JP2022054265A - Automatic driving device - Google Patents

Abstract

To secure safety against a complicated traffic environment in automatic driving and to determine driving action that is excellent in versatility and robustness conforming to a norm of driving.SOLUTION: An automatic driving device comprises: a long-term prediction part 142 that selects a driving mode in which an own vehicle travels from a plurality of driving modes in which combinations of travel routes and target speeds are different from each other, on the basis of a long-term collision risk in travelling on a travel route in a period of time from a current time to a long-term predicted time and a distance by which the vehicle can travel until the long-term prediction time; a short-term prediction part 143 that determines short-term driving action on the basis of a short-term collision risk in a period of time from the current time to a short-term prediction time shorter than the long-term prediction time, in a period of time during which the own vehicle is travelling on the basis of the driving mode selected by the long-term prediction part 142; and an ultrashort-term prediction part 144 that determines ultrashort driving action different from the short-term driving action on the basis of an ultrashort-term collision risk in a period of time from the current time to an ultrashort-term prediction time shorter than the short-term prediction time, when the short-term collision risk is above a threshold.SELECTED DRAWING: Figure 4

Description

The present invention relates to an automatic driving device.

Conventionally, in the field of autonomous driving, attempts have been made to determine the driving behavior of the own vehicle by the risk potential method. In the risk-potential method, the cost function is evaluated by the cumulative value of the potential at each time within the predicted future time, and the driving behavior is determined based on the evaluation result.

Japanese Unexamined Patent Publication No. 2010-18062

When the vehicle automatically drives, lane change (ALC: Auto Lane Changing), vehicle speed maintenance system (CC: Cruise Control), inter-vehicle distance control device (ACC: Adaptive Cruise Control), lane keeping system (LKS: Lane) Various functions such as Keeping System (AEB), Collision Damage Mitigation Brake (AEB: Autonomous Emergency Breaking), and Automatic Steering Avoidance (AES) are optimally combined and operated according to the surrounding conditions. If you try to set a combination of such multiple functions according to the traffic conditions around your vehicle, it is necessary to design the transition conditions and operations of a huge number of combinations at the development stage, so a large development man-hour is required. There was a problem that it was necessary. Further, there is a problem that the versatility or robustness for a complicated traffic environment such as a confluence of an urban area or a highway is insufficient.

Therefore, the present invention has been made in view of these points, and an object thereof is to improve versatility or robustness during automatic driving in a complicated traffic environment.

The automatic driving device of one aspect of the present invention is an automatic driving device that determines the driving behavior of the own vehicle based on the potential field, and has a long-term from the present from a plurality of driving modes in which the combination of the traveling route and the target speed is different. Long-term prediction to select the driving mode in which the own vehicle travels based on the long-term collision risk when traveling on the travel route until the predicted time and the distance travelable until the long-term predicted time. Short-term based on the short-term collision risk from the present to the short-term forecast time shorter than the long-term forecast time while the own vehicle is running based on the unit and the operation mode selected by the long-term forecast unit. The short-term driving behavior is based on the short-term collision risk that determines the driving behavior and the ultra-short-term collision risk from the present to the ultra-short-term prediction time shorter than the short-term prediction time when the short-term collision risk is equal to or greater than the threshold value. It is equipped with an ultra-short-term prediction unit that determines ultra-short-term driving behavior that is different from that of the above.

The long-term prediction unit may calculate the long-term collision risk on the assumption that the obstacle detected by the own vehicle continues to move over the long-term prediction time.

In the short-term prediction unit, when the obstacle detected by the own vehicle moves over the short-term prediction time, stands still for the short-term prediction time, or moves only for a part of the short-term prediction time. The short-term driving behavior may be determined based on the short-term collision risk calculated for the vehicle.

The short-term prediction unit may determine the short-term driving behavior based on the short-term collision risk and the destination potential and lane potential corresponding to the driving mode selected by the long-term prediction unit.

The ultra-short-term prediction unit includes the ultra-short-term collision risk when an obstacle detected by the own vehicle moves over the ultra-short-term prediction time or is stationary over the ultra-short-term prediction time, and the long-term prediction unit. The ultra-short-term driving behavior may be determined based on the lane potential corresponding to the selected driving mode.

The long-term prediction unit, the short-term prediction unit, and the ultra-short-term prediction unit assume that the obstacle detected by the own vehicle moves according to both the speed and the acceleration at the time when the obstacle is detected, and perform driving behavior. You may decide.

According to the present invention, there is an effect that a driving behavior excellent in versatility and robustness can be determined at the time of automatic driving in a complicated traffic environment.

It is a schematic diagram for demonstrating an example of the structure of an automatic driving apparatus. It is a figure which shows the outline of a plurality of predictions. It is a figure which shows the outline of a plurality of predictions. It is a figure which shows the structure of a control device. It is a flowchart which shows the flow of processing in a control device. It is a flowchart which shows the flow of a short-term forecast. It is a flowchart which shows the flow of ultra-short-term prediction.

[Overview of autonomous driving equipment]
An outline of the automatic driving device according to the embodiment of the present invention will be described with reference to FIG. The automatic driving device according to the present embodiment is, for example, a device mounted on a vehicle and executing various processes for automatically traveling the vehicle.

