JP2020203587A - Automatic driving system - Google Patents

Abstract

To provide an automatic driving system capable of performing travel support even in a case where the kind of an object cannot be specified.SOLUTION: An automatic driving system includes an external sensor 2 for acquiring external information on a vehicle, and a recognition determination device 6 for calculating an object track of the vehicle so as to avoid a collision with an object on the basis of information of the external sensor 2. The recognition determination device 6 determines the kind of the object when the external sensor 2 detects information on the object in an automatic driving state of system responsibility of the vehicle, determines whether or not the object is moving if the kind of the object cannot be specified, and performs driving support according to a determination result.SELECTED DRAWING: Figure 1

Description

The present invention relates to an automated driving system.

As a high safety technology for an automatic driving system, for example, there is a vehicle alarm device described in Patent Document 1. Patent Document 1 includes an object child / adult identification unit and an alarm determination unit. When the object child / adult identification unit detects a "person" from an image in front of the vehicle captured by an imaging device. , The detected "person" is identified as a "child" or an "adult", and the alarm determination unit sends the driver of the own vehicle according to the identification result of the object child / adult identification unit. A vehicle alarm device that outputs a warning alert is shown. By doing this, if the object is a child, it is judged that there is a high risk of jumping out on the road, the warning range is set large, and if the object is an adult, there is a risk of jumping out on the road. It can be judged to be low and the alarm range can be set low. That is, it is said that an alarm can be output in consideration of the risk of popping out according to the type of the object.

Further, there is Patent Document 2 as a prior art. In Patent Document 2, the risk potential of an object around the own vehicle and the virtual risk potential that predicts the possibility that the risk will increase in the future are calculated, and the route and speed of the own vehicle are calculated based on this risk potential and the virtual risk potential. The planned driving assistance technology is disclosed.

Japanese Unexamined Patent Publication No. 2014-78155 Japanese Unexamined Patent Publication No. 2017-182568

In the technique described in Patent Document 1, whether the detected "person" is a "child" or an "adult" is identified and an alarm is issued according to the type of the object (object). No consideration was given to what to do if the object could not be identified.

Further, in the technique described in Patent Document 2, the route and speed of the own vehicle are planned based on the risk potential and the virtual risk potential, but the coping method when the object cannot be specified is considered. There wasn't.

An object of the present invention is to provide an automatic driving system capable of providing driving support even when the type of an object cannot be specified.

In order to achieve the above object, in the present invention, an outside world sensor that acquires outside world information of a vehicle and a cognitive determination device that calculates a target trajectory of the vehicle so as to avoid a collision with an object based on the information of the outside world sensor. It is an automatic driving system equipped with
The cognitive determination device determines the type of the object when the external sensor detects the information of the object while the vehicle is in the system-responsible automatic driving state, and when the type of the object cannot be specified, the object moves. It is characterized in that it determines whether or not it is appropriate and provides driving support according to the determination result.

According to the present invention, it is possible to provide an automatic driving system capable of providing driving support even when the type of an object cannot be specified.

It is a system block diagram of the vehicle-mounted control system which concerns on 1st Embodiment of this invention. It is a block block diagram of the cognitive determination device which concerns on 1st Example of this invention. It is a figure which shows the avoidance trajectory when an object whose type can be specified exists. It is a figure which shows the avoidance trajectory when the static object of an unspecified kind exists. It is a figure which shows the avoidance trajectory when there is a dynamic object of which the kind cannot be specified. It is a flowchart of the responsibility determination part which concerns on 1st Embodiment of this invention. It is a figure which shows the operation of the automatic driving system when the object which can specify the type exists. It is a figure which shows the operation of the automatic driving system when the static object of an unspecified kind exists. It is a figure which shows the operation of the automatic driving system when the dynamic object of an unspecified kind exists. It is a flowchart of the responsibility determination part which concerns on 2nd Embodiment of this invention. It is a system block diagram of the vehicle-mounted control system which concerns on 3rd Embodiment of this invention. It is a flowchart of the responsibility determination part which concerns on 3rd Embodiment of this invention.

An embodiment of the present invention will be described prior to the description of the examples of the present invention. In the following explanation, it is assumed that a moving body capable of recognizing the surrounding environment and performing automatic driving based on the information is used. A vehicle is used as an example of a moving body, but the present invention is not limited thereto.

