JP7254115B2 - Other vehicle behavior prediction device and other vehicle behavior prediction method - Google Patents

Description

The present application relates to a vehicle behavior prediction device and a vehicle behavior prediction method.

2. Description of the Related Art Conventionally, systems have been developed that support the driving of a vehicle by predicting the behavior of other vehicles in the vicinity of the vehicle based on information obtained from sensors or the like mounted on the vehicle. For example, in Patent Document 1, when there is a possibility of a collision between other vehicles and the predicted movement range of other vehicles, the predicted movement range is calculated so as to avoid the collision, and the final predicted movement range of the other vehicle and the vehicle itself are calculated. A collision avoidance device has been disclosed as an automatic driving system that estimates the possibility of a collision between one's own vehicle and another vehicle based on the overlap with the predicted movement range of the vehicle.

International Patent Publication No. WO2015/156097 (paragraphs 0012 to 0026, FIG. 1)

However, in the automatic driving system as described in Patent Document 1, since it is not possible to predict the lane change behavior according to the speed of the flow of vehicles in the lane, there is a problem that there is a possibility of erroneous behavior prediction.

SUMMARY OF THE INVENTION The present application has been made to solve the above problems, and aims to provide a vehicle behavior prediction device and a vehicle behavior prediction method for predicting lane change behavior according to the speed of vehicle flow in a lane. aim.

The other vehicle behavior prediction device disclosed in the present application has map information, and measures the position of the own vehicle to determine the position of the lane in which the own vehicle travels and the positions of the lanes around the own vehicle from the map information. a map information unit for detecting; a sensor unit for detecting the speed of the own vehicle, the speed of other vehicles traveling around the own vehicle, and the position of the other vehicle relative to the own vehicle; a calculation unit that selects a lane in which the other vehicle travels based on the position and the relative position of the other vehicle from the own vehicle, and calculates the speed of the flow of vehicles in each lane based on the speed of the other vehicle; a target determination unit that determines, from among the other vehicles, a vehicle having the shortest inter-vehicle distance to the own vehicle as a target vehicle based on the position of the own vehicle and the position of the other vehicle relative to the own vehicle; a prediction unit that calculates a probability that the target vehicle will change lanes when the speed of the target vehicle and the speed of the flow of vehicles in the lane in which the target vehicle is traveling are different, The speed of the flow is the fastest speed among the flows of vehicles traveling in each lane when the speed of the flow of vehicles increases, and the speed of the lane when the speed of the flow of vehicles decreases . It is characterized by being the slowest speed among the flows of vehicles running every time .

The other vehicle behavior prediction method disclosed in the present application includes the steps of measuring the position of the own vehicle, detecting the position of the lane in which the own vehicle travels and the positions of the lanes around the own vehicle; the speed of the own vehicle; a step of detecting the speed of another vehicle running around the own vehicle and the position of the other vehicle relative to the own vehicle; determining the lane in which each of the other vehicles travels, based on the speed of the other vehicle; calculating the speed of the flow of vehicles in each lane based on the speed of the other vehicle; a step of determining, as a target vehicle, one of the other vehicles that has the shortest inter-vehicle distance to the own vehicle based on the relative positions of the other vehicles; calculating the probability that the target vehicle will change lanes if different from the vehicle flow velocity, wherein the vehicle flow velocity for each lane is calculated as the vehicle flow velocity increases. is the fastest speed among the flow of vehicles traveling in each lane when the speed is decreasing , and the slowest speed among the flow of vehicles traveling in each lane when the speed of the flow of vehicles is decreasing. It is characterized by

According to the present application, it is possible to predict the lane change behavior according to the speed of the flow of vehicles in the lane.