FIG. 1 is a schematic diagram for explaining an example of the configuration of the automatic driving device 1. The automatic driving device 1 is mounted on a vehicle such as a truck and supports the driving of the own vehicle. The automatic driving device 1 determines a driving mode and a driving behavior, for example, during automatic driving. The driving mode is determined by a combination of a traveling route starting from the current position of the own vehicle and a target traveling speed. The driving behavior is, for example, the movement of the own vehicle starting from the current time, which is determined by the acceleration / deceleration speed and the turning angular velocity (hereinafter referred to as “yaw rate”) of the own vehicle. The automatic driving device 1 determines the driving mode and driving behavior of the own vehicle based on the potential field.

As shown in FIG. 1, the automatic driving device 1 has a vehicle detection unit 2, an environment recognition unit 4, a map database 6, and a control device 10.
The vehicle detection unit 2 detects the state of the own vehicle. The vehicle detection unit 2 detects the position and speed of the own vehicle. For example, the vehicle detection unit 2 has a GPS (Global Positioning System) receiver, and detects the position of the own vehicle by the radio wave received by the GPS receiver. The vehicle detection unit 2 outputs to the control device 10 travel information indicating the position and speed of the own vehicle based on the detection result of the own vehicle position.

The environment recognition unit 4 recognizes the environmental conditions around the own vehicle. For example, the environment recognition unit 4 has an external sensor such as a camera or a radar. The environment recognition unit 4 recognizes an object (for example, another vehicle, a bicycle, a pedestrian, etc.) around the own vehicle based on the output of the external sensor. Further, the environment recognition unit 4 can recognize, for example, a travelable area in addition to the position and width of the lane in which the own vehicle travels. The environment recognition unit 4 outputs peripheral information indicating the recognition result of the surrounding environment to the control device 10.

The map database 6 stores road map information. The road map information includes, for example, data showing three-dimensional coordinates of the latitude, longitude and altitude of the road. In addition, the road map information includes information on the number of lanes and the lane structure of the road on which the own vehicle travels. Further, the map database 6 can instead acquire information on the lane recognized by the environment recognition unit 4 based on the position of the own vehicle detected by the vehicle detection unit 2.

The control device 10 controls the operation of the automatic driving device 1. The control device 10 uses the potential field to determine the driving behavior of the own vehicle. The potential field is, for example, a destination potential, an obstacle potential, or a lane potential. The destination potential is a potential based on a preset attractive or repulsive force to the destination. The obstacle potential is a potential based on the repulsive force from the obstacle. The lane potential is the potential to follow a predetermined lane.

Although details will be described later, the control device 10 of the present embodiment determines a driving behavior that can minimize a cost function including a cumulative value of potential over a predetermined period and a maximum collision risk as an actual risk. .. As a result, the automatic driving device 1 can prevent the determination of the driving behavior depending on the size of the obstacle, and can realize safer automatic driving.

The control device 10 uses long-term prediction, short-term prediction, and ultra-short-term prediction, which have different prediction times and prediction methods, in order to determine driving behavior. 2 and 3 are diagrams showing an outline of these plurality of predictions.

The long-term prediction is a process of determining which of a plurality of driving modes is best to select by calculating the collision risk over the longest period, for example, a lane change process. FIG. 3A shows a plurality of operation modes that are candidates to be selected in the long-term prediction. In the long-term forecast, for example, the driving mode I ₀ in which the own vehicle _stays in the driving lane, the driving mode IR in which the own vehicle changes lane to the right lane of the driving lane, and the driving mode IR in which the own vehicle is driving. From the driving mode _IL that changes lanes to the lane on the left side of, a driving mode is selected in which the collision risk is relatively small and the mileage within the time period for which long-term prediction is to be made is relatively large.

The long-term prediction is based on a long-term cost function that uses, for example, Δt _L = 10 seconds of collision risk (hereinafter sometimes referred to as “long-term collision risk”) and the distance travelable between Δt _L as parameters. This is a process for selecting, and since it involves a large amount of calculation load as compared with the short-term prediction described later, it is executed in a cycle of, for example, about 200 milliseconds to 1 second.

式（１）における第１項は、各運転モードに対応する経路における無次元化された最終到達距離（Δｔ_Ｌの間に走行可能な距離）であり、第２項は、各経路を通過する際の正規化された最大リスクである。式（１）はこれらの２項の重み付き和として長期コスト関数を定義している。ここで、V^targetは目標速度、S_tendは経路の終点までの道のり距離、R_max ^collは経路中の最大衝突リスク、R_th ^collは経路生成を打ち切るリスクの閾値である。 The long-term cost function used in the long-term forecast is expressed by, for example, the following equation (1).

The first term in the equation (1) is a dimensionless final reach (distance travelable during Δt _L ) in the path corresponding to each operation mode, and the second term passes through each path. This is the normalized maximum risk. Equation (1) defines a long-term cost function as the weighted sum of these two terms. Here, V ^target is the target velocity, S _tend is the distance to the end point of the route, R _max ^coll is the maximum collision risk in the route, and R _th ^coll is the threshold value of the risk of terminating the route generation.

