Vehicle control device, vehicle control method, and vehicle control computer program

Abstract

To provide a vehicle control device capable of shortening a time required until a vehicle stops after abnormality of a driver is detected.SOLUTION: The vehicle control device includes the abnormality detection unit 31 configured to detect the abnormality that has occurred to the driver of the vehicle 10, and the control unit 30 configured to, when the abnormality that has occurred to the driver is detected, alternatively, the determination unit 32 determines whether or not there is an evacuation space within a predetermined range from the current position of the vehicle 10 by recognizing a sign indicating the presence of an evacuation space from an external image obtained by the external camera 2 that captures an image of the surroundings of the vehicle 10. And a control part 33 for controlling the vehicle 10 so that a second deceleration width until the vehicle 10 stops after starting entering operation becomes larger than a first deceleration width of the vehicle 10 until starting the entering operation for making the vehicle 10 enter the evacuation space.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to a vehicle control device, a vehicle control method, and a computer program for vehicle control that control the running of a vehicle when an abnormality occurs in the driver. [Background technology]

[0002] Research has been conducted on a cruise control device that will allow a vehicle to retreat to an appropriate position if an abnormality occurs in the driver of the vehicle (see Patent Document 1). When an abnormal state of the driver is detected while the vehicle is traveling downhill, this cruise control device sets an area ahead of the road where the vehicle will retreat and stop as a forward retreat utilization area. The cruise control device then detects an object from the forward retreat utilization area that can be prevented from moving the vehicle after stopping as a retreat utilization object, sets a target course for the vehicle to travel with the retreat utilization object as a destination, and controls the vehicle to travel along the target course and stop near the retreat utilization object. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2018-43705 Summary of the Invention [Problem to be solved by the invention]

[0004] It is preferable that the time required from when a driver abnormality is detected until the vehicle is stopped be as short as possible.

[0005] Therefore, an object of the present invention is to provide a vehicle control device that can shorten the time required for the vehicle to stop after a driver abnormality is detected. [Means for solving the problem]

[0006] According to one embodiment, there is provided a vehicle control device that includes: a storage unit that stores map information including information about evacuation spaces into which the vehicle can retreat; an abnormality detection unit that detects an abnormality occurring in the driver of the vehicle; a determination unit that, when an abnormality occurring in the driver is detected, determines whether or not an evacuation space exists within a predetermined range from the current position of the vehicle by referring to the map information or by recognizing a sign indicating the existence of the evacuation space from an exterior image acquired by an exterior camera that captures the surroundings of the vehicle; and a control unit that, when an evacuation space exists within the predetermined range, stops the vehicle at the evacuation space and controls the vehicle so that a second deceleration amount from the start of the entry operation to the stop of the vehicle is greater than a first deceleration amount from the start of the entry operation to the evacuation space.

[0007] In one embodiment, if there is no evacuation space within a specified range, the control unit decelerates the vehicle by a third deceleration amount greater than the first deceleration amount, searches for a parking space where the vehicle can be stopped based on an exterior image, and stops the vehicle in the parking space.

[0008] In one embodiment, the control unit sets the collision avoidance conditions for initiating an avoidance operation to avoid the vehicle colliding with another object so that the collision avoidance conditions are relaxed after the entry operation has started compared to before the entry operation has started. [Effects of the Invention]

[0009] The vehicle control device according to the present disclosure has the effect of being able to reduce the time required for the vehicle to stop after a driver abnormality is detected. [Brief explanation of the drawings]

[0010] [Figure 1] 1 is a schematic configuration diagram of a vehicle control system in which a vehicle control device is implemented. [Figure 2] FIG. 2 is a hardware configuration diagram of an electronic control device. [Figure 3]FIG. 2 is a functional block diagram of a processor of an electronic control unit related to vehicle control processing. [Figure 4] FIG. 10 is an explanatory diagram of a vehicle control process when a turn-off space is present. [Figure 5] 4 is an operational flowchart of a vehicle control process. DETAILED DESCRIPTION OF THE INVENTION

[0011] A vehicle control device, a vehicle control method executed on the vehicle control device, and a computer program for vehicle control will be described below with reference to the drawings. The vehicle control device has the function of a so-called emergency driving stop system (EDSS). When an abnormality that makes it difficult for the driver to continue driving the vehicle is detected, the vehicle control device controls the vehicle according to an emergency stop mode that automatically stops the vehicle. In this case, the vehicle control device controls the vehicle so that a second deceleration amount, from when the vehicle starts an approach operation to when the vehicle stops, is greater than a first deceleration amount, from when the vehicle starts an approach operation to enter an evacuation space where the vehicle can escape.