1 is a block diagram showing the configuration of another vehicle behavior prediction device according to Embodiment 1; FIG. FIG. 4 is a flow chart diagram showing a processing procedure of the other vehicle behavior prediction device according to Embodiment 1; FIG. 2 is a diagram showing a vehicle motion model for explaining the other vehicle behavior prediction device according to Embodiment 1; FIG. 2 is a block diagram showing the hardware configuration of the other vehicle behavior prediction device according to Embodiment 1; FIG. FIG. 10 is a flow chart diagram showing a processing procedure of the other vehicle behavior prediction device according to Embodiment 2;

Embodiment 1.
FIG. 1 is a block diagram showing the configuration of another vehicle behavior prediction device 101 according to Embodiment 1. As shown in FIG. As shown in FIG. 1, the other vehicle behavior prediction device 101 includes a map information unit 1, a sensor unit 2, a lane information acquisition unit 3, a vehicle information acquisition unit 4, a lane speed calculation unit 5, a target determination unit 6, and a behavior prediction unit. 7.

The map information unit 1 holds map information such as the position, number and shape of lanes, and detects the lane in which the vehicle is traveling by measuring the position of the vehicle. The lane information acquisition unit 3 acquires lane information such as the position, number and shape of lanes in which the vehicle is traveling and lanes around the vehicle detected by the map information unit 1 as lane data.

The sensor unit 2 uses one or more peripheral sensor units (LiDAR (Light Detection and Ranging), camera, radar, etc.) to detect the speed of the own vehicle and other vehicles traveling within a recognizable range around the own vehicle. Detects the speed, position, distance, etc. of The vehicle information acquisition unit 4 acquires vehicle information such as the speed of the own vehicle detected by the sensor unit 2 and the speed, position, and distance of other vehicles traveling within a recognizable range around the own vehicle as object data.

Lane speed calculator 5 calculates sensor unit 2 in the vicinity of own vehicle based on the positions of the lanes around the own vehicle acquired by lane information acquisition unit 3 and the relative positions of other vehicles from the own vehicle acquired by vehicle information acquisition unit 4. Select the lanes in which all the other vehicles are traveling within the recognizable range, and calculate the average velocity for each lane as the velocity of the flow of vehicles in each lane from the velocities of the other vehicles traveling.

Based on the position of the own vehicle received by the lane information acquisition unit 3 and the position of the other vehicle relative to the own vehicle received by the vehicle information acquisition unit 4, the target determination unit 6 selects other vehicles from other vehicles traveling around the own vehicle. , the other vehicle with the shortest inter-vehicle distance is determined as the target vehicle.

The behavior prediction unit 7 compares the speed of the target vehicle received by the vehicle information acquisition unit 4 with the speed of the flow of vehicles in the lane in which the target vehicle travels, which is calculated by the lane speed calculation unit 5. If it is different from the speed of the vehicle flow in the lane in which the vehicle is traveling, predict that the target vehicle will change lanes, and calculate the probability that the target vehicle will change lanes.

The probability that the target vehicle will change lanes is calculated as follows. When there are two driving lanes, Vd1 is the difference between the running speed of the target vehicle and the flow speed of vehicles in the first running lane, and Vd2 is the difference between the running speed of the target vehicle and the flow speed of vehicles in the second running lane. If there is, the probability that the target vehicle selects the first lane is calculated by Vd2/(Vd1+Vd2), and the probability that the target vehicle selects the second lane is calculated by Vd1/(Vd1+Vd2).

When there are three driving lanes, the difference between the target vehicle's traveling speed and the vehicle flow speed in the first traveling lane is Vd1, and the difference between the target vehicle's traveling speed and the vehicle flow speed in the second traveling lane is Vd2. , when the difference between the running speed of the target vehicle and the speed of the flow of vehicles in the third running lane is Vd3, the probability that the target vehicle will select the first running lane is calculated by (Vd2+Vd3)/(Vd1+Vd2+Vd3), The probability that the target vehicle selects the second lane is calculated by (Vd1+Vd3)/(Vd1+Vd2+Vd3), and the probability that the target vehicle selects the third lane is calculated by (Vd1+Vd2)/(Vd1+Vd2+Vd3).

Next, another vehicle behavior prediction method by the other vehicle behavior prediction device 101 according to Embodiment 1 will be described. FIG. 2 is a flow chart showing the processing procedure of the other vehicle behavior prediction device. FIG. 3 is a diagram showing a vehicle motion model for explaining the operation of the other vehicle behavior prediction device, and is a diagram showing a case where the number of driving lanes is three. In FIG. 3, lane R1 is a low speed lane, lane R2 is a medium speed lane, and lane R3 is a high speed lane.