In the embodiment of the present invention, the position, speed and type of an object around the vehicle are recognized from the sensor information mounted on the vehicle, and the collision risk of the object is predicted based on the position, speed and type of the object. The present invention relates to an automatic operation system that avoids a collision with the object based on the collision risk. In the present embodiment, when there is an object whose type can be specified, the own vehicle calculates a collision avoidance trajectory according to the type of the object, and continues the system-responsible automatic driving based on the trajectory. In addition, if there is a static object of unknown type, the own vehicle will continue the system-responsible automatic driving. On the other hand, if an unknown type of dynamic object exists, the own vehicle switches from system-responsible automatic driving to driver-responsible automatic driving, and notifies the driving observer that the driving is driver-responsible automatic driving. , Requesting that the handle be gripped, etc.

Here, the dynamic object is an object that can be moved like another vehicle or a pedestrian, and the static object is an object that cannot be moved like a building. In addition, system-responsible automatic driving is the automatic driving level defined by SAE (Society of Automotive Engineers) and level 3 or higher (excluding emergencies and outside the ODD (Operational Design Domain) range), and the driving monitor. Autonomous driving of responsibility is level 2.

By applying the automatic driving system shown in this embodiment, when the type of object cannot be specified, the automatic driving level is appropriately changed according to whether it is a dynamic object or a static object, and driving safety and automatic operation are performed. The availability of the driving system can be compatible. In other words, if the accurate risk prediction of the object is not possible "the type of the object is unknown, but the object is dynamic", by switching to the driver-responsible automatic operation, the driver is informed of the possibility that the accurate risk prediction cannot be made in advance. It is possible to improve the safety of the system. When the risk of an object can be predicted accurately "when the type of object is unknown, but the object is static", the availability of the autonomous driving system can be improved by continuing the automatic operation of system responsibility.

A preferred embodiment of the present invention will be described below with reference to the drawings. The mimicry numerical values and the like shown in the following embodiments are merely examples for facilitating the understanding of the invention, and are not limited thereto unless otherwise specified.

Hereinafter, examples of the present invention will be described with reference to the accompanying drawings. Similar components are designated by the same reference numerals, and the same description will not be repeated.

The various components of the present invention do not necessarily have to be independent of each other, and one component is composed of a plurality of members, a plurality of components are composed of one member, and a certain component is different. It is allowed that a part of one component overlaps with a part of another component.

FIG. 1 is a system configuration diagram of an in-vehicle control system according to a first embodiment of the present invention. As shown in FIG. 1, the in-vehicle control system 1 includes an external sensor 2 that acquires information on the outside world of the own vehicle, an internal sensor 3 that detects the internal state of the own vehicle, and detection of the position of the own vehicle and a destination. The navigation system 4 that calculates the target route to the destination, the HMI device 5 (HMI: Human Machine Interface) that exchanges information between the driver (user) and the occupant and the in-vehicle control system of the own vehicle, the external sensor 2 and the internal world. A cognitive judgment device 6 that calculates a target trajectory for controlling the running of the own vehicle based on the information of the sensor 3, a steering control mechanism (not shown) of the own vehicle based on the target trajectory of the cognitive judgment device 6, and vehicle speed control. A vehicle motion control device 7 that calculates a command value to a mechanism (not shown) and a brake control mechanism (not shown), and a steering control mechanism of the own vehicle are controlled based on the command value of the vehicle motion control device 7. The steering control device 8 and the vehicle speed control device 9 that controls the vehicle speed control mechanism based on the command value to adjust the speed of the own vehicle, and the brake control mechanism that controls the brake control mechanism based on the command value to control the braking force of each wheel. A brake control device 10 for controlling is provided.

As described above, the outside world sensor 2 is a device for acquiring information on the outside world of the own vehicle. The external sensor 2 includes one or a plurality of light waves (including, for example, infrared rays), electromagnetic waves (including, for example, millimeter wave radar), cameras, and the like. In the first embodiment, the external sensor 2 is provided with a stereo camera and a millimeter wave radar in the front, a laser radar on the left and right sides, and a millimeter wave radar in the rear. In the first embodiment, the combination of the above sensors is shown as an example of the sensor configuration, but the combination is not limited to that, and for example, an ultrasonic sensor, a monocular camera, LiDAR (Light Detection and Ranging), and the like. It may be a combination. Further, the above-mentioned sensor types and sensing regions are shown as examples only, and are not limited thereto.

The internal sensor 3 is a device for acquiring the internal state of the own vehicle. The internal state of the own vehicle includes at least one of the speed, acceleration, posture, steering angle, steering torque, pedal depression amount and depression speed of the own vehicle. The internal world sensor 3 includes a vehicle speed sensor, an IMU (Inertial Measurement Unit), a steering angle sensor, a steering torque sensor, and a pedal sensor. It should be noted that this embodiment merely shows the combination of the above sensors as an example of the sensor configuration, and is not limited thereto.