Since the long-term forecast time is relatively long, it is unlikely that moving dynamic obstacles will stay in the same place. In addition, the long-term collision risk detected in the long-term prediction can be avoided by changing the driving behavior. Therefore, in the long-term prediction, the dynamic obstacles around the own vehicle have the same speed and acceleration / deceleration as the current speed and acceleration / deceleration. The cost function is calculated on the assumption that it keeps moving at the acceleration / deceleration.

The short-term forecast is a forecast regarding the near future state based on the potential field corresponding to the driving mode determined in the long-term forecast, and executes a driving action corresponding to, for example, a lane keeping system, an inter-vehicle distance control device, and a vehicle speed maintaining system. .. The short-term prediction is a process of selecting a driving behavior by predicting a collision risk in a short-term prediction time shorter than the long-term prediction time. Short-term prediction is based on, for example, Δt _S = collision risk over 2 to 5 seconds (hereinafter sometimes referred to as “short-term collision risk”) and short-term cost function with destination potential and lane potential as parameters. This is the process to select. The short-term prediction is executed in a cycle of, for example, about 10 milliseconds to 50 milliseconds because it is necessary to determine the latest driving behavior.

FIG. 3B shows a plurality of candidate driving behaviors selected in the short-term prediction with a plurality of arrows. In the short-term forecast, the driving behavior that minimizes the short-term cost function is selected from these plurality of driving behaviors.

式（２）における第１項は基本走行ポテンシャルU^baseの短期予測時間内における累積値であり、第２項は複数の運転行動それぞれの衝突リスクのうち最大のリスクR_max ^collと予測時間の積である。また、(X_t ^front, Y_t ^front)は自車両前面位置の座標を表す。なお、基本走行ポテンシャルは目的地ポテンシャル及び車線ポテンシャルを含んでいる。U^dst(X,Y)は目的地ポテンシャルであり、U^laneは車線ポテンシャルである。これらを加算した値が式（２）における基本走行ポテンシャルU^baseである。 The short-term cost function is expressed by, for example, the following equation (2).

The first term in equation (2) is the cumulative value of the basic driving potential U ^base within the short-term predicted time, and the second term is the product of the maximum risk R _max ^coll and the predicted time among the collision risks of each of the multiple driving behaviors. Is. In addition, (X _t ^front , Y _t ^front ) represents the coordinates of the front position of the own vehicle. The basic driving potential includes the destination potential and the lane potential. U ^dst (X, Y) is the destination potential and U ^lane is the lane potential. The value obtained by adding these is the basic running potential U ^base in the equation (2).

The basic traveling potential includes a destination potential for directing the own vehicle to a preset destination at a set speed (for example, a speed limit) and a lane potential for making the own vehicle follow the lane. The destination potential is, for example, the potential obtained by adding the speed difference potential proportional to the speed difference between the target speed and the speed of the own vehicle and the directional difference potential proportional to the directional difference between the target position and the position of the own vehicle. be. Further, the lane potential includes, for example, an attractive force potential that generates the own vehicle in the center of a predetermined lane and a repulsive force potential that is generated at both ends of the lane.

In short-term forecasts, it is important to prevent your vehicle from becoming a dangerous situation. Therefore, in the short-term prediction, the driving behavior is determined in consideration of the risks in both the case where the dynamic obstacle moves and the case where the dynamic obstacle stays in the same place, for example.

Ultra-short-term prediction is a process of selecting driving behavior by predicting collision risk in an ultra-short-term prediction time shorter than the short-term prediction time, for example, for automatic steering avoidance processing or at least one of the functions of collision damage mitigation braking. Equivalent to. Ultra-short-term prediction is a process of selecting driving behavior based on an ultra-short-term cost function with collision risk over a time of, for example, Δt _S' = 1 second (hereinafter, may be referred to as “ultra-short-term collision risk”) as a parameter. be.

FIG. 3 (c) shows a plurality of candidate driving behaviors selected in the ultra-short-term prediction by a plurality of arrows. In the ultra-short-term prediction, the driving behavior that minimizes the ultra-short-term cost function is selected from these plurality of driving behaviors.

超短期予測においては、危険が目前に迫っている状況なので、動的障害物の位置が超短期予測時間にわたって移動するという前提で、衝突を回避可能な安全な領域を探索する。超短期予測においては、障害物を緊急回避することが重要なので、運転行動を探索する際の自車両の加減速度及び旋回角速度の許容値が短期予測よりも大きくする。 The ultra-short-term cost function is expressed by, for example, the following equation (3).

In ultra-short-term prediction, the danger is imminent, so we will search for a safe area where collisions can be avoided on the assumption that the position of the dynamic obstacle will move over the ultra-short-term prediction time. In ultra-short-term prediction, it is important to avoid obstacles urgently, so the permissible values of the acceleration / deceleration speed and turning angular velocity of the own vehicle when searching for driving behavior are larger than in the short-term prediction.