[0012] FIG. 1 is a schematic diagram of a vehicle control system in which a vehicle control device is implemented. In this embodiment, the vehicle control system 1 is mounted on a vehicle 10 and controls the vehicle 10. The vehicle control system 1 includes an exterior camera 2, a driver monitor camera 3, a GPS receiver 4, a storage device 5, and an electronic control unit (ECU) 6, which is an example of a vehicle control device. The exterior camera 2, the driver monitor camera 3, the GPS receiver 4, the storage device 5, and the ECU 6 are communicatively connected to each other. The vehicle 10 may be provided with a distance measurement sensor (not shown), such as a LiDAR or radar, that measures the distance from the vehicle 10 to objects present around the vehicle 10. The vehicle 10 may also be provided with a notification device (not shown) for notifying the occupants of the vehicle 10. The vehicle 10 may also be provided with a wireless communication terminal (not shown) for wireless communication with other devices.

[0013] The exterior camera 2 is an example of an exterior sensor, and is attached to the vehicle 10 so as to face a predetermined area around the vehicle 10, such as the area ahead of the vehicle 10. Note that the vehicle 10 may be provided with multiple exterior cameras with different shooting directions or focal lengths. The exterior camera 2 captures an image of a predetermined area at each predetermined shooting period to generate an image of the predetermined area (hereinafter referred to as an exterior image), and outputs the generated exterior image to the ECU 6.

[0014] The driver monitor camera 3 is an example of an in-vehicle sensor for detecting the state of the driver. The driver monitor camera 3 is mounted near the top edge of the windshield or near the instrument panel, facing the driver, seated in the driver's seat of the vehicle 10, so that at least the head of the driver is included in the imaging target area. The driver monitor camera 3 may have a light source such as an infrared LED. The driver monitor camera 3 captures an image of the imaging target area at each predetermined imaging period to generate an image of the driver (hereinafter referred to as a driver image), and outputs the generated driver image to the ECU 6.

[0015] The GPS receiver 4 receives GPS signals from GPS satellites at predetermined intervals and determines the position of the vehicle 10 based on the received GPS signals. The GPS receiver 4 then outputs positioning information representing the positioning results of the vehicle 10 based on the GPS signals to the ECU 6 at predetermined intervals. Note that the vehicle control system 1 may include a receiver that complies with another satellite positioning system instead of the GPS receiver 4.

[0016] The storage device 5 is an example of a storage unit and includes, for example, a hard disk drive or a nonvolatile semiconductor memory. The storage device 5 stores map information indicating the location of spaces where the vehicle 10 can retreat.

[0017] The ECU 6 operates as an EDSS, that is, when the ECU 6 detects an abnormality that prevents the driver from continuing to drive the vehicle 10, the ECU 6 controls the vehicle 10 to bring the vehicle 10 to an emergency stop.

[0018] Fig. 2 is a hardware configuration diagram of the ECU 6. As shown in Fig. 2, the ECU 6 has a communication interface 21, a memory 22, and a processor 23. The communication interface 21, the memory 22, and the processor 23 may each be configured as separate circuits, or may be integrated into a single integrated circuit.

[0019] The communication interface 21 has an interface circuit for connecting the ECU 6 to other devices inside the vehicle. The communication interface 21 passes the vehicle exterior image received from the exterior camera 2, the driver image received from the driver monitor camera 3, and the positioning signal received from the GPS receiver 4 to the processor 23. The communication interface 21 also passes map information read from the storage device 5 to the processor 23. Furthermore, the communication interface 21 outputs a control signal for controlling the vehicle 10.

[0020] The memory 22 is another example of a storage unit and includes, for example, a volatile semiconductor memory and a non-volatile semiconductor memory. The memory 22 stores various data used in the vehicle control process executed by the processor 23 of the ECU 6. For example, the memory 22 stores parameters of the exterior camera 2, such as the installation position, shooting direction, and focal length. The memory 22 also stores various parameters used to detect driver abnormalities from the driver image. The memory 22 also temporarily stores the exterior image from the exterior camera 2, the driver image from the driver monitor camera 3, the positioning signal from the GPS receiver 4, and map information from the storage device 5.

[0021] The processor 23 includes one or more central processing units (CPUs) and their peripheral circuits. The processor 23 may further include other arithmetic circuits such as a logic unit, a numerical calculation unit, or a graphics processing unit. The processor 23 executes vehicle control processing for the vehicle 10.

