Driving assistance device and driving assistance method

Abstract

To provide a drive support device capable of supporting drive of a driver while suppressing compression of storage capacity of a nonvolatile memory or an external storage device, and a drive support method.SOLUTION: A drive support device 5 stores route information including a vehicle travel route and surrounding conditions of a vehicle V in the travel route sequentially acquired by a recognition processing unit 51 at the time of output operation or input operation of the vehicle performed by a driver in a storage unit 50. The drive support device 5 includes a route generation unit 55 for generating a target route through which the vehicle should pass at the time of unloading or loading of the vehicle by utilizing the route information stored in the storage unit 50. The storage unit 50 includes at least one of a nonvolatile memory 50b and an external storage device 60. A route storage unit 54 stores a part of the route information as storage information in at least one of the nonvolatile memory 50b and the external storage device 60.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present disclosure relates to a driving assistance device and a driving assistance method. [Background technology]

[0002] Conventionally, a parking assistance device that automatically parks a vehicle in a specified parking space is known (see, for example, Patent Document 1). When the driver parks the vehicle, the parking assistance device described in Patent Document 1 stores the driving route from the reference start position to the parking position and the surrounding conditions of the driving route as continuous data in a storage unit, and generates a parking route that is a target route during parking assistance based on the stored data. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Special Publication No. 2013-530867 Summary of the Invention [Problem to be solved by the invention]

[0004] As described above, the parking assistance device described in Patent Document 1 stores continuous data on the driving route from the reference start position to the parking position and the surrounding conditions of the driving route, so the amount of data in the non-volatile memory becomes enormous. This is undesirable because it puts a strain on the storage capacity of the non-volatile memory, for example. This also occurs when storing data in an auxiliary storage unit installed in the vehicle or an external storage device such as an external server installed outside the vehicle.

[0005] An object of the present disclosure is to provide a driving assistance device and a driving assistance method that are capable of providing driving assistance to a driver while minimizing pressure on the storage capacity of a non-volatile memory or an external storage device. [Means for solving the problem]

[0006] Claim 1、2 The invention described in A driving assistance device, a route storage unit (54) that stores in a storage unit (50) route information including a vehicle travel route and a surrounding situation of the vehicle on the travel route, the route information being sequentially acquired by a recognition processing unit (51) when a driver performs a vehicle leaving or entering operation of the vehicle (V); a route generating unit (55) that generates a target route that the vehicle should take when leaving or entering the vehicle, using the route information stored in the storage unit; The storage unit includes at least one of a non-volatile memory (50b) and an external storage device (60); The route storage unit stores a portion of the route information as stored information in at least one of the non-volatile memory and the external storage device. The invention described in claim 1 is When a predetermined section in a travel route is defined as a first section, and a section in the travel route in which the amount of vehicle operation by the driver is greater than that in the first section is defined as a second section, The route memory unit thins out information regarding the first section from the route information according to a predetermined rule and stores it in at least one of the non-volatile memory and the external storage device, and stores information regarding the second section in at least one of the non-volatile memory and the external storage device without thinning it out. The invention described in claim 2 is The storage unit includes a volatile memory (50a) that temporarily stores the route information sequentially acquired by the recognition processing unit, The route storage unit stores all of the partial information stored in the volatile memory as stored information in at least one of the non-volatile memory and the external storage device.

[0007] Claim 8、9 The invention described in A driving assistance method, comprising: storing in a storage unit (50) route information including a travel route of the vehicle and a surrounding situation of the vehicle on the travel route, the travel route being sequentially acquired by a recognition processing unit (51) when a driver performs an operation of leaving or entering the vehicle (V) by the vehicle; generating a target route that the vehicle should take when leaving or entering the vehicle based on the information stored in the storage unit; The storage unit includes at least one of a non-volatile memory and an external storage device (60); When the route information is stored in the storage unit, a portion of the route information is stored as stored information in at least one of the non-volatile memory and the external storage device. The invention described in claim 8 is When a predetermined section in a travel route is defined as a first section, and a section in the travel route in which the amount of vehicle operation by the driver is greater than that in the first section is defined as a second section, When storing the route information in the memory unit, information regarding the first section of the route information is thinned out according to a predetermined rule and stored in at least one of the non-volatile memory and the external storage device, and information regarding the second section is stored in at least one of the non-volatile memory and the external storage device without being thinned out. The invention described in claim 9 is The storage unit includes a volatile memory (50a) that temporarily stores the route information successively acquired by the recognition processing unit, When the route information is stored in the storage unit, all of the partial information stored in the volatile memory is stored as stored information in at least one of the nonvolatile memory and the external storage device.

[0008] In this way, by storing a portion of the route information in the non-volatile memory as memory information, it is possible to reduce the strain on the storage capacity of the non-volatile memory compared to when all of the route information is stored in the non-volatile memory as continuous data. Therefore, according to the driving assistance device and driving assistance method disclosed herein, it is possible to provide driving assistance to the driver while reducing the strain on the storage capacity of the non-volatile memory.