As described above, the automatic driving device 1 determines the driving behavior by using the long-term prediction, the short-term prediction, and the ultra-short-term prediction for different purposes. Then, the automatic driving device 1 executes the long-term prediction, the short-term prediction, and the ultra-short-term prediction in parallel at different cycles. Short-term forecasts and ultra-short-term forecasts are carried out in the same cycle, and long-term forecasts are carried out in a longer cycle than the short-term forecast and ultra-short-term forecast cycles. By operating the automatic driving device 1 in this way, the delay time from the completion of the long-term prediction to the determination of the driving behavior can be reduced as compared with the case where the short-term prediction and the ultra-short-term prediction are performed. , Driving behavior during automatic driving can be determined in real time.
Hereinafter, the configuration and operation of the control device 10 will be described in detail.

[Detailed configuration of control device 10]
FIG. 4 is a diagram showing the configuration of the control device 10. The control device 10 has a storage unit 12 and a control unit 14. The storage unit 12 includes, for example, a ROM (Read Only Memory) and a RAM (Random Access Memory). The storage unit 12 stores programs and various data for execution by the control unit 14.

The control unit 14 is, for example, a CPU (Central Processing Unit). The control unit 14 functions as an information acquisition unit 141, a long-term prediction unit 142, a short-term prediction unit 143, an ultra-short-term prediction unit 144, and a driving behavior determination unit 145 by executing a program stored in the storage unit 12.

The information acquisition unit 141 acquires the traveling information of the own vehicle. For example, the information acquisition unit 141 acquires the position and speed of the own vehicle while traveling. The information acquisition unit 141 acquires the position and speed of the own vehicle from the detection result of the vehicle detection unit 2 (FIG. 1).

In addition, the information acquisition unit 141 acquires information about objects around the own vehicle. For example, the information acquisition unit 141 acquires peripheral information about an object (another vehicle, a pedestrian, etc.) existing in the traveling direction of the own vehicle from the detection result of the environment recognition unit 4 (FIG. 1).

In addition, the information acquisition unit 141 acquires target information regarding a target position to be traveled and a target speed. The target position is, for example, a position ahead of the own vehicle by a predetermined distance (200 m as an example). The target position may be an arbitrary point set in the road map information stored in the map database 6. The target speed is, for example, the legal speed of the lane. The information acquisition unit 141 can acquire target information by referring to, for example, the road map information stored in the map database 6. The information acquisition unit 141 inputs the acquired driving information, surrounding information, and road map information to the long-term prediction unit 142, the short-term prediction unit 143, and the ultra-short-term prediction unit 144.

長期予測部１４２は、移行した運転モードを運転行動決定部１４５に通知する。長期予測部１４２は、移行した運転モードを短期予測部１４３に通知してもよい。 [Long-term forecast]
The long-term forecasting unit 142 executes the long-term forecasting. The long-term prediction unit 142 can be used between a plurality of operation modes having different combinations of travel routes and target speeds, a long-term collision risk when traveling on a travel route from the present to the long-term forecast time, and a long-term forecast time. Select the driving mode in which the own vehicle travels based on the mileage and the travelable distance. The long-term prediction unit 142 calculates a long-term cost function C ^path (I) for each of a plurality of operation mode candidates using, for example, the above formula (1), and based on the following formula (4), the long-term is long-term. Select the operating mode that minimizes the cost function. Further, the long-term prediction unit 142 shifts to the selected driving mode by determining a state such as whether the own vehicle can run stably or whether the winker is ON.

The long-term prediction unit 142 notifies the driving behavior determination unit 145 of the shifted operation mode. The long-term prediction unit 142 may notify the short-term prediction unit 143 of the shifted operation mode.

The long-term prediction unit 142 may calculate the long-term collision risk on the assumption that the obstacle detected by the own vehicle continues to move for the long-term prediction time. The long-term prediction unit 142 may calculate the long-term collision risk, for example, assuming that the obstacle continues to move at the speed and acceleration at the time when the obstacle is detected.

[Short-term forecast]
The short-term prediction unit 143 is based on the short-term collision risk from the present to the short-term prediction time shorter than the long-term prediction time while the own vehicle is running based on the driving mode selected by the long-term prediction unit 142. Determine driving behavior. The short-term prediction unit 143 acquires the operation mode selected by the long-term prediction unit 142, and determines the optimum short-term driving behavior in the potential field in the acquired operation mode. That is, the short-term prediction unit 143 determines the short-term driving behavior based on the short-term collision risk and the destination potential and lane potential corresponding to the driving mode selected by the long-term prediction unit 142.

The short-term prediction unit 143 determines the short-term driving behavior by updating the parameters related to the potential field based on the operation mode determined by the long-term prediction unit 142 and calculating the short-term cost function. The short-term prediction unit 143 notifies the driving behavior determination unit 145 of the determined short-term driving behavior. The short-term prediction unit 143 may notify the ultra-short-term prediction unit 144 of the determined short-term driving behavior.