[0022] 3 is a functional block diagram of processor 23 related to vehicle control processing. Processor 23 has an abnormality detection unit 31, a determination unit 32, and a vehicle control unit 33. Each of these units in processor 23 is a functional module realized by, for example, a computer program running on processor 23. Alternatively, each of these units in processor 23 may be a dedicated arithmetic circuit provided in processor 23.

[0023] The abnormality detection unit 31 detects an abnormality when an abnormality occurs that prevents the driver from continuing to drive the vehicle 10. Note that, for the sake of convenience, hereinafter, when an abnormality occurs that prevents the driver from continuing to drive the vehicle 10, it may be simply referred to as an abnormality occurring in the driver.

[0024] The anomaly detection unit 31 sequentially inputs multiple driver images in the order in which they were generated to a classifier that has been trained in advance to detect various driver abnormalities. The classifier that detects driver abnormalities is configured as a deep neural network (DNN) with a recursive structure, such as a recurrent neural network (RNN) or a long short-term memory (LSTM). By using a DNN with a recursive structure as the classifier, the anomaly detection unit 31 can use the driver's behavior corresponding to the driver's abnormality to detect the abnormality, thereby accurately detecting the abnormality. Note that the classifier may be configured based on a machine learning method other than DNN. The classifier is trained in advance according to a predetermined supervised learning method, such as backpropagation, using as training images a time-series series of images depicting a normal driver and a time-series series of images depicting a driver in an abnormal state for each type of abnormality to be detected.

[0025] Furthermore, the abnormality detection unit 31 may detect an abnormality in the driver using other techniques for detecting an abnormality occurring in the driver from a driver image.

[0026] For example, the abnormality detection unit 31 may periodically determine the driver's drowsiness level based on a series of driver images acquired over a recent fixed period. If the driver's drowsiness level is at a level that prevents the driver from monitoring the area ahead of the vehicle 10, the abnormality detection unit 31 may determine that an abnormality has occurred in the driver. To this end, the abnormality detection unit 31 detects the driver's gaze direction, eye opening degree (hereinafter referred to as eye opening degree), and mouth opening degree from each of the series of driver images acquired over the recent fixed period. The abnormality detection unit 31 then determines the driver's drowsiness level based on the detected gaze direction, eye opening degree, and drowsiness level. In this case, the abnormality detection unit 31 detects the eye region and mouth region from each driver image by inputting each driver image into a classifier that has been trained in advance to detect the eye region representing the driver's eyes and the mouth region representing the driver's mouth. For each driver image, the abnormality detection unit 31 calculates the ratio of the vertical size to the horizontal size of the eye region as the eye opening degree, and calculates the ratio of the vertical size to the horizontal size of the mouth region as the mouth opening degree.The abnormality detection unit 31 then calculates the time from when the eye opening degree reaches a maximum value to when it reaches the next maximum value as the duration of one blink of the driver, based on the time-series change in the eye opening degree for each of the series of driver images.The abnormality detection unit 31 then counts the number of blinks over a recent fixed period and calculates the average time between blinks as the blink period.

[0027] Furthermore, the abnormality detection unit 31 detects the pupil center and the Purkinje image by template matching between the eye region, a template representing the pupil, and a template representing the corneal reflection image (Purkinje image) of the light source.The abnormality detection unit 31 then calculates the direction and distance from the Purkinje image to the pupil center, and detects the driver's gaze direction by referring to a table showing the relationship between the direction and distance and the driver's gaze direction. Note that such a table may be stored in advance in the memory 22.The abnormality detection unit 31 then calculates the amount of movement in the gaze direction for each pair of two consecutive driver images captured within a recent fixed period, and calculates the gaze direction movement speed by dividing the average amount of movement by the interval between driver image captures.

[0028] The abnormality detection unit 31 determines the drowsiness level of the driver based on at least one of the period and frequency of blinking, the degree of mouth opening, and the speed of movement in the direction of gaze, and determines that an abnormality has occurred in the driver if the drowsiness level is at a level that makes it impossible to monitor the area ahead of the vehicle 10. For example, the abnormality detection unit 31 determines that an abnormality has occurred in the driver if the number of blinks in the most recent fixed period is equal to or greater than a predetermined number, the blinking period is longer than a predetermined time threshold, and the degree of mouth opening is greater than a predetermined opening degree.