The vehicle speed sensor is a device for measuring the speed in the traveling direction of the vehicle by detecting the rotation speed of the wheels of the vehicle as a pulse signal.

The IMU is a device for detecting the acceleration and attitude of the own vehicle. The IMU is composed of, for example, a three-axis angular velocity sensor (gyro sensor) and a three-axis acceleration sensor, and detects the acceleration and attitude of the own vehicle by measuring the three-dimensional angular velocity and the acceleration signal.

The steering angle sensor is a device for detecting the steering angle of the own vehicle. The steering angle sensor may be built in the steering control device 8.

The steering torque sensor is provided on the steering shaft of the vehicle, for example, and detects the steering torque applied to the steering wheel by the driver of the vehicle.

The information acquired by the outside world sensor 2 and the inside world sensor 3 is transmitted to the cognitive determination device 6. The navigation system 4 (details are not shown) is a device that guides the own vehicle to a destination set by the occupants of the own vehicle via the HMI device 5 (details will be described later).

The navigation system 4 is composed of a GNSS (Global Navigation Satellite System) and a map database. Absolute position information of the own vehicle from the GNSS (for example, the latitude and longitude of the own vehicle) and a land from the stereo camera of the outside world sensor 2. The position (self-position) of the own vehicle on the map is estimated based on the mark information, the information of the acceleration sensor, the angular speed sensor, and the vehicle speed sensor of the internal world sensor 3, and the information of the map database, and the map information around the own vehicle is obtained. Output via the HMI device 5. Further, the navigation system 4 calculates the target route to the set destination based on the estimated position information of the own vehicle and the map information of the map database. The position information and map information of the own vehicle are transmitted to the cognitive determination device 6.

The HMI device 5 is a device provided with means for inputting and outputting information between the driver and / or occupant of the own vehicle and the vehicle-mounted control system of the vehicle. The input information acquired by the HMI device 5 is transmitted to the navigation system or the cognitive determination device 6. The information input operation means may be a touch panel, operation buttons, or voice input, and may be any means as long as the driver or the occupant can input the information into the HMI device 5.

The touch panel is used, for example, to set a destination or a route, enlarge or reduce a map, set an operation mode (automatic operation or manual operation), and the like. The operation buttons are used, for example, for adjusting the volume and switching from automatic operation to manual operation.

Further, as a means for outputting information and an alarm to the driver and the occupant, a display device for displaying text or image information and a speaker for generating sound are provided. The display is used to display the target route, guide to the destination (turn left at the next intersection, etc.), display the driving mode, monitor the driving state of the own vehicle, and the like. The speaker is used in conjunction with the display to transmit guidance to the destination, warning and alerting regarding the driving of the own vehicle or the surrounding environment, instruction of driving operation, and the like.

In the present embodiment, the combination of the above devices is shown as an example of the HMI device 5, but the present invention is not limited to this, and a voice recognition device may be provided as an HMI device for inputting information, for example. Further, as the information output HMI device 5, a lamp, a vibrator that vibrates the driver, a driver seat adjuster that changes the angle or position of the driver seat, and the like may be provided.

Although the details are not shown in FIG. 1, the cognitive determination device 6 has, for example, a memory such as a CPU (Central Processing Unit), a ROM (Read Only Memory), and a RAM (Random Access Memory), an input / output interface, and the like. It is a computer that controls the own vehicle. The ROM has a recognition unit that recognizes an object and determines whether or not to switch the automatic driving level based on the recognition result, a driving action plan that determines an automatic driving strategy, and a track that plans the trajectory of the own vehicle. The program of the planning department and the program are stored, the surrounding environment of the own vehicle is recognized, and based on the recognition result, the target trajectory that the own vehicle can safely avoid the object is generated and transmitted to the vehicle motion control device 7. .. However, the above function is only an example, and is not limited thereto. The vehicle motion control device 7 calculates the command value of the steering control mechanism, the command value of the engine control mechanism, and the command value of the brake control mechanism so that the own vehicle follows the target trajectory, and the steering control device 8 of each control mechanism. , The vehicle speed control device 9 and the brake control device 10. The steering control device 8, the vehicle speed control device 9, and the brake control device 10 of each control mechanism receive the command value of the cognitive determination device 6 and control each control mechanism based on the command value. The cognitive determination device 6 may be composed of a plurality of cognitive determination devices.

The steering control device 8 is, for example, an electronic unit that controls EPS (Electric Power Steering) of a vehicle. The steering control device 8 controls the steering angle of the vehicle by driving an assist motor that controls the steering torque of the vehicle in the electric power steering system. The steering control device 8 controls the steering angle according to a control signal from the cognitive determination device 6.