The short-term prediction unit 143 calculates a short-term cost function including the short-term collision risk during running from the present to the short-term prediction time as a parameter for each of a plurality of driving behaviors. The short-term prediction unit 143 can calculate a short-term cost function for each of a plurality of driving behavior candidates based on, for example, the above equation (2), but the short-term prediction unit 143 has a short-term collision risk and a destination. A short-term cost function may be calculated that includes the potential and the lane potential as parameters. Further, the short-term prediction unit 143 may determine the acceleration / deceleration speed and the yaw rate of the own vehicle as the driving behavior of the own vehicle. Then, the short-term prediction unit 143 may calculate a short-term cost function having a regularization term for the driving behavior including the acceleration / deceleration speed and the yaw rate of the own vehicle as parameters, as shown by the following equation (5).

The short-term prediction unit 143 specifies the basic driving potential by specifying the destination potential and the lane potential using the information acquired by the information acquisition unit 141.

The third and fourth terms in the equation (5) are regularization terms necessary for smooth operation. α means acceleration / deceleration, γ means yaw rate, w _α is the weight of acceleration / deceleration, and w _γ is the weight of yaw rate.

The short-term prediction unit 143 obtains the collision risk with an object around the own vehicle within a predetermined prediction time as the actual risk included in the short-term cost function. For example, the short-term prediction unit 143 obtains the maximum collision risk with respect to the object detected by the environment recognition unit 4. When there are a plurality of objects in the vicinity, the short-term prediction unit 143 obtains the maximum collision risk for each object. The short-term prediction unit 143 obtains the maximum collision risk from the obtained maximum collision risks for a plurality of objects.

Using the maximum collision risk has the following advantages. Here, it is assumed that there is a large object (for example, another vehicle) and a small object (for example, a pedestrian) in front of the traveling direction of the own vehicle, and it is necessary to surely avoid the small object for safety. .. When the cumulative value of the collision risk is used, the driving behavior depends on the size of the object, so that there is a possibility of avoiding a large object and heading for a small object. On the other hand, when the maximum collision risk is used, small objects with high risk can be avoided, and safe driving behavior becomes possible.

The short-term prediction unit 143 determines the optimum driving behavior (acceleration / deceleration and yaw rate) that minimizes the short-term cost function based on the following equation (6).

In this way, when the short-term prediction unit 143 selects the driving behavior when the value of the short-term prediction cost function is minimized, an obstacle in front or an obstacle in the rear approaching the own vehicle exists at a very close position. At that time, even if any of the driving behaviors (acceleration / deceleration and yaw rate) that can be selected by the short-term prediction unit 143 is selected, the collision risk may become a high value. If the own vehicle performs such driving behavior, speed maintenance or lane maintenance is prioritized, and there is a risk of collision with an obstacle.

Therefore, the short-term prediction unit 143 may drive the own vehicle by the optimum driving behavior by comparing the short-term collision risk when the determined optimum driving behavior is performed with the threshold value R _th , or it is dangerous in the optimum driving behavior. Is inevitable, and it is determined whether other driving behavior based on ultra-short-term prediction is necessary. The threshold value R _th is determined based on the likelihood of sudden acceleration / deceleration (for example, sudden braking), and the smaller the threshold value R _th is, the more sudden acceleration / deceleration is performed by the ultra-short-term prediction unit 144. Is easier to select. When the short-term prediction unit 143 instructs the ultra-short-term prediction unit 144 to determine the driving behavior, at least one of a warning sound or a display indicating that there is a risk of collision or that sudden acceleration / deceleration is performed. Depending on the situation, the occupants of the own vehicle may be notified.

In order to improve safety, the short-term prediction unit 143 determines that the obstacle detected by the own vehicle moves over the short-term prediction time, stands still for the short-term prediction time, or is a part of the short-term prediction time. The short-term driving behavior may be determined based on the short-term collision risk calculated for the case of moving only. The short-term prediction unit 143 may determine short-term driving behavior based on the short-term collision risk calculated for a plurality (for example, all) of these cases. The short-term prediction unit 143 selects, for example, a short-term driving behavior when the short-term collision risk is less than the threshold value R _th among the short-term collision risks based on all the calculated driving behaviors, and determines the selected short-term driving behavior. Notify 145. When a plurality of short-term collision risks are less than the threshold value R _th , the short-term prediction unit 143 selects the short-term driving behavior that minimizes the short-term collision risk.

On the other hand, when all the calculated short-term collision risks are equal to or higher than the threshold value, or when the short-term collision risk when the short-term cost function is minimized is equal to or higher than the threshold value R _th , the short-term prediction unit 143 is based on the ultra-short-term prediction. Instruct the ultra-short-term prediction unit 144 to determine the driving behavior.

[Ultra-short-term forecast]
When the short-term collision risk is equal to or higher than the threshold value, the ultra-short-term prediction unit 144 performs ultra-short-term driving behavior different from the short-term driving behavior based on the ultra-short-term collision risk from the present to the ultra-short-term prediction time shorter than the short-term prediction time. To decide. The ultra-short-term prediction unit 144 starts from the present when, for example, all the short-term collision risks calculated by the short-term prediction unit 143 are equal to or greater than the threshold, or when the short-term collision risk when the short-term cost function is minimized is equal to or greater than the threshold. The ultra-short-term collision risk during driving up to the ultra-short-term predicted time shorter than the short-term predicted time, and the ultra-short-term cost function including the ultra-short-term collision risk as parameters are calculated. The ultra-short-term prediction unit 144 may calculate an ultra-short-term cost function including ultra-short-term collision risk, destination potential, and lane potential as parameters.

