocity information included in the surrounding vehicle detection information as an input value, and a second probability calculation model generating cut-in state information by operating the first probability value and a pre-calculated state transition probability value.
9 . The vehicle control method of claim 8 , wherein the surrounding vehicle detection information includes transverse position information, transverse velocity information, heading angle information, and lane information about a surrounding vehicle.
10 . The vehicle control method of claim 8 , wherein the cut-in state information includes N preset states divided with respect to a state in which a surrounding vehicle performs cut-in to a lane of the host vehicle, wherein N is a natural number of 2 or more.
11 . The vehicle control method of claim 10 , wherein the N preset states include a lane keeping state in which the surrounding vehicle maintains a lane, a cut-in ready state in which the surrounding vehicle prepares to change a lane to a host lane, a cut-in keeping state in which the surrounding vehicle is changing the lane to the host lane, and a cut-in ending state in which the surrounding vehicle finishes the lane change to the host lane.
12 . The vehicle control method of claim 11 , wherein when the cut-in state corresponds to the cut-in ready state, the calculating the required acceleration selects a preceding vehicle of the host vehicle as a follow-up target, and calculates any one of a first required acceleration for the follow-up target and a second required acceleration calculated to control the host vehicle to drive at a constant velocity or to decelerate as the required acceleration.
13 . The vehicle control method of claim 11 , wherein when the cut-in state corresponds to the lane keeping state, the calculating the required acceleration calculates the required acceleration by selecting a preceding vehicle of the host vehicle as the follow-up target.
14 . The vehicle control method of claim 11 , wherein when the cut-in state is the cut-in keeping state or the cut-in ending state, the calculating the required acceleration calculates the required acceleration by selecting the surrounding vehicle for which the cut-in state is determined as the follow-up target.