The vehicle speed control device 9 is an electronic control unit that controls the vehicle speed of the vehicle. The vehicle speed control device 9 controls the speed of the vehicle by, for example, controlling the amount of fuel supplied to the engine and the amount of air supplied. When the vehicle is a hybrid vehicle or an electric vehicle, the vehicle speed control device 9 functions as a motor control unit that controls a motor driven as a power source. The vehicle speed control device 9 controls the speed of the vehicle in response to a control signal from the vehicle motion control device 7.

The brake control device 10 is an electronic control unit that controls the brake control mechanism of the vehicle. As the brake control mechanism, for example, a hydraulic brake control mechanism can be used. The brake control device 10 controls the braking force applied to the wheels of the vehicle by adjusting the hydraulic pressure applied to the hydraulic brake control mechanism. The brake control device 10 controls the braking force on the wheels in response to a control signal from the cognitive determination device 6. When the vehicle is equipped with a regenerative brake control mechanism, the brake control device 10 may control both the hydraulic brake control mechanism and the regenerative brake control mechanism.

As described above, the in-vehicle control system 1 appropriately controls the speed of the vehicle by controlling the vehicle speed control device 9 and the brake control device 10 according to the recognized surrounding environment of the own vehicle, and also controls the steering control mechanism. It is possible to realize lane keeping control, lane change control, automatic merging control, automatic branch control, switching of driving level, and the like.

Next, the configuration of the cognitive determination device 6 will be described with reference to FIG. FIG. 2 is a block configuration diagram of the cognitive determination device according to the first embodiment of the present invention.

As shown in FIG. 2, the cognitive determination device 6 includes a recognition unit 61, a responsibility determination unit 62, a risk prediction unit 63, a driving behavior planning unit 64, and a track planning unit 65. These control programs are stored in the ROM and executed by the CPU.

The recognition unit 61 recognizes a sign, a white line, a road edge, and an object based on the information of each external world sensor 2, and recognizes the recognition result of the sign, the white line, the road edge, and the object as a risk prediction unit 63, a driving action planning unit 64, and a track plan. It is output to the unit 65, and the recognition result of the object is output to the responsibility determination unit 62. Here, the information of the object includes the position, speed, type of the object, and information on whether the object is dynamic or static. In order to recognize the object, first, the object around the own vehicle is detected based on the information obtained from the outside world sensor 2. To detect an object, for example, by irradiating a millimeter-wave radar (not shown) and detecting radio waves reflected by the object and returning, the distance and direction to the object are detected. In another method (not shown), the object is detected based on whether the shape of the target point detected by the distance sensor matches the shape of the template stored in advance. By detecting an object by the above method, information on the size, shape, position from the own vehicle, absolute and relative speed of the object can be obtained. It should be noted that the above object detection method is merely an example and is not limited thereto. Since there are other methods for detecting objects, any method may be appropriately selected when carrying out the invention.

Next, after the object is detected, the type of the object is specified based on the information of the outside world sensor 2. To identify an object, for example, an image acquired from a stereo camera is given to a pre-machine-learned classifier, and post-processing (details will be described later) is added to the output result of the classifier so that the object is stored in the database. Which type of throat belongs to is identified. There are a neural network, a support vector machine, and the like as the classifier, and any classifier may be used in this embodiment. Further, a plurality of classifiers may be used in combination. Further, although details are omitted, preprocessing such as filtering and feature extraction processing may be performed on the image acquired from the camera before inputting the image to the classifier.

Next, in order to explain an example of the post-processing, it is assumed that a neural network is used as a discriminator. In general, the neural network outputs the possibility that the input image belongs to each of the predefined types as a percentage. From the output results of the neural network, the one having the highest output value is selected, and when the value is equal to or more than a preset threshold value, the type of the object is determined to be the type corresponding to the output value. On the other hand, when the output value is less than the threshold value, the type of the object cannot be specified. That is, the type of object is unknown. The above-mentioned post-treatment method is an example, and is merely an example for facilitating the understanding of the present invention, and the present invention is not limited to the above-mentioned method. For the recognition method of signs, white lines, and road edges, general methods such as pattern matching and edge extraction by Hough transform are used.

The responsibility determination unit 62 determines whether or not it is necessary to switch the automatic driving level based on the object information of the recognition unit 61 and the information of the outside world sensor 2 in the automatic driving state of the system responsibility, and whether the vehicle is the driver responsible automatic driving. The responsible state amount indicating whether the system is responsible for automatic operation is output to the HMI device 5, and the determination result of whether the object is a static object or a dynamic object is output to the risk prediction unit 63. The HMI device 5 outputs the information of the responsibility determination unit 62 to notify the driver, and alerts the driver. In addition, the recognition result of the sign, the white line, and the road edge may be used for the judgment of the responsibility determination unit 62.