[0029] The abnormality detection unit 31 may determine whether an abnormality has occurred in the driver according to other indicators that represent the driver's condition. For example, if a microphone (not shown) is provided in the vehicle cabin, the abnormality detection unit 31 may detect a specific abnormal sound (e.g., snoring) emitted by the driver from an audio signal that represents the sound in the vehicle cabin and is generated by the microphone. The abnormality detection unit 31 may then determine that an abnormality has occurred in the driver if it detects the specific abnormal sound emitted by the driver. The abnormality detection unit 31 may detect the abnormal sound emitted by the driver according to any method for detecting the specific abnormal sound from an audio signal.

[0030] When the abnormality detection unit 31 determines that an abnormality has occurred in the driver, it instructs the determination unit 32 and the vehicle control unit 33 to activate the EDSS function, i.e., to apply the emergency stop mode. On the other hand, when the abnormality detection unit 31 determines that an abnormality has not occurred in the driver, it is not necessary to activate the EDSS function.

[0031] When an abnormality in the driver is detected, that is, when the abnormality detection unit 31 notifies the determination unit 32 that an emergency stop mode is to be applied, the determination unit 32 determines whether or not there is an evacuation space where the vehicle 10 can escape within a predetermined range (for example, a range of several hundred meters to several kilometers) from the current position of the vehicle 10. The evacuation space is, for example, an emergency evacuation shelter provided on the side of a road in a downhill section. Alternatively, the evacuation space may be an area provided on the side of a road where the vehicle 10 can stop, such as a service area, a parking area, or a chain attachment / detachment site.

[0032] The determination unit 32 determines whether or not the map information indicates an escape space within a predetermined range in the road section on which the vehicle 10 is traveling, along the traveling direction of the vehicle 10 indicated by a direction sensor (not shown) mounted on the vehicle 10 from the current position of the vehicle 10 indicated by the latest positioning information. If such an escape space is indicated in the map information, the determination unit 32 determines that an escape space exists within a predetermined range from the current position of the vehicle 10.

[0033] Furthermore, the determination unit 32 may determine that an evacuation space exists if it can recognize a sign indicating the presence of an evacuation space (hereinafter, sometimes referred to as an evacuation sign). In this case, the determination unit 32 detects the evacuation sign from the vehicle exterior image by inputting the vehicle exterior image into a classifier that has been trained in advance to detect evacuation signs. The classifier for detecting evacuation signs is configured, for example, as a convolutional neural network (CNN)-type architecture or a DNN with an attention mechanism. When an evacuation sign is detected, the determination unit 32 detects a numerical value indicating the distance to the evacuation space indicated on the evacuation sign. To this end, the determination unit 32 inputs an area in which the evacuation sign detected from the vehicle exterior image is displayed to a character recognizer. As a result, the determination unit 32 recognizes the distance to the evacuation space indicated on the evacuation sign. Note that the character recognizer may also be configured as a DNN with a CNN-type architecture or an attention mechanism. Note that the classifier for detecting evacuation signs and the character recognizer used to recognize the distance to the evacuation space indicated on the evacuation sign may be configured integrally.

[0034] If an evacuation sign is detected from the outside-vehicle image and the distance to the evacuation space indicated on the evacuation sign is within a predetermined range from the current position of the vehicle 10, the judgment unit 32 judges that an evacuation space exists within a predetermined range from the current position of the vehicle 10.

[0035] When the determination unit 32 determines that an evacuation space exists, it notifies the vehicle control unit 33 of the determination result and the location of the evacuation space.

[0036] The vehicle control unit 33 is an example of a control unit, and when a driver abnormality is detected, i.e., when the abnormality detection unit 31 notifies the application of emergency stop mode, it controls the vehicle 10 to stop in accordance with the emergency stop mode.

[0037] First, in the control notice phase, the vehicle control unit 33 notifies those around the vehicle 10 that the vehicle 10 will make an emergency stop. To do so, the vehicle control unit 33 turns on the hazard lights. The vehicle control unit 33 also notifies the occupants of the vehicle 10 that the emergency stop mode will be executed via a notification device (not shown).

[0038] After the control notice phase lasting a predetermined period (for example, several seconds), the vehicle control unit 33 stops the vehicle 10 at the target stopping position as the driving intervention phase. Here, if the determination unit 32 notifies the vehicle control unit 33 of the determination result that an evacuation space exists and the location of the evacuation space, the vehicle control unit 33 sets the target stopping position at the evacuation space. On the other hand, if the determination result that an evacuation space exists has not been notified, that is, if there is no evacuation space within a predetermined range from the current position of the vehicle 10, the vehicle control unit 33 sets the target stopping position on the shoulder of the road section on which the vehicle 10 is traveling. The vehicle control unit 33 then controls each unit of the vehicle 10 so that the vehicle 10 stops at the target stopping position.