[0009] The reference symbols in parentheses attached to each component indicate an example of the correspondence between the component and specific components described in the embodiments described below. [Brief description of the drawings]

[0010] [Figure 1] 1 is a schematic configuration diagram of an automatic parking system according to an embodiment. FIG. [Diagram 2] FIG. 13 is an explanatory diagram for explaining a situation when entering a vehicle backwards. [Diagram 3] FIG. 11 is an explanatory diagram for explaining an example of a driving route when leaving the warehouse in a forward direction. [Figure 4] 4 is a flowchart showing a flow of a learning process executed by a vehicle control unit of the embodiment. [Diagram 5] 5 is a flowchart showing a flow of information selection executed by a vehicle control unit. [Figure 6] FIG. 11 is an explanatory diagram for explaining an example of an index for identifying a section that becomes a second section. [Figure 7] 7 is an explanatory diagram for explaining a method for identifying a second section based on the indexes shown in FIG. 6. FIG. [Figure 8] 4 is a flowchart showing a flow of a following control process executed by a vehicle control unit. [Figure 9] FIG. 13 is an explanatory diagram for explaining the situation when leaving the warehouse facing backwards. [Figure 10] FIG. 11 is an explanatory diagram for explaining an example of a driving route when entering a storehouse facing forward. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0011] An embodiment of the present disclosure will be described below with reference to Fig. 1 to Fig. 8. In this embodiment, an example will be described in which a driving assistance device 5 and a driving assistance method according to the present disclosure are applied to an autonomous driving system 1. As shown in Fig. 1, the autonomous driving system 1 has a surroundings monitoring sensor 3, various ECUs 4, and a driving assistance device 5. The driving assistance device 5 is communicatively connected to the surroundings monitoring sensor 3 and the various ECUs 4 directly or via an in-vehicle LAN (Local Area Network).

[0012] The perimeter monitoring sensor 3 is an autonomous sensor that monitors the surrounding environment of the vehicle V. For example, the perimeter monitoring sensor 3 detects obstacles OB consisting of three-dimensional objects around the vehicle, such as moving dynamic targets such as pedestrians and other vehicles, and stationary static targets such as road structures, as detection objects, and parking assistance marks showing parking information, which is information about a parking lot PL. Here, the perimeter monitoring sensor 3 includes a perimeter monitoring camera 31 that captures an image of a predetermined range around the vehicle, a sonar 32 that transmits a search wave to a predetermined range around the vehicle, a millimeter wave radar 33, a LiDAR (Light Detection and Ranging) 34, and other search wave sensors.

[0013] The periphery monitoring camera 31 corresponds to an imaging device, captures images of the periphery of the vehicle, and outputs the captured image data as sensing information to the driving support device 5. Here, the periphery monitoring cameras 31 are exemplified by a front camera 31a, a rear camera 31b, a left side camera 31c, and a right side camera 31d, which capture images of the front, rear, left and right sides of the vehicle, but are not limited thereto.

[0014] The exploration wave sensor outputs exploration waves and sequentially outputs measurement results such as the relative speed and distance to the target and the azimuth angle at which the target is located, obtained by acquiring the reflected waves, as sensing information to the driving assistance device 5. The sonar 32 performs measurements using ultrasonic waves as exploration waves, and is provided at multiple locations on the vehicle V, for example, multiple units are arranged in the left and right directions of the vehicle on the front and rear bumpers, and performs measurements by outputting exploration waves around the vehicle. The millimeter wave radar 33 performs measurements using millimeter waves as exploration waves, and the LiDAR 34 performs measurements using laser light as exploration waves, and both output exploration waves within a predetermined range, for example, in front of the vehicle V, and perform measurements within the output range.

[0015] In this embodiment, the perimeter monitoring sensor 3 is exemplified by a perimeter monitoring camera 31, a sonar 32, a millimeter wave radar 33, and a LiDAR 34, but it is sufficient if perimeter monitoring can be performed using one or a combination of more of these, and it is not necessary to include all of them.

[0016] In addition, the driving support device 5 is connected to a map database 35 and a GPS 36, and is capable of measuring the current position of the vehicle V. The map database 35 may be built in an in-vehicle device, or may be built in a device outside the vehicle (for example, an external server).

[0017] The driving assistance device 5 constitutes an ECU (electronic control unit) for performing various controls to realize the driving assistance method in the autonomous driving system 1, and is composed of a microcomputer equipped with a CPU, a memory unit 50, I / O, etc.

[0018] The storage unit 50 includes a ROM, a RAM, an EEPROM, and the like. The storage unit 50 is configured of a non-transient tangible recording medium. Specifically, the storage unit 50 has a volatile memory 50a such as a RAM that temporarily stores information, and a non-volatile memory 50b such as an EEPROM. Unlike the volatile memory 50a, the non-volatile memory 50b retains its memory even when the ignition switch IG is turned off and the supply of power is stopped. The driving support device 5 is connected to an external storage device 60. The external storage device 60 is a storage device outside the driving support device 5. The external storage device 60 corresponds to an auxiliary storage unit 61 mounted on the vehicle or an external server 62 installed outside the vehicle. The auxiliary storage unit 61 is connected to the driving support device 5 via, for example, an in-vehicle LAN. The auxiliary storage unit 61 is composed of a large-capacity storage medium such as an HDD or SSD, and retains its storage even when the ignition switch IG is turned off and the power supply is stopped. The external server 62 is connected to the driving support device 5 via, for example, a WAN (Wide Area Network). The external server 62 is driven by a power source separate from the vehicle, and retains its storage even when the ignition switch IG is turned off. The external storage device 60 may be composed of one of the auxiliary storage unit 61 and the external server 62.

[0019] The driving assistance device 5 assists the driver in driving the vehicle V between the public road OL and a parking space SP provided on land along the public road OL. As shown in Fig. 2, the driving assistance device 5 of this embodiment assists the vehicle V in entering the parking space SP. Note that while Fig. 2 illustrates a situation in which the vehicle V enters the parking space backwards, the driving assistance provided by the driving assistance device 5 can be implemented not only when the vehicle enters the parking space backwards, but also when the vehicle enters the parking space forwards.