First, as shown in FIG. 3, in a vehicle 11 that is running, the lane information acquisition unit 3 measures the position of the vehicle 11 using the map information unit 1, and determines the position of the lane in which the vehicle 11 is traveling and the The position, number, shape, etc. of lanes around the vehicle are detected from the map information and acquired as lane information (step S201).

Subsequently, the vehicle information acquisition unit 4 uses the sensor unit 2 to determine the speed of the own vehicle 11, the speeds of other vehicles 21, 22, 23, 24, etc. traveling within a range that can be recognized around the own vehicle, and from the own vehicle 11. are detected and acquired as vehicle information (step S202).

Next, the lane speed calculation unit 5 calculates the positions of the lanes around the own vehicle acquired by the lane information acquisition unit 3 and the other vehicles 21, 22, 23, 24, . based on the relative positions of the other vehicles 21, 22, 23, 24, . . .

Next, the target determination unit 6 determines the position of the own vehicle 11 acquired by the lane information acquisition unit 3 and the other vehicles 21, 22, 23, 24 . Based on the position of , the other vehicle (referred to as the other vehicle 21 in FIG. 3) with the shortest inter-vehicle distance is determined as the target vehicle from among the other vehicles 21, 22, 23, 24, etc. traveling around the own vehicle. (Step S204).

After determining the target vehicle (other vehicle 21), it is checked whether there is another vehicle (step S205). If there is another vehicle (Yes in step S205), the steps from step S201 to step S204 are repeated.

If there are no other vehicles (No in step S205), the lane speed calculation unit 5 calculates the vehicle speed in each lane based on the speeds of the other vehicles 21, 22, 23, 24, ... acquired by the vehicle information acquisition unit 4. The average speed for each lane is calculated as the speed of the flow of water (step S206).

Next, the behavior prediction unit 7 calculates the speed of the target vehicle (other vehicle 21) received by the vehicle information acquisition unit 4 and the vehicle flow in the lane R1 in which the target vehicle (other vehicle 21) travels, which is calculated by the lane speed calculation unit 5. are compared (step S207).

If the speed of the target vehicle (other vehicle 21) does not differ from the vehicle flow speed in the lane R1 on which the target vehicle (other vehicle 21) is traveling (No in step S208), the process returns to step S207.

If the speed of the target vehicle (other vehicle 21) is different from the speed of the flow of vehicles in the lane R1 in which the target vehicle (other vehicle 21) travels (Yes in step S208), the behavior prediction unit 7 predicts that the target vehicle The probability of changing lanes to lane R2 adjacent to lane R1 in which (other vehicle 21) is traveling is calculated (step S209).

In this way, the other vehicle behavior prediction device 101 predicts the behavior of the target vehicle (other vehicle 21) based on the lane change probability calculated by the behavior prediction unit 7, and ends the process.

The other vehicle behavior prediction device 101 is composed of a processor 200 and a storage device 201, as shown in FIG. 4 as an example of hardware. Although not shown, the storage device includes a volatile storage device such as a random access memory and a non-volatile auxiliary storage device such as a flash memory. Also, an auxiliary storage device such as a hard disk may be provided instead of the flash memory. Processor 200 executes a program input from storage device 201 . In this case, the program is input from the auxiliary storage device to the processor 200 via the volatile storage device. Further, the processor 200 may output data such as calculation results to the volatile storage device of the storage device 201, or may store the data in the auxiliary storage device via the volatile storage device.

As described above, according to the other vehicle behavior prediction device 101 according to Embodiment 1, map information is provided, and the position of the own vehicle 11 is measured to determine the position of the lane in which the own vehicle 11 travels and the surroundings of the own vehicle. a map information unit 1 for detecting the position of the lane from the map information, the speed of the own vehicle 11, the speeds of the other vehicles 21, 22, 23, 24, . . . 21, 22, 23, 24, . Based on this, select the lane in which each of the other vehicles 21, 22, 23, 24, . and the position of the vehicle 11 and the relative positions of the other vehicles 21, 22, 23, 24, . . . A target determination unit 6 that determines the other vehicle 21 having the shortest inter-vehicle distance from the own vehicle 11 as the target vehicle, and When the speed of the vehicle flow differs, it is predicted that the target vehicle (other vehicle 21) will change lanes to the adjacent lane R2, and the target vehicle (other vehicle 21) travels. Since a behavior prediction part 7 for calculating the probability of lane change from the lane R1 to the adjacent lane R2 is provided, the lane change behavior according to the speed of the flow of vehicles in the lane can be predicted.