The ultra-short-term prediction unit 144 can perform an ultra-short-term cost function including ultra-short-term collision risk and lane potential as parameters for each of a plurality of driving behavior candidates, for example, based on the above equation (3). As shown by the following equation (7), the ultra-short-term prediction unit 144 determines the driving behavior using the maximum risk R _max ^coll in the ultra-short-term prediction as a long-term and short-term cost function. Alternatively, as shown in equations (8), (9), and (10), an ultra-short-term cost function that considers only the lane potential as the basic driving potential, an ultra-short-term cost function that considers both the destination potential and the lane potential, and further. An ultra-short-term cost function having a regularization term including the acceleration / deceleration of the own vehicle and the yaw rate as parameters may be calculated.

The acceleration / deceleration weight _w'α and the yaw rate weight _w'α in the third and fourth terms of the equation (10) are the third and fourth terms of the short-term cost prediction function (formula (5)) in the short-term prediction. It is smaller than the weight of acceleration / deceleration w _α and the weight of yaw rate w _γ contained in. That is, in the ultra-short-term cost function, the effect of the acceleration / deceleration and the yaw rate is smaller than the effect of the acceleration / deceleration and the yaw rate in the short-term cost function, and the ultra-short-term prediction unit 144 tends to increase the acceleration / deceleration and the yaw rate. In this case, the short-term prediction unit 143 calculates a short-term cost function including a regularization term for the driving behavior of the own vehicle, and the ultra-short-term prediction unit 144 includes a regularization term for the driving behavior having a smaller weight than the short-term cost function. Calculate the ultra-short-term cost function. As described above, the ultra-short-term prediction unit 144 may calculate the ultra-short-term cost function including the acceleration / deceleration rate and the yaw rate having a smaller weight than the short-term cost function as parameters. By using such an ultra-short-term cost function by the ultra-short-term prediction unit 144, it becomes possible to avoid danger by applying a sudden brake or suddenly accelerating.

The ultra-short-term prediction unit 144 determines the optimum driving behavior (acceleration / deceleration and yaw rate) that minimizes the ultra-short-term cost function based on the following equation (11). The ultra-short-term prediction unit 144 replaces the optimum driving behavior determined by the short-term prediction unit 143 with the optimum driving behavior determined based on the ultra-short-term cost function.

The ultra-short-term prediction unit 144 sets the ultra-short-term collision risk when the obstacle detected by the own vehicle moves over the ultra-short-term prediction time or stands still for the ultra-short-term prediction time, and the operation mode selected by the long-term prediction unit. Ultra-short-term driving behavior may be determined based on the corresponding lane potential. By operating the ultra-short-term prediction unit 144 in this way, safe driving behavior is selected on the assumption that the position of the dynamic obstacle will continue to move during the ultra-short-term prediction time in a situation where danger is imminent. can do.

ここで、d_minは周辺の物体との最小の距離であり、d_aveは複数の周辺物体との平均距離である。 If the peripheral obstacles cannot be avoided by minimizing the risk, the ultra-short-term prediction unit 144 may calculate an ultra-short-term cost function including the distance to the obstacles around the own vehicle as a parameter. That is, the ultra-short-term prediction unit 144 may determine the driving behavior based on the ultra-short-term cost function including the distance to the surrounding object as a parameter. The ultra-short-term cost function introduced as a parameter of the distance to the obstacle with respect to the equation (7) is expressed by the following equation (12).

Here, d _min is the minimum distance to surrounding objects, and d _ave is the average distance to multiple peripheral objects.

d _min and d _ave are calculated by the following equation (13). (X ^ts'ego , Y _{ts' ego} ⁾ indicates the position of the own vehicle after the time ts _' , and (X _{i, ts'} ^obj , Y _{i, ts'} ^obj ) is the i-th after the time ts _' . Indicates the position of the object.

The ultra-short-term prediction unit 144 determines the driving behavior based on the collision risk of the ultra-short-term prediction time shorter than the short-term prediction time, which is the time for the short-term prediction unit 143 to select the driving behavior. By making predictions in such a short time by the ultra-short-term prediction unit 144, even if the short-term collision risk corresponding to the driving behavior selected by the short-term prediction unit 143 is large, the ultra-short-term prediction time is shorter than the short-term prediction time. It is easy to distinguish between relatively dangerous driving behavior and relatively safe driving behavior within the range of. The long-term prediction unit 142, the short-term prediction unit 143, and the ultra-short-term prediction unit 144 determine the driving behavior on the assumption that the obstacle moves according to both the speed and the acceleration at the time when the obstacle is detected. May be good.