Next, the risk prediction unit 63 predicts the collision risk of the object based on the recognition result of the recognition unit 61 and the determination result of the responsibility determination unit 62, and determines the collision risk with the driving action planning unit 64 and the trajectory planning unit 65. Output to. As the collision risk of the object, for example, the maximum value may be 100 and the minimum value may be 0, and the higher the value, the higher the collision risk. The risk prediction unit 63 sets the collision risk based on the relative position of the object, the relative velocity, the type of the object, whether it is a dynamic object or a static object, and the like, for example, as follows.

Next, the avoidance trajectory for the object will be described with reference to FIG. FIG. 3A is a diagram showing an avoidance trajectory when an object whose type can be specified exists.

In FIG. 3A, the own vehicle is traveling in the left lane of a road having two lanes on each side in a system-responsible automatic driving state. There are obstacles in the left lane. Around the object, the collision risk is set in a circle around the object. The collision risk is high for the object itself and decreases as the distance from the object increases. In addition, the size of the circle indicating the collision risk is set so as to differ depending on the type of the detected object.

In FIG. 3A, (a) shows an avoidance trajectory when the object is determined to be a child, and (b) shows an avoidance trajectory when the object is determined to be an adult.

As shown in FIG. 3A, when the type of the object can be specified based on the information obtained from the external sensor 2, the collision risk area is calculated based on the type of the object. For example, when the object is determined to be a child as shown in (a), the collision risk area is predicted to be wider than when it is determined to be an adult as shown in (b). By doing so, when it is determined that the child is a child, the trajectory planning unit 65, which will be described later, can generate a large avoidance trajectory in consideration of the possibility that the child will jump out. That is, an appropriate avoidance trajectory can be generated according to the type of object. In the system-responsible automatic operation state, the responsibility determination unit 62 continues the system-responsible automatic operation state when the type of the object can be specified based on the information obtained from the external sensor 2.

Next, the case where the object type cannot be specified will be described. FIG. 3B is a diagram showing an avoidance trajectory when a static object of an unspecified type exists. FIG. 3C is a diagram showing an avoidance trajectory when a type of unspecified dynamic object exists.

As shown in FIG. 3B, when the type of the object cannot be specified and it is a static object, the collision risk is set around the object on the assumption that the object does not move. By doing so, the trajectory planning unit 65, which will be described later, can generate an avoidance trajectory that matches the driver's feeling without overestimating the collision risk and taking a large avoidance trajectory. In the system-responsible automatic operation state, the responsibility determination unit 62 continues the system-responsible automatic operation state when the object type cannot be specified based on the information obtained from the external sensor 2 and the object is a static object. To do.

Further, as shown in FIG. 3C, when the type of the object cannot be specified and it is a dynamic object, it is not possible to predict how the object will behave. Therefore, for example, the object jumps out on the road like a child. Assuming, set the collision risk so that it has a wider range than static objects.
In the system-responsible automatic operation state, the responsibility determination unit 62 cannot specify the object type based on the information obtained from the outside world sensor 2, and if it is a dynamic object, the driver from the system-responsible automatic operation state. Switch to responsible autonomous driving state. By doing so, when the type of the object cannot be specified and it is a dynamic object, it is possible to generate an avoidance trajectory assuming the worst state. The above method of calculating the collision risk is only an example, and is not limited thereto. The collision risk calculated by the risk prediction unit 63 is output to the driving behavior planning unit 64 and the track planning unit 65.

The driving action planning unit 64 is based on the information of each internal sensor 3, the map information from the navigation system 4, the output result of the risk prediction unit 63, the sign of the recognition unit 61, the white line, the road edge, and the object information. Plan the driving actions (functions to be executed) that the vehicle will take in the future. Here, the driving behavior is an automatic driving function such as driving control in the own lane, automatic merging control, lane change control, automatic branch control, right turn at an intersection, left turn at an intersection, and straight ahead at an intersection. However, the driving behavior is not limited to the above functions, and the driving behavior may be expressed by information such as a traveling lane. The track planning unit 65 plans a target track based on the driving behavior, map information, white line, road edge, object information, and output result of the risk prediction unit 63.

Next, with reference to FIG. 4, the processing flow of the responsibility determination unit 62 of the vehicle-mounted control system 1 according to the first embodiment will be described. FIG. 4 is a flowchart of the responsibility determination unit according to the first embodiment of the present invention.