[0020] The driving assistance device 5 generates a target route that the vehicle V should take when parking the vehicle V, based on route information including the driving route of the vehicle V when the driver performs an entry or exit operation of the vehicle V and the surrounding conditions of the vehicle V on the driving route. Then, during driving assistance, the driving assistance device 5 automatically moves the vehicle V along the target route to the parking space SP, which is the planned parking position, or automatically moves the vehicle V from the parking space SP to a predetermined position.

[0021] The driving support device 5 stores in the storage unit 50, for example, route information including the driving route of the vehicle V and the surrounding conditions of the vehicle V on the driving route, which are sequentially acquired by the recognition processing unit 51 described later when the driver performs the operation of leaving the vehicle V, as shown in FIG. 3. In addition, the driving support device 5 may store in the storage unit 50, the route information sequentially acquired by the recognition processing unit 51 when the driver performs the operation of entering the vehicle V, as shown in FIG. 2. In this way, the driving support device 5 performs a learning process to store the route information during manual driving by the driver. This learning process is executed, for example, when a learning switch (not shown) is operated by the driver. In addition, the "surrounding conditions of the vehicle V" are, for example, dynamic targets such as people and other vehicles around the vehicle V, static targets such as curbs and buildings around the vehicle V, various signs, road markings such as guide lines, and the like.

[0022] While moving from the learning start position STP, which is the start position of the learning process, to the learning stop position SPP, the driving assistance device 5 recognizes targets, free spaces where parking is possible, parking positions, and the like on the driving route of the vehicle V based on sensing information from the periphery monitoring sensor 3. These recognition results are temporarily stored as route information in the volatile memory 50a of the storage unit 50. After that, a part of the route information stored in the volatile memory 50a is stored in the non-volatile memory 50b as memory information and is used during driving assistance.

[0023] The driving assistance device 5 performs various controls for generating a target route and driving assistance based on the stored information stored in the storage unit 50 and route information sequentially acquired by the recognition processing unit 51 during driving assistance. That is, when an instruction for driving assistance is issued, the driving assistance device 5 generates a target route based on the sensing information stored in the storage unit 50 and the sensing information of the surrounding monitoring sensor 3 during driving assistance, and performs route tracking control according to the route. Specifically, the driving assistance device 5 is configured to have a recognition processing unit 51, a vehicle information acquisition unit 52, and a vehicle control unit 53 as functional units that execute various controls.

[0024] The recognition processing unit 51 receives sensing information from the periphery monitoring sensor 3, and recognizes the surrounding environment of the vehicle to be parked, the scene of the parking scene, and three-dimensional objects present around the vehicle based on the sensing information. Specifically, the recognition processing unit 51 sequentially acquires route information including the travel route of the vehicle V and the surrounding conditions of the vehicle V on the travel route. Here, the recognition processing unit 51 is composed of an image recognition unit 51a, a space recognition unit 51b, and a free space recognition unit 51c.

[0025] The image recognition unit 51a includes a scene recognition unit 51aa, a three-dimensional object recognition unit 51ab, and a landmark / marker recognition unit 51ac. These units input image data from the surrounding surveillance camera 31 as sensing information, and perform scene recognition, three-dimensional object recognition, and landmark / marker recognition by performing image analysis of the image data.

[0026] In scene recognition, it is recognized what kind of parking scene it is, for example, whether it is a normal parking scene where there is ample aisle width on the route to the parking space SP, or a special parking scene where there is no ample aisle width on the route to the parking space SP due to an obstacle OB.

[0027] Since the image data input from the periphery monitoring camera 31 shows the surroundings, by analyzing the image, it is possible to determine whether the parking scene is a normal parking scene or a special parking scene. For example, the width of the parking space SP is calculated from the image data, and if the width is within a predetermined range that is set in advance based on the width of the vehicle, it can be determined that the parking scene is a special parking scene. Note that the scene recognition may be performed based not only on the sensing information of the periphery monitoring camera 31 but also on the sensing information of a search wave sensor.

[0028] In the three-dimensional object recognition, obstacles OB, which are three-dimensional objects around the vehicle, such as dynamic targets and static targets, are recognized as detection objects. Based on the shapes of the detection objects recognized by this three-dimensional object recognition, preferably static targets, the above-mentioned scene recognition and the generation of a driving assistance map including the obstacles OB are performed.

[0029] In landmark / marker recognition, landmarks indicating parking spaces SP, graphic marks indicating parking lots PL, graphic marks indicating parking orientation, two-dimensional barcodes indicating parking scenes and parking orientations, etc. are recognized. The above-mentioned scene recognition is performed based on the marks recognized by landmark / marker recognition. In addition, for example, parking assistance marks indicating parking information such as parking scenes are attached in or in front of the parking space SP, and when a parking assistance mark is found in the captured image data, the type of parking scene indicated by the parking assistance mark can be recognized.

[0030] The space recognition unit 51b also has a three-dimensional object recognition unit 51ba. The three-dimensional object recognition unit 51ba recognizes three-dimensional objects in the space around the vehicle based on sensing information from at least one of the sonar 32, the millimeter wave radar 33, and the LiDAR 34. The three-dimensional object recognition here is similar to the three-dimensional object recognition performed by the image recognition unit 51a. Therefore, three-dimensional object recognition can be performed if either the image recognition unit 51a or the space recognition unit 51b is provided. In addition, in the case of this embodiment, the space recognition unit 51b does not perform scene recognition, but the space recognition unit 51b can also perform scene recognition based on sensing information from at least one of the sonar 32, the millimeter wave radar 33, and the LiDAR 34.