[0039] If a turn-off space exists within the predetermined range, the vehicle control unit 33 controls the powertrain and brake device to decelerate the vehicle 10 by a first deceleration amount after the start of the driving intervention phase. When decelerating the vehicle 10 by the first deceleration amount, the vehicle control unit 33 may set the accelerator opening to 0 to allow the vehicle 10 to naturally decelerate. The vehicle control unit 33 then drives the vehicle 10 at a predetermined speed after deceleration to a position where the vehicle can enter the turn-off space. The vehicle control unit 33 may also sound the horn when starting to decelerate the vehicle 10. Furthermore, if the lane in which the vehicle 10 is traveling is different from a lane where the vehicle can enter the turn-off space, the vehicle control unit 33 controls the steering wheels of the vehicle 10 to change lanes to a lane where the vehicle can enter the turn-off space before the vehicle 10 reaches a position where the vehicle can enter the turn-off space. The vehicle control unit 33 may identify the current lane and lanes that can be used to enter the evacuation space by referring to map information and the position of the vehicle 10 indicated in the positioning signal. Alternatively, the vehicle control unit 33 may detect individual lane markings on the road section on which the vehicle 10 is traveling by inputting an exterior image into a classifier that has been trained in advance to detect lane markings. The vehicle control unit 33 may then identify the number of lanes from the current lane to the lanes that can be used to enter the evacuation space based on the number of lane markings on the left or right side of the vehicle 10.

[0040] Furthermore, the vehicle control unit 33 may determine that the vehicle 10 has reached the position where the vehicle 10 can enter the evacuation space if the position of the vehicle 10 indicated in the positioning signal reaches the position where the vehicle 10 can enter the evacuation space indicated in the map information. Alternatively, the vehicle control unit 33 may determine that the vehicle 10 has reached the position where the vehicle 10 can enter the evacuation space if the size of a sign indicating the position where the vehicle 10 can enter the evacuation space on the exterior image of the vehicle becomes equal to or larger than a predetermined size, or if the bottom edge of the sign on the exterior image of the vehicle becomes higher than a predetermined position. The vehicle control unit 33 may detect the area where the sign is displayed on the exterior image of the vehicle by inputting the exterior image into a classifier that has been trained in advance to detect the sign. The classifier for detecting lane markings and the classifier for detecting signs are also configured as a DNN with a CNN-type architecture or an attention mechanism. Furthermore, the same classifier may be trained in advance to detect both lane markings and signs.

[0041] When the vehicle 10 reaches a position where it can enter the turn-off space, the vehicle control unit 33 causes the vehicle 10 to start an operation of entering the turn-off space. This operation of entering the turn-off space is an operation of steering the vehicle 10 so that the vehicle 10 enters the turn-off space. After starting the operation of entering the turn-off space, the vehicle control unit 33 decelerates the vehicle 10 by a second deceleration amount until the vehicle 10 stops, thereby stopping the vehicle 10 in the turn-off space.

[0042] In this embodiment, the vehicle control unit 33 controls the powertrain and brake device of the vehicle 10 so that the second deceleration amount of the vehicle 10 after starting the operation to enter the evacuation space is greater than the first deceleration amount. Note that the deceleration amount here refers to the difference in speed before and after deceleration, and not the rate of change in speed (deceleration) during deceleration. For example, assume that the speed of the vehicle 10 immediately before the driving intervention phase starts is 60 km / h. In this case, the vehicle control unit 33 decelerates the vehicle 10 by 10 km / h as a first deceleration amount, and then causes the vehicle 10 to travel at 50 km / h until the vehicle 10 reaches a position where it can enter the evacuation space. Then, after starting the operation to enter the evacuation space, the vehicle control unit 33 decelerates the vehicle 10 by 50 km / h as a second deceleration amount, thereby stopping the vehicle 10. Note that even if the speed of the vehicle 10 immediately after the start of the driving intervention phase is maintained, as long as the vehicle 10 can stop after entering the evacuation space, the first deceleration amount may be set to 0. For example, if the speed of the vehicle 10 immediately after the start of the driving intervention phase is equal to or less than the legal speed limit for the road section on which the vehicle 10 is traveling, the vehicle control unit 33 may set the first deceleration amount to 0. In this way, by suppressing the deceleration of the vehicle 10 until the vehicle 10 reaches a position where it can enter the evacuation space, the time required for the vehicle 10 to reach the evacuation space is reduced.