By this process, it is possible to determine whether to continue the system-responsible automatic driving or switch to the driver-responsible automatic driving according to the surrounding environment of the own vehicle. In the situation described below, it is assumed that the vehicle-mounted control system 1 performs automatic driving including lane keeping control, lane change control, and navigation control.

In step S101, the object recognition result of the recognition unit 61 is received, and the object information is acquired.

Next, in step S102, it is determined whether or not the type of the object can be specified based on the object recognition result of the recognition unit 61. Here, when the type of the object can be specified (Yes in step S102), the responsibility determination unit 62 outputs the automatic operation level of the system responsibility to the HMI device 5, continues the automatic operation of the system responsibility as it is, and is responsible for the system. The responsible state amount corresponding to the automatic operation of is set (step S105).

On the other hand, when the type of the object cannot be specified (No in step S102), the process proceeds to step S103, and it is determined whether the object is a dynamic object or a static object based on the information of the outside world sensor 2. Dynamic objects are movable objects such as other vehicles and pedestrians, and static objects are immovable objects such as buildings.

To determine whether an object is a static object or a dynamic object, any of the general methods such as filter, optical flow (motion vector), and pattern matching is used. Further, a plurality of methods may be used in combination, such as optical flow and pattern matching.

Optical flow can detect the movement of an object regardless of the type of object, but in the case of a stationary pedestrian, the pedestrian is identified as a static object. On the other hand, pattern matching can discriminate whether an object is static or dynamic regardless of the movement of the object, but cannot discriminate an object that has not been learned in advance. In this way, by combining optical flow and pattern matching, it is possible to correctly identify objects that may move, such as pedestrians, and even unknown objects are correct if they are moving. It can be determined.

When the object is determined to be a static object based on the above determination (Yes in step S103), the responsibility determination unit 62 outputs the automatic operation level of system responsibility to the HMI device 5 and continues the automatic operation of system responsibility. , Set the responsibility state amount corresponding to the automatic operation of system responsibility (step S105).

On the other hand, when the object is determined to be a dynamic object (No in step S103), the process proceeds to step S104, and the responsibility determination unit 62 sets the responsibility state amount corresponding to the automatic operation of the driver responsibility, and sets the responsibility state amount. Output to HMI device 5. The responsibility determination unit 62 alerts the driver via the HMI device 5, requests the driver to grip the steering wheel, and the like, and switches to the driver-responsible automatic operation. Although not shown, the automatic driving system ends the automatic driving when the driver performs a driving operation (steering wheel operation, stepping on the brake or the accelerator, etc.) at any of the above automatic driving levels.

In step S106, information on whether the object is a static object or a dynamic object is transmitted to the risk prediction unit 63, and the responsible state quantity is output to the HMI device 5.

FIG. 5 shows an operation example when the automatic driving system described above is applied.
FIG. 5A is a diagram showing the operation of the automatic driving system when an object whose type can be specified exists, FIG. 5B is a diagram showing the operation of the automatic driving system when a static object whose type cannot be specified exists, and FIG. 5C is a diagram showing the operation of the automatic driving system. It is a figure which shows the operation of the automatic driving system when the dynamic object of an unspecified kind exists.

As shown in FIG. 5A, when there is an object whose type can be specified, the cognitive judgment device 6 of the own vehicle calculates a collision avoidance trajectory according to the type of the object, and based on the trajectory, the system is responsible for automatic driving. To continue.

Further, as shown in FIG. 5B, when there is a static object whose type cannot be specified, the cognitive judgment device 6 of the own vehicle calculates the collision avoidance trajectory according to the static object and continues the system-responsible automatic driving. To do.

On the other hand, as shown in FIG. 5C, when there is a dynamic object whose type cannot be specified by the process of step S103 (FIG. 4), the recognition determination device 6 of the own vehicle performs the process of step S104 (FIG. 4). As a result, the automatic operation level is changed so as to switch from the system-responsible automatic operation to the driver-responsible automatic operation, and the driver is alerted via the HMI device 5 to request that the steering wheel be gripped.

From the above, by applying the automatic driving system shown in this embodiment, when the type of object cannot be specified, the automatic driving level is appropriately changed according to whether it is a dynamic object or a static object, and driving safety is achieved. It is possible to achieve both safety and availability of the autonomous driving system. In other words, if the accurate risk prediction of the object is not possible "the type of the object is unknown, but the object is dynamic", by switching to the driver-responsible automatic operation, the driver is informed of the possibility that the accurate risk prediction cannot be made in advance. It is possible to improve the safety of the system. When the risk of an object can be predicted accurately "when the type of object is unknown, but the object is static", the availability of the autonomous driving system can be improved by continuing the automatic operation of system responsibility.