[0031] Although three-dimensional object recognition and scene recognition can be performed by either the image recognition unit 51a or the space recognition unit 51b, more accurate three-dimensional object recognition and scene recognition can be performed by using both of them. For example, three-dimensional object recognition and scene recognition by the image recognition unit 51a can be complemented by three-dimensional object recognition and scene recognition by the space recognition unit 51b, thereby making it possible to perform three-dimensional object recognition and scene recognition with higher accuracy.

[0032] The free space recognition unit 51c performs free space recognition to recognize a place that is a free space in the parking lot PL. The free space means, for example, a space in the parking lot PL that has an area and shape that allows the vehicle V to run.

[0033] The free space recognition unit 51c recognizes free spaces in the parking lot PL based on the results of scene recognition and three-dimensional object recognition by the image recognition unit 51a and the space recognition unit 51b. For example, the shape of the parking lot PL and the presence or absence of other vehicles parked therein can be ascertained from the results of scene recognition and three-dimensional object recognition, and the free space recognition unit 51c recognizes free spaces in the parking lot PL based on the results.

[0034] The map information matching unit 51d acquires map information from the map database 35, and identifies the position of the vehicle V on the map as the current position by matching the acquired map information with the position information acquired by the GPS 36. The map information matching unit 51d may be configured to identify the current position of the vehicle V by using information other than the map information in the map database 35 and the position information acquired by the GPS 36.

[0035] The vehicle information acquisition unit 52 acquires information on the operation amount of the vehicle V from other ECUs 4, etc. Specifically, the vehicle information acquisition unit 52 acquires detection signals output from each sensor mounted on the vehicle V, such as an accelerator position sensor, a brake depression force sensor, a steering angle sensor, a wheel speed sensor, a shift position sensor, etc.

[0036] The vehicle control unit 53 executes various controls required for driving assistance. Specifically, the vehicle control unit 53 includes a route storage unit 54, a route generation unit 55, a position estimation unit 56, and a following control unit 57 as functional units that execute various controls.

[0037] The route storage unit 54 stores in the storage unit 50 route information including a driving route through which the vehicle V passes when the driver performs one of an operation of leaving the parking space SP and an operation of entering the parking space SP, and the surrounding conditions of the vehicle V on the driving route. The route storage unit 54 of this embodiment stores in the storage unit 50 route information when the driver performs an operation of leaving the parking space SP. Specifically, the route storage unit 54 stores in the storage unit 50 route information including landmarks on the driving route of the vehicle V, free spaces in which parking can be performed, parking positions, etc., sequentially acquired by the recognition processing unit 51.

[0038] The route generating unit 55 generates a route based on the results of the scene recognition, the three-dimensional object recognition, and the free space recognition. The route generating unit 55 generates a target route that the vehicle V should take when entering or leaving the warehouse, based on the route information stored during the learning process. For example, the route generating unit 55 uses the travel route of the vehicle V as a reference route, and when there is a section in the reference route where the distance between the vehicle V and an obstacle OB is equal to or smaller than a predetermined value, the route generating unit 55 replaces the section with a route where the distance between the vehicle V and the obstacle OB exceeds the predetermined value, and generates the target route. Note that the obstacle OB is composed of a three-dimensional object recognized by the three-dimensional object recognition.

[0039] Here, the route generating unit 55 avoids the obstacle OB when generating the target route, but it may generate the target route by avoiding only the static targets. Since the dynamic targets move, the vehicle V may be moved only after there is no risk of collision with the dynamic targets. In that case, it is sufficient to generate the target route taking into consideration only the static targets.

[0040] The position estimation unit 56 estimates the current position of the vehicle V based on the route information stored in the memory unit 50 and the route information sequentially acquired by the recognition processing unit 51 during driving assistance. The position estimation unit 56, for example, compares the sensing information stored in the memory unit 50 with the sensing information acquired during driving assistance, and estimates the current position based on the difference therebetween.

[0041] The following control unit 57 automatically moves the vehicle V to the parking space SP along the target route by performing vehicle motion control such as acceleration / deceleration control and steering control of the vehicle V. Specifically, the following control unit 57 outputs control signals to the various ECUs 4 so that the vehicle V reaches the parking space SP along the target route.

[0042] The various ECUs 4 include a steering ECU 41 that performs steering control, a brake ECU 42 that performs acceleration / deceleration control, a power management ECU 43, and a body ECU 44 that controls various electrical components such as lights and door mirrors.

[0043] Specifically, the following control unit 57 acquires detection signals output from various sensors mounted on the vehicle V, such as an accelerator position sensor, a brake depression force sensor, a steering angle sensor, a wheel speed sensor, and a shift position sensor, via the vehicle information acquisition unit 52. Then, the following control unit 57 detects the state of each part from the acquired detection signals, and outputs control signals to the various ECUs 4 to move the vehicle V by following the target route.

[0044] Here, there may be a case where a static target object that was not recognized when the target route was initially calculated exists. Therefore, the three-dimensional object recognition units 51ab and 51ba continue to recognize the three-dimensional object while the vehicle V is moving while following the target route. Also, if the static target object exists in a place where the vehicle V may collide with the static target object when the vehicle V moves while following the target route, the vehicle V is guided to a route different from the target route. Note that, for example, when the vehicle V is moved from the current position to the parking space SP, a person or another vehicle may approach. Therefore, the following control unit 57 temporarily stops the vehicle V until the dynamic target object is outside the range of the planned movement trajectory of the vehicle V estimated from the target route and the vehicle width, so that the vehicle V does not collide with the dynamic target object.