[0043] Furthermore, if there is no evacuation space within a predetermined range from the current position of the vehicle 10, the vehicle control unit 33 decelerates the vehicle 10 by a third deceleration amount that is greater than the first deceleration amount. The vehicle control unit 33 then continues driving the vehicle 10 at a slow speed after the deceleration (for example, 10 km / h) until the vehicle 10 enters the shoulder of the road, and searches for a stopping space on the shoulder of the road where the vehicle 10 can stop. When a stopping space is found, the vehicle control unit 33 sets the stopping space as a target stopping position. This allows the vehicle control unit 33 to safely stop the vehicle 10 even if there is no evacuation space.

[0044] When the vehicle 10 searches for a space where it can stop, the vehicle control unit 33 determines whether or not there is an obstacle that would hinder the vehicle 10 from stopping on the shoulder of the road, based on the exterior image obtained by the exterior camera 2. Such obstacles include, for example, a person, a motorcycle, a vehicle, a sign, a block, a pole, or a pylon. The vehicle control unit 33 detects the obstacle by inputting the exterior image into a classifier that has been trained in advance to detect obstacles. The classifier for obstacle detection is also configured as a CNN-type architecture or a DNN with an attention mechanism. The vehicle control unit 33 then determines, as a stopping space, an area in real space that is included in the range corresponding to the shoulder of the road in the exterior image and that corresponds to an area where no obstacles are detected, and sets that stopping space as the target stopping position. In this case, the vehicle control unit 33 may identify an area corresponding to the shoulder on the vehicle exterior image based on the position of the vehicle 10 measured by a positioning device (not shown) mounted on the vehicle 10, the traveling direction of the vehicle 10 measured by a direction sensor (not shown) mounted on the vehicle 10, parameters of the exterior camera 2 such as the shooting direction and angle of view, and map information. Alternatively, the vehicle control unit 33 may identify an area corresponding to the shoulder on the vehicle exterior image by detecting the shoulder from the vehicle exterior image. In this case, the above-mentioned classifier for obstacle detection may be trained in advance to also detect the shoulder. If the vehicle 10 has a distance measurement sensor such as a LiDAR sensor, the vehicle control unit 33 may detect the obstacle based on a distance measurement signal obtained by the distance measurement sensor. In this case, the vehicle control unit 33 can also detect the obstacle by inputting the distance measurement signal to a classifier trained in advance for obstacle detection. When an obstacle is detected, the vehicle control unit 33 determines whether or not the obstacle is present on the shoulder by referring to the direction and distance to the obstacle indicated by the ranging signal, the position and orientation of the vehicle 10, and the distance from the position of the vehicle 10 to the shoulder in the direction in which the obstacle is present.

[0045] When the target stopping position is found, the vehicle control unit 33 controls each unit of the vehicle 10 to stop the vehicle 10 at the target stopping position. If the vehicle's own lane is different from a lane that allows entry to the shoulder, the vehicle control unit 33 may control the steering wheels of the vehicle 10 to change lanes to a lane that allows entry to the shoulder before the vehicle 10 reaches the target stopping position, just as in the case where the vehicle's own lane is different from a lane that allows entry to the evacuation space.

[0046] Furthermore, the vehicle control unit 33 controls the vehicle 10 so that the vehicle 10 does not collide with obstacles present around the vehicle 10 until the vehicle 10 comes to a stop.

[0047] The vehicle control unit 33 tracks obstacles present around the vehicle 10 detected from a series of time-series exterior images, etc., and estimates a predicted trajectory of each obstacle up to a predetermined time ahead from the trajectory obtained as a result of the tracking. In doing so, the vehicle control unit 33 tracks the obstacles by applying a predetermined tracking process such as Byte Track to the series of exterior images.

[0048] The vehicle control unit 33 converts the coordinates of each obstacle in the image into coordinates on the bird's-eye view image (bird's-eye view coordinates) by performing a viewpoint conversion process using parameters of the exterior camera 2, such as the mounting position on the vehicle 10, for each obstacle being tracked. In this process, the vehicle control unit 33 can estimate the position of the detected obstacle at the time of capturing each image based on the position of the vehicle 10 measured by the positioning device, the traveling direction of the vehicle 10 measured by the direction sensor, the estimated distance to the detected obstacle, and the direction from the vehicle 10 toward the obstacle. It is assumed that the position of the bottom edge of the object area depicting the detected obstacle represents the position where the obstacle contacts the road surface. Therefore, the vehicle control unit 33 can calculate the estimated distance to the detected obstacle based on the position of the bottom edge of the object area in the exterior image and parameters of the exterior camera 2, such as the shooting direction and installation height. Alternatively, the vehicle control unit 33 may use the distance measured by a ranging sensor in the direction corresponding to the object area depicting the detected obstacle as the estimated distance to the detected obstacle. The vehicle control unit 33 can estimate the trajectory of each obstacle being tracked by arranging the estimated positions of the obstacles in chronological order. The vehicle control unit 33 can estimate the predicted trajectory of the obstacle up to a predetermined time ahead by performing prediction processing using a Kalman filter, a particle filter, or the like based on the traveling trajectory of the obstacle being tracked during the most recent predetermined period.