Next, a second embodiment of the present invention will be described with reference to FIG. FIG. 6 is a flowchart of the responsibility determination unit according to the second embodiment of the present invention. The description of the same contents as those in the first embodiment will be omitted as appropriate.

FIG. 6 is different from the first embodiment in that it has a process (step S201) of determining whether or not the distance L to the recognized object is equal to or greater than the threshold value TL. For the distance to the object, for example, the millimeter wave radar described in the first embodiment is used.

In the second embodiment, after the object is recognized by the recognition unit 61, the distance to the object is determined based on the recognition result. Specifically, the distance L between the own vehicle and the object is compared with the preset threshold value TL, and when the distance L is equal to or greater than the threshold value TL (Yes in step S201), the process proceeds to step S105 to automatically drive the system. If the distance L is less than the threshold value TL (No in step S201), the process proceeds to step S102.

Here, the threshold value TL is set to the maximum value of the object distance at which the object recognition performance can achieve a predetermined performance under the conditions of various object distances, for example, in a recognition performance test. The above TL calculation method is merely an example, and is not limited thereto. In addition to the method of acquiring the distance of the object from the recognition result of the recognition unit 61 as described above, for example, the distance information of the object can be acquired from a sensor outside the own vehicle. In carrying out the present invention, it is advisable to appropriately use an arbitrary method for acquiring the distance information of the object.

In the second embodiment, it is technically difficult to identify the type of an object existing in the distance and to determine whether it is a static object or a dynamic object, and erroneous determination is likely to occur. There is a risk that the driving level will be canceled, and in this case there is a problem that the convenience of the driver is impaired. Therefore, by applying the second embodiment, it is possible to suppress the number of times the automatic driving level is switched by ignoring objects that exist far enough away that do not need to be recognized, and improve the convenience of the driver. Can be done.

Next, a third embodiment of the present invention will be described with reference to FIGS. 7 and 8. The same contents as those in the first embodiment will be omitted as appropriate. FIG. 7 is a system configuration diagram of the vehicle-mounted control system according to the third embodiment of the present invention, and FIG. 8 is a flowchart of the responsibility determination unit according to the third embodiment of the present invention.

In FIG. 7, the difference from the first embodiment (FIG. 1) is that the wireless communication device 11 is provided.

The wireless communication device 11 is a device for communicating between the own vehicle and an external in-vehicle control system. As shown in FIG. 7, the wireless communication device 11 has a function of acquiring information of the outside world sensor 2, the inside world sensor 3, and the HMI device 5 and transmitting the information to the remote control system 12. Further, as shown in FIG. 7, it becomes possible to receive a command from the remote control system 12 via the wireless communication device 11. The remote control system 12 controls the vehicle at a position away from the vehicle. In the third embodiment, the operator controls the vehicle using the remote control system 12.

The operator controls the steering control device 8, the vehicle speed control device 9, and the brake control device 10 by monitoring the running state of the vehicle using the remote control system 12 and generating command values of the steering wheel, the brake, and the accelerator. be able to. That is, the operator can perform remote control of the vehicle, which could not be realized in the first embodiment and the second embodiment.

Next, the processing flow of the responsibility determination unit 62 of the cognitive determination device in the third embodiment will be described with reference to FIG. Since steps S101-S106 in FIG. 8 are the same as steps S101-S106 in FIG. 4 in the description of the first embodiment, the description thereof will be omitted. The difference from the first embodiment is that the processing of step S301-step S303 is added to the flowchart of the first embodiment.

In the third embodiment, it is determined in step S103 whether the object is a dynamic object that is a static object, and if the object is a dynamic object, the driver in the vehicle is based on the information of the internal sensor 3. Determines if is present (step S301). Here, the internal sensor used is, for example, a seating sensor mounted on a seat. When the driver is present in the vehicle based on the seating sensor (Yes in step S301), the responsibility state amount corresponding to the automatic driving of the driver responsibility is set (step S104) and the responsibility is set as in the first embodiment. The state amount is output to the HMI device 5, the driver is alerted via the HMI device 5, the driver is requested to grip the steering wheel, and the like, and the automatic operation is switched to the driver's responsibility.