[0045] The following control unit 57 includes a suggestion unit 58 that proposes a target route to the driver. The suggestion unit 58 makes various suggestions, including driving assistance, to the driver through the HMI (short for Human Machine Interface) 45. The HMI 45 is a device for providing various assistance to the driver. The HMI 45 functions as a notification device having an ECU, a display, a speaker, etc. Note that the suggestion unit 58 does not have a function specialized for the following control unit 57, and may be usable in conjunction with other functional units.

[0046] The automatic driving system 1 according to this embodiment is configured as described above. Next, the operation of the automatic driving system 1 configured in this manner will be described. In this embodiment, as shown in FIG. 2, an example will be described in which a vehicle V is parked in a parking space SP provided in a parking lot PL along a public road OL. The parking lot PL shown in FIG. 2 has a portion in the passage from the public road OL to the parking space SP that has an aisle width that allows one vehicle V to pass through. FIG. 2 also illustrates an example of backward parking in which the vehicle V is moved backward into the parking space SP and parked.

[0047] First, the learning process for storing route information during manual driving by the driver will be described with reference to the flowchart shown in Fig. 4. The learning process shown in Fig. 4 is executed by the vehicle control unit 53 at every predetermined control period when an instruction to start from a parked state is issued, such as when the ignition switch IG is turned on. Note that each process shown in this flowchart is realized by each functional unit of the driving support device 5. Also, each step for realizing this process can be understood as each step for realizing a driving support method.

[0048] 4, the vehicle control unit 53 starts the recognition process in step S100. In this recognition process, sensing information from the periphery monitoring sensor 3 is input, and the above-mentioned scene recognition, three-dimensional object recognition, and free space recognition are started based on the input sensing information. In addition, in the recognition process, detection of the current position of the vehicle V using the map database 35 and the GPS 36 is started.

[0049] Next, in step S110, the vehicle control unit 53 determines whether or not a learning start command has been received from the driver. This determination process is performed based on, for example, whether or not a learning switch (not shown) has been turned on by the driver.

[0050] The vehicle control unit 53 proceeds to step S120 if an instruction to start learning is received, and waits if an instruction to start learning is not received. The vehicle control unit 53 starts storing various information necessary for driving assistance in step S120. The vehicle control unit 53 stores route information including the driving route of the vehicle V and the surrounding conditions of the driving route, which are sequentially acquired by the recognition processing unit 51, in the volatile memory 50a of the storage unit 50.

[0051] Next, in step S130, the vehicle control unit 53 determines whether or not the driver has instructed the vehicle to stop learning. This determination process is performed, for example, based on whether or not the driver has turned off a learning switch (not shown). If the driver has instructed the vehicle to stop learning, the vehicle control unit 53 proceeds to step S140, and if the driver has not instructed the vehicle to stop learning, the vehicle control unit 53 waits. In step S140, the vehicle control unit 53 stops storing various pieces of information necessary for driving assistance.

[0052] Next, in step S150, the vehicle control unit 53 stores a part of the route information stored in the volatile memory 50a in the non-volatile memory 50b as storage information, and ends the learning process. Note that the learning process from step S100 to step S150 is performed by the route storage unit 54 of the vehicle control unit 53.

[0053] In the process of step S150, the vehicle control unit 53 selects the route information stored in the volatile memory 50a and stores it in the non-volatile memory 50b so that more information corresponding to some sections in the travel route of the vehicle V is included than information of other sections. Hereinafter, an example of the information selection process executed by the vehicle control unit 53 will be described with reference to FIG.

[0054] 5, in step S200, the vehicle control unit 53 divides the driving route of the vehicle V into a plurality of sections, and determines whether or not each of the plurality of sections is a section in which the amount of operation of the vehicle V is large. Note that the determination process in step S200 is performed based on, for example, sensor outputs of an accelerator position sensor, a brake depression force sensor, a steering angle sensor, a shift position sensor, and the like acquired via the vehicle information acquisition unit 52.

[0055] For example, the vehicle control unit 53 divides the travel route into a plurality of equal sections. Then, the vehicle control unit 53 judges whether each of the plurality of sections corresponds to at least one of the five sections listed in FIG. 6. That is, the vehicle control unit 53 judges whether each of the plurality of sections corresponds to any of the following: a section in which the vehicle V is turned around, a section in which the amount of operation of the accelerator or brake by the driver changes by a certain amount or more, and a section in which the travel state of the vehicle V changes. The section in which the travel state of the vehicle V changes is a section in which the travel state of the vehicle V changes from straight travel to turning travel and a section in which the travel state changes from turning travel to straight travel. As a result, for example, as shown by the circle S in FIG. 7, the vicinity of the learning start position STP, the vicinity of the learning stop position SPP, and the vicinity of the position in which the traveling direction of the vehicle V changes on the travel route are set as the second section.

[0056] If the section is not one in which the amount of operation of the vehicle V is large, the vehicle control unit 53 proceeds to step S210 and sets the section to be judged as the first section. On the other hand, if the section is one in which the amount of operation of the vehicle V is large, the vehicle control unit 53 proceeds to step S220 and sets the section to be judged as the second section. The second section is a section in which the amount of operation of the vehicle V is larger than the first section, which is a predetermined section of the travel route.

[0057] Next, in step S230, the vehicle control unit 53 determines whether or not the section setting for each of the multiple sections has been completed. If the section setting for each of the multiple sections has not been completed, the vehicle control unit 53 returns to step S200, and if the section setting for each of the multiple sections has been completed, the vehicle control unit 53 proceeds to step S230.