Embodiment 2.
In the first embodiment, the speed of the target vehicle differs from the speed of the flow of vehicles in the lane in which the target vehicle travels. A case where the speed is faster or slower than the speed of the vehicle flow will be described.

The configuration of the other vehicle behavior prediction device according to Embodiment 2 is the same as that of the other vehicle behavior prediction device 101 of Embodiment 1, and corresponding parts are denoted by the same reference numerals, and descriptions thereof will be omitted.

Next, another vehicle behavior prediction method by the other vehicle behavior prediction device according to Embodiment 2 will be described. FIG. 5 is a flow chart showing the processing procedure of the other vehicle behavior prediction device according to the second embodiment. Steps S401 to S407 in FIG. 5 are the same as steps S201 to S207 in FIG. 2 of Embodiment 1, respectively, and description thereof will be omitted.

In step S407, the speed of the target vehicle (other vehicle 21) is compared with the speed of the vehicle flow in the lane R1 in which the target vehicle (other vehicle 21) is traveling, and the speed of the target vehicle (other vehicle 21) is compared with that of the target vehicle ( If the vehicle flow speed is faster than the vehicle flow speed in the lane R1 in which the other vehicle 21) is traveling (Yes in step S408), the behavior prediction unit 7 predicts the vehicle flow speed in the lane R2 (in FIG. If the speed of the flow of vehicles is faster than the speed of the flow of vehicles in lane R1), the probability of changing lanes is calculated (step S409).

If the speed of the target vehicle (other vehicle 21) is not faster than the speed of the flow of vehicles in the lane R1 on which the target vehicle (other vehicle 21) travels (No in step S408), the target vehicle (other vehicle 21 ) is not slower than the speed of the flow of vehicles in the lane R1 in which the target vehicle (other vehicle 21) is traveling, that is, the speed of the target vehicle (other vehicle 21) and the speed of the target vehicle (other vehicle 21) are equal to each other. If the speed of the flow of vehicles in lane R1 is the same (No in step S410), the process returns to step S407.

When the speed of the target vehicle (other vehicle 21) is slower than the speed of the vehicle flow in the lane R1 in which the target vehicle (other vehicle 21) travels (Yes in step S410), the behavior prediction unit 7 The probability of lane change to lane R2 where the flow speed is slow (when the flow speed of vehicles in lane R2 is slower than the flow speed of vehicles in lane R1 in FIG. 3) is calculated (step S411).

In this way, the other vehicle behavior prediction device predicts the behavior of the target vehicle (other vehicle 21) based on the lane change probability calculated by the behavior prediction unit 7, and ends the process.

As described above, according to the other vehicle behavior prediction device according to the second embodiment, the speed of the target vehicle (other vehicle 21) measured by the sensor unit 2 and the target vehicle (other vehicle 21) calculated by the lane speed calculation unit 5 ) is different from the speed of the flow of vehicles in the lane R1 in which the target vehicle (other vehicle 21) is traveling, it is predicted that the target vehicle (other vehicle 21) will change lanes to the adjacent lane R2, and the speed of the target vehicle (other vehicle 21) is the target vehicle If the vehicle flow speed is faster than the vehicle flow speed in the lane R1 in which the target vehicle (other vehicle 21) is traveling, the vehicle flow speed is faster than the vehicle flow speed in the lane R1 in which the target vehicle (other vehicle 21) is traveling. is calculated, and if the speed of the target vehicle (other vehicle 21) is slower than the speed of the flow of vehicles in the lane R1 in which the target vehicle (other vehicle 21) travels, the target vehicle (other vehicle 21) travels and a behavior prediction unit 7 for calculating the probability of changing lanes to the adjacent lane where the vehicle flow speed is slower than the vehicle flow speed in the lane R1. The corresponding lane change behavior can be predicted.