[Determination of driving behavior]
The driving behavior determination unit 145 determines to drive the own vehicle with the driving behavior notified by the ultra-short-term prediction unit 144 or the driving behavior notified by the driving behavior determination unit 145, and the driving behavior data indicating the determined driving behavior. Is notified to the device or unit that controls the running of the own vehicle. That is, when the ultra-short-term prediction unit 144 calculates the ultra-short-term cost function, the driving behavior determination unit 145 determines the driving behavior based on the ultra-short-term cost function, and the ultra-short-term prediction unit 144 calculates the ultra-short-term cost function. If not, determine driving behavior based on a short-term cost function.

[Flow chart of processing in the control device 10]
FIG. 5 is a flowchart showing the flow of processing in the control device 10. The control device 10 repeats the processes from S11 to S18 shown in FIG. 5 while the engine of the own vehicle is running.

First, the information acquisition unit 141 acquires various information from the vehicle detection unit 2, the environment recognition unit 4, and the map database 6 (S11), and calculates a potential map based on the acquired information (S12). The potential map is data showing the destination potential and the lane potential.

The long-term prediction unit 142 selects the optimum operation mode from the plurality of operation modes based on the potential map (S13). Subsequently, the short-term prediction unit 143 selects the optimum driving behavior by executing the short-term prediction using the potential corresponding to the operation mode selected by the long-term prediction unit 142 (S14). The flow of processing for short-term forecasts will be described later.

When the short-term collision risk corresponding to the optimum short-term driving behavior selected by the short-term prediction unit 143 is equal to or higher than the threshold value (YES in S15), it is determined that the ultra-short-term prediction is necessary, and the ultra-short-term prediction is executed. Instruct the short-term prediction unit 144. The ultra-short-term prediction unit 144 executes ultra-short-term prediction based on the instruction (S16). The flow of processing for ultra-short-term forecasts will be described later.

When the short-term collision risk corresponding to the optimum short-term driving behavior selected by the short-term prediction unit 143 is less than the threshold value (NO in S15), the driving behavior determination unit 145 uses the short-term driving behavior selected by the short-term prediction unit 143 as its own vehicle. (S17). When the short-term collision risk corresponding to the optimum short-term driving behavior selected by the short-term prediction unit 143 is equal to or higher than the threshold value (YES in S15), the driving behavior determination unit 145 determines the ultra-short-term driving behavior selected by the ultra-short-term prediction unit 144. Determines the driving behavior of the own vehicle (S17). The control device 10 repeats the processes from S11 to S18 until the operation is completed (NO in S18).

[Flow chart for short-term forecast]
FIG. 6 is a flowchart showing the flow of short-term forecast. First, the short-term prediction unit 143 selects a driving behavior to be investigated for suitability by calculating a short-term cost function from a plurality of driving behaviors (S141). Subsequently, the short-term prediction unit 143 identifies the state of the own vehicle at time t _s (S142). Specifically, the short-term prediction unit 143 specifies the position of the own vehicle (for example, the X coordinate and the Y coordinate of the center of the rear wheel axis), the yaw angle, and the speed.

Subsequently, the short-term prediction unit 143 calculates the basic running potential (S143). Specifically, the short-term prediction unit 143 calculates the basic driving potential by adding the destination potential and the lane potential. Further, the short-term prediction unit 143 calculates the collision risk within the short-term prediction time (S144). The short-term prediction unit 143 calculates the cost based on the short-term cost function including the calculated basic running potential and collision risk as parameters (S145), and stores the calculated cost in the storage unit 12 in association with the driving behavior.

The short-term prediction unit 143 determines whether or not the cost has been calculated for all the selectable driving behaviors (S146), and when all the driving behaviors have been selected and the cost has not been calculated (NO in S146), S141 Return the process to. When the short-term prediction unit 143 calculates the cost for all selectable driving behaviors (YES in S146), the short-term driving behavior is the driving behavior with the minimum cost among the plurality of driving behaviors stored in the storage unit 12. (S147).

[Flowchart for ultra-short-term forecast]
FIG. 7 is a flowchart showing the flow of ultra-short-term prediction. First, the ultra-short-term prediction unit 144 selects an ultra-short-term cost function from a plurality of driving behaviors to be investigated for suitability (S161). Subsequently, the ultra-short-term prediction unit 144 identifies the state of the own vehicle (S162). Specifically, the ultra-short-term prediction unit 144 specifies the position, yaw angle, and speed of the own vehicle at time t _s' .

Subsequently, the ultra-short-term prediction unit 144 calculates the lane potential (S163). Further, the ultra-short-term prediction unit 144 calculates the collision risk within the short-term prediction time (S164). The ultra-short-term prediction unit 144 calculates the cost based on the ultra-short-term cost function including the calculated lane potential and collision risk as parameters (S165), and stores the calculated cost in the storage unit 12 in association with the driving behavior.

The ultra-short-term prediction unit 144 determines whether or not the cost has been calculated for all the selectable driving behaviors (S166), and when all the driving behaviors have been selected and the cost has not been calculated (NO in S166). The process is returned to S161. When the ultra-short-term prediction unit 144 calculates the cost for all selectable driving behaviors (YES in S166), the ultra-short-term prediction unit 144 determines the driving behavior with the minimum cost among the plurality of driving behaviors stored in the storage unit 12. Determine the driving behavior (S167).