[0058] In step S230, the vehicle control unit 53 stores the second information corresponding to the second section in the non-volatile memory 50b in preference to the first information corresponding to the first section among the route information stored in the volatile memory 50a, and then exits from this process. For example, the vehicle control unit 53 thins out the information related to the first section according to a predetermined rule and stores it in the non-volatile memory 50b, while storing the information related to the second section in the non-volatile memory 50b without thinning it out. As a result, the storage information stored in the non-volatile memory 50b is such that the first information corresponding to the first section is sparse and the second information corresponding to the second section is dense. In other words, the storage information contains more second information corresponding to the second section included in the route information than first information corresponding to the first section included in the route information.

[0059] Next, the following control process for automatically moving the vehicle V to the parking space SP along the target route will be described with reference to the flowchart shown in Fig. 8. The following control process shown in Fig. 8 is executed by the vehicle control unit 53 at each predetermined control period in a situation where the learning process has been performed at least once. Note that each process shown in this flowchart is realized by each functional unit of the driving assistance device 5. Also, each step for realizing this process can be understood as each step for realizing a driving assistance method.

[0060] 8, the vehicle control unit 53 starts the recognition process in step S300. In this recognition process, sensing information from the periphery monitoring sensor 3 is input, and the above-mentioned scene recognition, three-dimensional object recognition, and free space recognition are started based on the input sensing information.

[0061] Next, in step S310, the vehicle control unit 53 determines whether or not the current position of the vehicle V is near the assistance start position designated in advance by the driver. Specifically, the vehicle control unit 53 determines whether or not the current position of the vehicle V is near the assistance start position by using the sensing information of the periphery monitoring sensor 3, the map database 35, and the GPS 36. The assistance start position is set, for example, near the vehicle entrance / exit B that is the boundary between the public road OL and the parking lot PL.

[0062] The vehicle control unit 53 waits if the current position of the vehicle V is not near the assistance start position, and proceeds to step S320 if the current position of the vehicle V is near the assistance start position. When proceeding to step S320, the vehicle control unit 53 proposes driving assistance for the entrance operation to the driver via the HMI 45. Then, in step S330, the vehicle control unit 53 determines whether or not an instruction to provide driving assistance for the entrance operation has been received from the driver via the HMI 45.

[0063] If the driver does not instruct the vehicle control unit 53 to provide driving assistance for the entry operation, the vehicle control unit 53 skips the subsequent processes and exits from this process. On the other hand, if the driver instructs the vehicle control unit 53 to provide driving assistance for the entry operation, the vehicle control unit 53 executes a target route generation process in step S340. The vehicle control unit 53 generates a target route that the vehicle V should take when parking the vehicle V based on route information including the driving route of the vehicle V at the time of the learning process.

[0064] Next, in S350, the vehicle control unit 53 estimates the current position of the vehicle V based on the stored information stored in the storage unit 50 and the route information successively acquired by the periphery monitoring sensor 3 during driving assistance.

[0065] Next, in step S360, the vehicle control unit 53 performs vehicle motion control such as acceleration / deceleration control and steering control of the vehicle V to automatically move the vehicle V to the parking space SP. Specifically, the vehicle control unit 53 outputs control signals to the various ECUs 4 so that the vehicle V reaches the parking space SP along the target route. Thereafter, in step S370, the vehicle control unit 53 determines whether the vehicle V has reached the parking space SP, which is the assistance end position. If the vehicle V has not reached the assistance end position, the vehicle control unit 53 returns to the process of step S350, and if the vehicle V reaches the assistance end position, the vehicle control unit 53 exits the assistance process. The processes of steps S350, S360, and S370 are performed by the following control unit 57 of the vehicle control unit 53.

[0066] The driving assistance device 5 described above stores in the storage unit 50 route information including the driving route of the vehicle V and the surrounding conditions of the vehicle V on the driving route, which are sequentially acquired by the recognition processing unit 51 when the driver performs a leaving or entering operation of the vehicle V. The driving assistance device 5 includes a route generating unit 55 that uses the route information stored in the storage unit 50 to generate a target route that the vehicle V should take when leaving or entering the storage. The storage unit 50 includes a non-volatile memory 50b. The route storage unit 54 stores a portion of the route information in the non-volatile memory 50b as storage information.

[0067] In this way, by storing a part of the route information as storage information in the non-volatile memory 50b, it is possible to suppress the pressure on the storage capacity of the non-volatile memory 50b compared to the case where all of the route information is stored in the non-volatile memory 50b. Therefore, according to the driving assistance device 5 and the driving assistance method disclosed herein, it is possible to perform driving assistance for the driver while suppressing the pressure on the storage capacity of the non-volatile memory 50b.

[0068] Moreover, according to the driving support device 5 of this embodiment, the following effects can be obtained.

[0069] (1) The storage unit 50 includes a volatile memory 50a that temporarily stores route information sequentially acquired by the recognition processing unit 51. The route storage unit 54 stores some of the route information stored in the volatile memory 50a in the non-volatile memory 50b as stored information. In this way, once the route information sequentially acquired by the recognition processing unit 51 is stored in the volatile memory 50a, it is possible to select information to be stored in the non-volatile memory 50b from the route information sequentially acquired by the recognition processing unit 51.

[0070] (2) The stored information includes more second information corresponding to the second section included in the route information than first information corresponding to the first section included in the route information. This ensures an amount of information for sections where the driver operates the vehicle V a lot, thereby reducing the impact on the driver's driving assistance that is caused by a reduction in the amount of information stored in the non-volatile memory 50b.

[0071] (3) The route storage unit 54 identifies the second section of the travel route based on the route information stored in the volatile memory 50a. This makes it possible to appropriately select information to be stored in the non-volatile memory 50b.