Although the average speed is used as the speed of the flow of vehicles in each lane in the first and second embodiments, the present invention is not limited to this. The maximum speed may be used if the speed of the vehicle flow in the lane is increasing. Also, the minimum speed may be used when the speed of the vehicle flow in the lane is decreasing. A more accurate prediction can be made by comparing the speed difference from the target vehicle with the speed of the flow of vehicles that finally settles down.

While this application describes various exemplary embodiments and examples, various features, aspects, and functions described in one or more embodiments may not apply to particular embodiments. can be applied to the embodiments singly or in various combinations. Accordingly, numerous variations not illustrated are envisioned within the scope of the technology disclosed herein. For example, when at least one component is modified, added or omitted, and at least one component is determined and combined with the components of other embodiments.

1 map information unit, 2 sensor unit, 5 lane speed calculation unit, 6 target determination unit, 7 behavior prediction unit, 101 other vehicle behavior prediction device.

Claims (4)

a map information unit having map information and measuring the position of the own vehicle to detect the position of the lane in which the own vehicle travels and the positions of the lanes around the own vehicle from the map information;
a sensor unit that detects the speed of the own vehicle, the speed of other vehicles traveling around the own vehicle, and the position of the other vehicle relative to the own vehicle;
A lane in which the other vehicle travels is selected based on the position of the lane around the own vehicle and the relative position of the other vehicle from the own vehicle, and the flow of vehicles in each lane is selected based on the speed of the other vehicle. a calculation unit for calculating velocity;
a target determination unit that determines, as a target vehicle, the other vehicle having the shortest inter-vehicle distance to the own vehicle from among the other vehicles, based on the position of the own vehicle and the relative position of the other vehicle from the own vehicle;
a prediction unit that calculates a probability that the target vehicle will change lanes when the speed of the target vehicle and the speed of the flow of vehicles in the lane in which the target vehicle is traveling are different,
The speed of the flow of vehicles in each lane is the fastest speed among the flows of vehicles traveling in each lane when the speed of the flow of vehicles increases, and the speed of the flow of vehicles decreases. and the slowest speed among the flows of vehicles traveling in each of the lanes . When the speed of the target vehicle is higher than the speed of the flow of vehicles in the lane in which the target vehicle is traveling, the prediction unit determines that the speed of the flow of vehicles is higher than the speed of the flow of vehicles in the lane in which the target vehicle is traveling. 2. The other vehicle behavior prediction device according to claim 1, wherein it is predicted that the vehicle will change lanes to a lane with a higher speed. When the speed of the target vehicle is lower than the speed of the flow of vehicles in the lane in which the target vehicle is traveling, the prediction unit determines that the speed of the flow of vehicles is lower than the speed of the flow of vehicles in the lane in which the target vehicle is traveling. 2. The other vehicle behavior predicting device according to claim 1, wherein it is predicted that the vehicle will change lanes to a slow lane. a step of measuring the position of the own vehicle and detecting the position of the lane in which the own vehicle travels and the position of the lane around the own vehicle;
a step of detecting the speed of the own vehicle, the speed of other vehicles traveling around the own vehicle, and the position of the other vehicle relative to the own vehicle;
determining the lane in which each of the other vehicles travels based on the position of the lane around the own vehicle and the relative position of the other vehicle from the own vehicle;
calculating a vehicle flow velocity for each lane based on the other vehicle velocity;
a step of determining, from among the other vehicles, the other vehicle having the shortest inter-vehicle distance to the own vehicle as a target vehicle based on the position of the own vehicle and the position of the other vehicle relative to the own vehicle;
calculating the probability that the target vehicle will change lanes if the speed of the target vehicle and the speed of the flow of vehicles in the lane in which the target vehicle is traveling are different;
The speed of the flow of vehicles in each lane is the fastest speed among the flows of vehicles traveling in each lane when the speed of the flow of vehicles increases, and the speed of the flow of vehicles decreases. A method for predicting the behavior of other vehicles, wherein the speed is the slowest speed among the flows of vehicles traveling in each of the lanes .

Images