[Effect of control device 10]
As described above, the control device 10 includes the potential as a parameter and determines the final driving behavior by minimizing the cost functions of the different long-term prediction, short-term prediction, and ultra-short-term prediction. The control device 10 can determine the optimum driving behavior according to the traffic conditions around the own vehicle by changing the parameters included in the cost function according to the purpose of each prediction. As a result, various types such as lane change (ALC), vehicle speed maintenance system (CC), inter-vehicle distance control device (ACC), lane maintenance system (LKS), collision damage mitigation brake (AEB), automatic steering avoidance (AES), etc. It can be optimally operated according to the situation around the driving behavior corresponding to the function. Therefore, it is possible to ensure safety against complicated traffic environments in autonomous driving and to determine driving behavior with excellent versatility and robustness in accordance with driving standards, which improves safety and enables normative driving. realizable.

If a combination of multiple driving support functions as described above is to be set in advance for each traffic condition around the own vehicle, it is necessary to determine the operation of a huge number of combinations at the development stage, which requires a large development man-hour. It takes. In addition, the versatility and robustness for complicated traffic environments such as urban areas or confluences of highways are insufficient. On the other hand, as in the control device 10 according to the present embodiment, the operation mode is determined based on the long-term prediction, and the short-term prediction and the ultra-short-term prediction are used based on the potential of running in the determined operation mode. By determining the driving behavior, versatility and robustness can be improved.

Further, the ultra-short-term prediction unit 144 superimposes when all the short-term collision risks calculated by the short-term prediction unit 143 are equal to or greater than the threshold value, or when the short-term collision risk when the short-term cost function is minimized is equal to or greater than the threshold value. The short-term collision risk is calculated, and the driving behavior is determined based on the ultra-short-term cost function including the ultra-short-term collision risk as a parameter. In this way, when the risk is not sufficiently reduced by the driving behavior determined in the short-term prediction, the control device 10 performs the driving behavior that can avoid the risk by the ultra-short-term prediction in which the conditions of acceleration / deceleration and yaw rate are relaxed. decide.

By operating the control device 10 in this way, it is possible to avoid a collision risk that cannot be avoided if the automatic operation is performed based on the predicted time of a single length. It also facilitates proper driving behavior to ensure maximum safety against sudden jumps and interruptions.

Although the present invention has been described above using the embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments, and various modifications and changes can be made within the scope of the gist. be. For example, all or part of the device can be functionally or physically distributed / integrated in any unit. Also included in the embodiments of the present invention are new embodiments resulting from any combination of the plurality of embodiments. The effect of the new embodiment produced by the combination has the effect of the original embodiment together.

1 Automatic driving device 2 Vehicle detection unit 4 Environment recognition unit 6 Map database 10 Control device 12 Storage unit 14 Control unit 141 Information acquisition unit 142 Long-term prediction unit 143 Short-term prediction unit 144 Ultra-short-term prediction unit 145 Driving behavior decision unit

Claims (6)

It is an automatic driving device that determines the driving behavior of the own vehicle based on the potential field.
The long-term collision risk when traveling on the travel route from the present to the long-term predicted time from multiple operation modes with different combinations of travel routes and target speeds, and the distance that can be traveled until the long-term predicted time. Based on the above, a long-term prediction unit that selects the driving mode in which the own vehicle travels, and
While the own vehicle is running based on the driving mode selected by the long-term prediction unit, short-term driving behavior is performed based on the short-term collision risk from the present to the short-term prediction time shorter than the long-term prediction time. Short-term forecasting department to decide,
When the short-term collision risk is equal to or higher than the threshold value, the ultra-short-term driving behavior different from the short-term driving behavior is determined based on the ultra-short-term collision risk from the present to the ultra-short-term predicted time shorter than the short-term predicted time. Short-term prediction department and
Equipped with an automatic driving device. The long-term prediction unit calculates the long-term collision risk on the assumption that the obstacle detected by the own vehicle continues to move over the long-term prediction time.
The automatic driving device according to claim 1. In the short-term prediction unit, when the obstacle detected by the own vehicle moves over the short-term prediction time, stands still for the short-term prediction time, or moves only for a part of the short-term prediction time. The short-term driving behavior is determined based on the short-term collision risk calculated for the vehicle.
The automatic driving device according to claim 1 or 2. The short-term prediction unit determines the short-term driving behavior based on the short-term collision risk and the destination potential and lane potential corresponding to the driving mode selected by the long-term prediction unit.
The automatic driving device according to claim 3. The ultra-short-term prediction unit includes the ultra-short-term collision risk when an obstacle detected by the own vehicle moves over the ultra-short-term prediction time or is stationary over the ultra-short-term prediction time, and the long-term prediction unit. The ultra-short-term driving behavior is determined based on the lane potential corresponding to the selected driving mode.
The automatic driving device according to any one of claims 1 to 4. The long-term prediction unit, the short-term prediction unit, and the ultra-short-term prediction unit assume that the obstacle detected by the own vehicle moves according to both the speed and the acceleration at the time when the obstacle is detected, and perform driving behavior. decide,
The automatic driving device according to any one of claims 1 to 5.

Images