[0072] (4) Specifically, the second section includes at least one of a section where a turning operation of the vehicle V is performed, a section where the amount of operation of at least one of the accelerator operation and the brake operation by the driver changes, and a section where the driving condition of the vehicle V changes. The section where the driving condition of the vehicle V changes is a section where the driving condition of the vehicle V changes from straight driving to turning driving and a section where the driving condition changes from turning driving to straight driving.

[0073] (5) The driving assistance device 5 includes a following control unit 57 that automatically causes the vehicle V to leave or enter the garage based on the current position and the target route of the vehicle V. The driving assistance device 5 includes a position estimation unit 56 that estimates the current position based on stored information and route information successively acquired by the recognition processing unit 51 when the vehicle V is automatically moved by the following control unit 57. This makes it possible to appropriately assist the vehicle V in leaving or entering the garage.

[0074] (Modification) The driving support device 5 may be configured to support the exit operation of the vehicle V from the parking space SP, for example, as shown in Fig. 9. Note that Fig. 9 illustrates a situation in which the vehicle V exits the parking space backwards, but the driving support by the driving support device 5 is not limited to the case in which the vehicle exits the parking space backwards, and can also be performed when the vehicle V exits the parking space forwards.

[0075] For example, as shown in FIG. 10, when the driver performs a yard entry operation of the vehicle V, the driving assistance device 5 stores part of the route information sequentially acquired by the recognition processing unit 51 as storage information in the non-volatile memory 50b of the storage unit 50. The driving assistance device 5 performs various controls for generating a target route and driving assistance based on the storage information stored in the storage unit 50 and the route information sequentially acquired by the recognition processing unit 51 during driving assistance. The driving assistance device 5 may be configured to store part of the route information sequentially acquired by the recognition processing unit 51 as storage information in the non-volatile memory 50b of the storage unit 50 when the driver performs a yard exit operation of the vehicle V.

[0076] The route storage unit 54 stores part of the route information as storage information in the non-volatile memory 50b, but may store part of the route information in the external storage device 60 instead of the non-volatile memory 50b. In this case, the route storage unit 54 stores part of the route information stored in the volatile memory 50a in the external storage device 60 as storage information. Then, the route generation unit 55 uses the storage information stored in the external storage device 60 to generate a target route that the vehicle V should take when leaving or entering the garage. According to these, it is possible to suppress the pressure on the storage capacity of the external storage device 60 compared to the case where all of the route information is stored in the external storage device 60. Therefore, according to the driving support device 5 and the driving support method of the present disclosure, it is possible to perform driving support for the driver while suppressing the pressure on the storage capacity of the external storage device 60. In addition, it is possible to suppress the amount of communication between the driving support device 5 and the external storage device 60.

[0077] (Other embodiments) Representative embodiments of the present disclosure have been described above, but the present disclosure is not limited to the above-described embodiments and can be modified in various ways, for example, as described below.

[0078] In the above embodiment, the detailed configuration of the driving assistance device 5, the detailed contents of the learning process, and the detailed contents of the following control process have been described, but the present invention is not limited to these, and some of these may be different.

[0079] For example, the driving assistance device 5 in the above embodiment is connected to the map database 35 and the GPS 36, but this is not essential. The driving assistance device 5 does not have to be connected to the map database 35 and the GPS 36, for example.

[0080] In the above embodiment, the route information sequentially acquired by the recognition processing unit 51 is stored in the volatile memory 50a, and some of the route information stored in the volatile memory 50a is stored as stored information in the non-volatile memory 50b, but the driving support device 5 is not limited to this. For example, the driving support device 5 may store some of the route information sequentially acquired by the recognition processing unit 51 in the volatile memory 50a, and store all of the information stored in the volatile memory 50a in the non-volatile memory 50b as stored information.

[0081] As in the above embodiment, it is desirable that the stored information contains more second information corresponding to the second section included in the route information than the first information corresponding to the first section included in the route information, but this is not limited thereto. For example, the stored information may contain less second information corresponding to the second section than the first information corresponding to the first section included in the route information.

[0082] In the above embodiment, a specific example of a method for identifying the second section is given, but the method is not limited to this, and the second section may be identified by another method.

[0083] In the above-described embodiment, an example has been described in which the driving assistance device 5 of the present disclosure is applied to driving assistance in a small parking lot PL in front of one's home, but the application is not limited to this, and can also be applied to driving assistance in other areas other than the parking lot PL in front of one's home.

[0084] In the above embodiment, the automatic driving control including the driving assistance control by the automatic driving system 1 has been described, but the driving assistance may include control for generating a target route for moving the vehicle and parking it in the parking space SP, regardless of whether the vehicle is driven automatically. For example, the driving assistance also includes a case where the target route is simply displayed on a display and used as an indicator when the driver drives the vehicle to enter or leave the parking space, and it is not essential that the path following control for automatically moving the vehicle along the target route is performed.

[0085] In the above-described embodiments, it goes without saying that the elements constituting the embodiments are not necessarily essential, except in cases where it is particularly expressly stated that they are essential or where they are clearly considered to be essential in principle.

[0086] In the above-described embodiments, when numerical values ​​such as the number, values, amounts, ranges, etc. of components of the embodiments are mentioned, they are not limited to the specific numbers unless it is specifically stated as required or unless it is clearly limited to a specific number in principle.

[0087] In the above-described embodiments, when referring to the shapes, positional relationships, etc. of components, etc., there is no limitation to those shapes, positional relationships, etc., unless specifically stated or in principle limited to a specific shape, positional relationship, etc.