[0049] Based on the predicted trajectory of each obstacle being tracked, the vehicle control unit 33 controls each unit (powertrain, brake device, steering wheel) of the vehicle 10 so that the predicted value of the distance between each obstacle being tracked and the vehicle 10 for a predetermined time period ahead is equal to or greater than a predetermined distance. For example, assume that the vehicle 10 is traveling along its current course at its current speed and acceleration / deceleration, and that any detected obstacle moves along its predicted trajectory. At this time, if a collision between the vehicle 10 and the obstacle is predicted and the estimated predicted time until the collision is equal to or less than a predetermined collision determination time, the vehicle control unit 33 decelerates the vehicle 10 or changes the traveling direction of the vehicle 10. In this case, the vehicle control unit 33 may decelerate the vehicle 10 by more than a first deceleration amount, as necessary, before starting to enter the evacuation space.

[0050] When the vehicle 10 stops, the vehicle control unit 33 unlocks the doors and continues to sound the horn as a rescue support phase. The vehicle control unit 33 may also report the driver's abnormality via a wireless communication terminal (not shown) mounted on the vehicle 10.

[0051] FIG. 4 is an explanatory diagram of vehicle control processing when a turn-off space exists. In FIG. 4, graph 400 represents the change in speed depending on the position of vehicle 10. In this example, when vehicle 10 is located at position P1, a driver abnormality is detected and emergency stop mode is initiated. Thereafter, a control notice phase is executed until vehicle 10 reaches position P2. After vehicle 10 reaches position P2, a driving intervention phase begins, and vehicle 10 is decelerated by a first deceleration width D1. Thereafter, when vehicle 10 reaches position P3 where it can enter turn-off space S, vehicle 10 enters the turn-off space, and then vehicle 10 decelerates by a second deceleration width D2 and stops. In this way, when a turn-off space exists, vehicle 10 is controlled so that second deceleration width D2 is greater than first deceleration width D1.

[0052] FIG. 5 is an operational flowchart of the vehicle control process executed by the processor 23.

[0053] The abnormality detection unit 31 determines whether or not an abnormality has been detected in the driver (step S101). If an abnormality in the driver has not been detected (step S101-No), the processor 23 repeats the process of step S101.

[0054] On the other hand, if a driver abnormality is detected (step S101-Yes), the determination unit 32 determines whether or not an evacuation space exists within a predetermined range from the current position of the vehicle 10 (step S102). If an evacuation space exists (step S102-Yes), the vehicle control unit 33 decelerates the vehicle 10 by a first deceleration amount until the vehicle 10 reaches a position where it can enter the evacuation space (step S103). Then, when the vehicle 10 starts to enter the evacuation space, the vehicle control unit 33 decelerates the vehicle 10 by a second deceleration amount that is greater than the first deceleration amount, thereby stopping the vehicle 10 (step S104).

[0055] On the other hand, if there is no evacuation space (step S102-No), the vehicle control unit 33 decelerates the vehicle 10 by a third deceleration amount that is greater than the first deceleration amount (step S105). Thereafter, the vehicle control unit 33 searches for a parking space on the road shoulder where the vehicle 10 can stop, and stops the vehicle 10 in the parking space (step S106).

[0056] After step S104 or S106, vehicle control unit 33 unlocks the doors and notifies the driver of an abnormality (step S107), and processor 23 then ends the vehicle control process.

[0057] As explained above, when the vehicle control device brings the vehicle to an emergency stop upon detection of a driver abnormality, it controls the vehicle so that the second deceleration magnitude from when the vehicle starts the entry operation to when the vehicle stops is greater than the first deceleration magnitude from when the vehicle starts the entry operation to enter the evacuation space where the vehicle can escape. Therefore, the vehicle control device can shorten the time it takes for the vehicle to reach the evacuation space, and can therefore shorten the time it takes from when the driver abnormality is detected until the vehicle stops.