On the other hand, when it is determined that the driver does not exist in the vehicle (No in step S301), the internal information of the own vehicle and the information of the surrounding environment are first transferred to the external in-vehicle control system (S9), and then the operator is responsible. The responsible state amount corresponding to the automatic operation of the above is set (step S303), the responsible state amount is output to the HMI device 5, and the HMI device 5 alerts the remote operator of the information via the wireless communication device 11. Then, we will work on requests, etc. to stand by in a system that allows remote operation, and switch to operator-responsible automatic operation. Here, if an override is required at the discretion of the operator, it can be overridden by performing a driving operation (joystick or steering wheel operation, stepping on the brake or accelerator, etc.) using an operation device for remote control. (Not shown).

Although not shown, it is also possible to insert the process of step S201 used in FIG. 6 of the second embodiment between step S101 and step S102 in the responsibility determination unit of the third embodiment. .. By adding the process of step S201, it is possible to ignore an object existing in a distant place that does not need to be recognized, the number of times of switching the automatic driving level can be suppressed, and the convenience of the driving monitor is improved. be able to.

In the first embodiment and the second embodiment, it was assumed that the driver exists in the vehicle. In the third embodiment, the object can be safely avoided even in an unmanned traveling vehicle in which the driver does not exist in the vehicle, so that the availability of the automatic driving system can be improved.

In the first to third embodiments, the cognitive determination device 6 is mounted on the vehicle, but the cognitive determination device 6 can be installed at any place outside the vehicle. In that case, the vehicle is equipped with the wireless communication device 11 as described in the third embodiment, and each device mounted on the vehicle is wirelessly connected to the cognitive determination device 6 installed at an arbitrary location. To do.
With this configuration, even when the cognitive determination device 6 is installed at an arbitrary location, it is possible to realize the same function as that of the cognitive determination device 6 mounted on the vehicle.

Further, the applicable field of the present invention is not limited to the in-vehicle system, and although details are omitted, autonomous driving robots and the like can also be applied.

The present invention is not limited to the above-described examples, and includes various modifications. The above-described examples have been described in detail in order to explain the present invention in an easy-to-understand manner, and are not necessarily limited to those having all the described configurations.

1 ... In-vehicle control system, 2 ... External sensor, 3 ... Internal sensor, 4 ... Navigation system, 5 ... HMI device, 6 ... Cognitive judgment device, 7 ... Vehicle motion control device, 8 ... Steering control device, 9 ... Vehicle speed Control device, 10 ... Brake control device, 11 ... Wireless communication device, 12 ... Remote control system, 61 ... Recognition unit, 62 ... Responsibility judgment unit, 63 ... Risk prediction unit, 64 ... Driving behavior planning unit, 65 ... Track planning unit ..

Claims (8)

An automatic driving system including an outside world sensor that acquires outside world information of a vehicle and a cognitive determination device that calculates a target trajectory of the vehicle so as to avoid a collision with an object based on the information of the outside world sensor.
The cognitive determination device determines the type of the object when the external sensor detects the information of the object in the automatic driving state in which the vehicle is responsible for the system, and moves the object when the type of the object cannot be specified. An automatic driving system characterized in that it determines whether or not it is correct and provides driving support according to the determination result. In claim 1,
The cognitive judgment device includes a responsibility judgment unit.
The responsibility determination unit determines whether or not the object is dynamic, and if the object is static, the automatic operation system is characterized in that the automatic operation of the system responsibility is continued. In claim 2,
The responsibility determination unit is an automatic driving system characterized in that when the object is dynamic, the automatic driving of the system responsibility is switched to the automatic driving of the driver responsibility. In claim 3,
It is equipped with an HMI device that outputs the information of the responsibility determination unit.
The responsible determination unit is an automatic driving system characterized in that, when the object is dynamic, the driver is notified via the HMI device that the automatic driving is the responsibility of the driver. In claim 3,
The responsible determination unit is an automatic driving system characterized in that when the distance to the object obtained from the external sensor is equal to or greater than a preset threshold value, the automatic operation of the system responsibility is continued. In claim 5,
The responsibility determination unit is an automatic driving system characterized in that when the distance to the object obtained from the outside world sensor is less than a preset threshold value, the type of the object is determined. In claim 3,
It is equipped with an internal sensor that detects the internal state of the vehicle.
The responsibility determination unit determines whether or not a driver exists in the vehicle based on the information of the internal sensor, and when the object is dynamic, the driver exists in the vehicle. If so, the automatic driving system is characterized by switching from the system-responsible automatic driving to the driver-responsible automatic driving. In claim 7,
A wireless communication device for the operator to communicate with a remote control system for remote control of the vehicle is provided.
In the case where the object is dynamic and the driver does not exist in the vehicle, the responsibility determination unit causes the operator to use the remote control system from the automatic operation of the system responsibility. An automatic driving system characterized by switching to automatic driving that is the responsibility of the operator who controls the vehicle.

Images