[0088] The control unit and the method of the present disclosure may be implemented in a special-purpose computer provided by configuring a processor and a memory programmed to execute one or more functions embodied in a computer program. The control unit and the method of the present disclosure may be implemented in a special-purpose computer provided by configuring a processor with one or more dedicated hardware logic circuits. The control unit and the method of the present disclosure may be implemented in one or more special-purpose computers configured by a combination of a processor and a memory programmed to execute one or more functions and a processor configured with one or more hardware logic circuits. The computer program may also be stored in a computer-readable non-transitory tangible recording medium as instructions executed by a computer. [Explanation of symbols]

[0089] 5 Driving assistance devices 50 Storage section 50b Non-volatile memory 54 Route memory section 55 Route Generation Unit 60 External storage device

Claims

1. A driving assistance device, a route storage unit (54) that stores in a storage unit (50) route information including a travel route of the vehicle (V) and a surrounding situation of the vehicle on the travel route, the route information being sequentially acquired by a recognition processing unit (51) when a driver performs a vehicle leaving or entering operation of the vehicle (V); a route generating unit (55) that generates a target route that the vehicle should take when leaving or entering the vehicle, using the route information stored in the storage unit; The storage unit includes a non-volatile memory (50b) and an external storage device (60); the route storage unit stores a portion of the route information as stored information in at least one of the non-volatile memory and the external storage device; When a predetermined section in the travel route is defined as a first section, and a section in the travel route in which an operation amount of the vehicle by the driver is greater than that in the first section is defined as a second section, A driving assistance device, wherein the route memory unit thins out information regarding the first section from the route information according to a predetermined rule and stores it in at least one of the non-volatile memory and the external storage device, and stores information regarding the second section in at least one of the non-volatile memory and the external storage device without thinning out the information.

2. A driving assistance device, a route storage unit (54) that stores in a storage unit (50) route information including a travel route of the vehicle (V) and a surrounding situation of the vehicle on the travel route, the route information being sequentially acquired by a recognition processing unit (51) when a driver performs a vehicle leaving or entering operation of the vehicle (V); a route generating unit (55) that generates a target route that the vehicle should take when leaving or entering the vehicle, using the route information stored in the storage unit; the storage unit includes a non-volatile memory (50b), an external storage device (60), and a volatile memory (50a) that temporarily stores a portion of the route information sequentially acquired by the recognition processing unit; The route storage unit storing a part of the route information as storage information in at least one of the non-volatile memory and the external storage device; A driving assistance device that stores all of the route information stored in the volatile memory as the stored information in at least one of the non-volatile memory and the external storage device.

3. The storage unit includes a volatile memory (50a) that temporarily stores the route information sequentially acquired by the recognition processing unit, The driving assistance device according to claim 1 , wherein the route storage unit stores the part of the route information stored in the volatile memory as the stored information in at least one of the non-volatile memory and the external storage device.

4. When a predetermined section in the travel route is defined as a first section, and a section in the travel route in which an operation amount of the vehicle by the driver is greater than that in the first section is defined as a second section, 3. The driving assistance device according to claim 2, wherein the stored information includes more second information corresponding to the second section included in the route information than first information corresponding to the first section included in the route information.

5. The driving assistance device according to claim 1 , wherein the route storage unit identifies the second section of the travel route based on the route information stored in the volatile memory.

6. 5. The driving assistance device according to claim 1, 3, or 4, wherein the second section includes at least one of a section in which a turning operation of the vehicle is performed, a section in which an amount of operation of at least one of an accelerator operation and a brake operation by the driver changes, a section in which a driving state of the vehicle changes from straight driving to turning driving, and a section in which the driving state changes from the turning driving to the straight driving.

7. A tracking control unit (57) that automatically causes the vehicle to leave or enter the garage based on the current position of the vehicle and the target route; and a position estimation unit (56) that estimates the current position based on the memory information stored in the memory unit and the route information successively acquired by the recognition processing unit when the vehicle is automatically moved by the following control unit.

8. A driving assistance method, comprising: storing in a storage unit (50) route information including a travel route of the vehicle (V) and a surrounding situation of the vehicle on the travel route, the travel route being sequentially acquired by a recognition processing unit (51) when a driver performs a vehicle leaving or entering operation of the vehicle (V); generating a target route that the vehicle should take when leaving or entering the vehicle based on the information stored in the storage unit; The storage unit includes a non-volatile memory (50b) and an external storage device (60); When storing the route information in the storage unit, a part of the route information is stored as storage information in at least one of the non-volatile memory and the external storage device; When a predetermined section in the travel route is defined as a first section, and a section in the travel route in which an operation amount of the vehicle by the driver is greater than that in the first section is defined as a second section, A driving assistance method in which, when storing the route information in the storage unit, information regarding the first section of the route information is thinned out according to a predetermined rule and stored in at least one of the non-volatile memory and the external storage device, and information regarding the second section is stored in at least one of the non-volatile memory and the external storage device without being thinned out.

9. A driving assistance method, comprising: storing in a storage unit (50) route information including a travel route of the vehicle (V) and a surrounding situation of the vehicle on the travel route, the travel route being sequentially acquired by a recognition processing unit (51) when a driver performs a vehicle leaving or entering operation of the vehicle (V); generating a target route that the vehicle should take when leaving or entering the vehicle based on the information stored in the storage unit; the storage unit includes a non-volatile memory (50b), an external storage device (60), and a volatile memory (50a) that temporarily stores a portion of the route information sequentially acquired by the recognition processing unit; When the route information is stored in the storage unit, storing a part of the route information as storage information in at least one of the non-volatile memory and the external storage device; A driving assistance method comprising: storing all of the route information stored in the volatile memory as the stored information in at least one of the non-volatile memory and the external storage device.

Images