[0058] According to a modified example, the vehicle control unit 33 may set the collision avoidance condition for initiating an avoidance operation to avoid the vehicle 10 colliding with another object so that it is more lenient after the vehicle starts entering the evacuation space than before the vehicle starts entering the evacuation space. For example, the vehicle control unit 33 can relax the collision avoidance condition by lowering the detection threshold used to detect an obstacle after the vehicle starts entering the evacuation space compared to the detection threshold used to detect an obstacle before the vehicle starts entering the evacuation space. This is because a lower detection threshold makes it easier to detect an object to be detected. Alternatively, the vehicle control unit 33 may relax the collision avoidance condition by making the collision determination time after the vehicle starts entering the evacuation space longer than the collision determination time before the vehicle starts entering the evacuation space. Relaxing the collision avoidance condition in this way reduces the likelihood of the vehicle 10 colliding with an obstacle even when an evacuation space is not available.

[0059] A computer program for realizing the vehicle control process according to the above embodiment or modification may be provided in a form recorded on a computer-readable portable recording medium.

[0060] As described above, those skilled in the art can make various modifications to the embodiments within the scope of the present invention. [Explanation of symbols]

[0061] 1 Vehicle control system, 10 Vehicle, 2 Exterior camera, 3 Driver monitor camera, 4 GPS receiver, 5 Storage device, 6 Electronic control unit (ECU, vehicle control unit), 21 Communication interface, 22 Memory, 23 Processor, 31 Abnormality detection unit, 32 Determination unit, 33 Vehicle control unit

Claims

1. a storage unit that stores map information including information about an evacuation space into which the vehicle can escape; an abnormality detection unit that detects an abnormality occurring in the driver of the vehicle; a determination unit that, when an abnormality occurring in the driver is detected, determines whether the evacuation space exists within a predetermined range from the current position of the vehicle by referring to the map information or by recognizing a sign indicating the existence of the evacuation space from an outside image of the vehicle obtained by an outside camera that photographs the surroundings of the vehicle; a control unit that, when the evacuation space exists within the predetermined range, stops the vehicle at the evacuation space and controls the vehicle so that a second deceleration width of the vehicle from when the vehicle starts to enter the evacuation space until the vehicle stops is greater than a first deceleration width of the vehicle from when the vehicle starts to enter the evacuation space until the vehicle starts to enter the evacuation space; A vehicle control device having the above.

2. 2. The vehicle control device according to claim 1, wherein, when the evacuation space is not present within the predetermined range, the control unit decelerates the vehicle by a third deceleration amount greater than the first deceleration amount, searches for a stopping space where the vehicle can be stopped based on the exterior image, and stops the vehicle in the stopping space.

3. 3. The vehicle control device according to claim 1, wherein the control unit sets a collision avoidance condition for initiating an avoidance operation to avoid the vehicle colliding with another object so that the collision avoidance condition is relaxed after the entry operation has started compared to before the entry operation has started.

4. Detects abnormalities in the vehicle driver, When an abnormality occurring in the driver is detected, the system determines whether or not the evacuation space exists within a predetermined range from the current position of the vehicle by referring to map information including information about an evacuation space into which the vehicle can be evacuated, or by recognizing a sign indicating the existence of the evacuation space from an outside image of the vehicle obtained by an outside camera that photographs the surroundings of the vehicle; When the turn-off space is present within the predetermined range, the vehicle is stopped at the turn-off space, and the vehicle is controlled so that a second deceleration width of the vehicle from when the vehicle starts to enter the turn-off space until the vehicle stops is greater than a first deceleration width of the vehicle from when the vehicle starts to enter the turn-off space until the vehicle starts to enter the turn-off space. A vehicle control method comprising:

5. Detects abnormalities in the vehicle driver, When an abnormality occurring in the driver is detected, the system determines whether or not the evacuation space exists within a predetermined range from the current position of the vehicle by referring to map information including information about an evacuation space into which the vehicle can be evacuated, or by recognizing a sign indicating the existence of the evacuation space from an outside image of the vehicle obtained by an outside camera that photographs the surroundings of the vehicle; When the turn-off space is present within the predetermined range, the vehicle is stopped at the turn-off space, and the vehicle is controlled so that a second deceleration width of the vehicle from when the vehicle starts to enter the turn-off space until the vehicle stops is greater than a first deceleration width of the vehicle from when the vehicle starts to enter the turn-off space until the vehicle starts to enter the turn-off space. A computer program for vehicle control that causes a processor mounted on the vehicle to execute the above.

Images