Driving assistance systems

Abstract

To stabilize behavior of an automatic driving vehicle which detects a target and performs avoidance traveling.SOLUTION: A driving support device according to the present invention includes: an acquisition unit configured to acquire information on a target at least in a traveling direction of an own vehicle; a generation unit configured to generate a region corresponding to the target; a calculation unit configured to calculate size of the region; a setting unit configured to set vehicle speed of the own vehicle according to a change amount of the size of the region; and a control unit configured to control traveling of the own vehicle based on the vehicle speed set by the setting unit.SELECTED DRAWING: Figure 3

Description

TECHNICAL FIELD

[0001] The present invention relates to a vehicle driving assistance device.

BACKGROUND ART

[0002] In recent years, research on automated driving vehicles has been advanced. An automated driving vehicle refers to a motor vehicle in which a system (machine) performs at least part of actions such as recognition, judgment, and driving operations (acceleration, steering, braking, etc.) that a driver (human) performs during driving, on behalf of the driver.

[0003] Hereinafter, the prior art will be described with reference to FIG. 6 and FIG. 7. FIG. 6 and FIG. 7 are explanatory diagrams of the prior art. As shown in FIG. 6, when the host vehicle C1, which is an automated driving vehicle traveling along the original route R1, performs avoidance traveling to avoid a roadside parked vehicle C2 (an example of an obstacle; hereinafter also referred to as "target object") present in the traveling direction, for example, the following processes (1) to (3) are executed.

[0004] (1) Detect a region A (for example, a rectangle) corresponding to the roadside parked vehicle C2 (2) Generate an avoidance route R2 based on the region A and an appropriate margin (3) Reduce the speed and travel along the avoidance route R2

[0005] In addition, the speed in (3) is generally determined, for example, as in the following (11) to (13). (11) Determine as a preset speed for avoidance traveling (fixed value) (12) Determine based on the curvature of the avoidance route R2 (13) Determine based on the degree of deviation between the avoidance route R2 and the original route R1

PRIOR ART DOCUMENTS

PATENT DOCUMENTS

[0006]

PATENT DOCUMENT 1

SUMMARY OF INVENTION

[0007] However, in the conventional technology described above, the region A corresponding to both parked vehicles C2 cannot always be detected stably and with high accuracy. For example, as shown in Figure 7, the detected region A may change significantly over time. Also, generally speaking, the detected region A tends to change more significantly on curves than on straight roads.

[0008] Furthermore, in situations where area detection is unstable, the generated avoidance paths also become unstable, leading to problems such as lateral swaying of the vehicle during avoidance maneuvers.

[0009] Therefore, the object of the present invention is to provide a driving assistance device that can stabilize the behavior of an autonomous vehicle that detects and avoids targets. [Means for solving the problem]

[0010] To solve the above-mentioned problems, the driving assistance device of the present invention includes an acquisition unit that acquires information on targets in at least the direction of travel of the vehicle, a generation unit that generates a region corresponding to the target, and a calculation unit that calculates the size of the region. Based on time-series data of the size of the aforementioned region Change in the size of the aforementioned region An indicator showing instability The system includes a setting unit that sets the vehicle speed accordingly, and a control unit that controls the vehicle's movement based on the vehicle speed set by the setting unit.

[0011] According to the above configuration, by changing the vehicle speed in accordance with the amount of change in the size of the area corresponding to the target, the behavior of the autonomous vehicle that detects and avoids the target can be stabilized.

[0012] Furthermore, the setting unit sets the vehicle speed of the vehicle to a lower value as the amount of change in the size of the area increases.

[0013] Since the smaller the vehicle speed of the host vehicle is, the higher the detection accuracy of the region corresponding to the target is, according to the above configuration, by setting the vehicle speed of the host vehicle to be smaller as the amount of change in the size of the region is larger, the detection accuracy can be improved and the vehicle behavior can be stabilized.

[0014] Further, the setting unit sets the vehicle speed of the host vehicle to be small when the amount of change in the size of the region exceeds a first threshold value.

[0015] Since the smaller the vehicle speed of the host vehicle is, the higher the detection accuracy of the region corresponding to the target is, according to the above configuration, by setting the vehicle speed of the host vehicle to be small when the amount of change in the size of the region exceeds the first threshold value, the detection accuracy can be improved and the vehicle behavior can be stabilized.

[0016] Further, after setting the vehicle speed of the host vehicle to be small, the setting unit sets the vehicle speed of the host vehicle to be large when the amount of change in the size of the region becomes equal to or less than a second threshold value.

[0017] According to the above configuration, when the amount of change in the size of the region is equal to or less than the second threshold value, it is considered that the detection accuracy of the region has been improved, so by setting the vehicle speed to be large, it is possible to avoid a situation where the low-speed state continues more than necessary while stabilizing the vehicle behavior. [Effects of the Invention]

[0018] According to the present invention, it is possible to stabilize the behavior of an autonomous driving vehicle that detects a target and travels to avoid the target. [Brief Description of the Drawings]

[0019] [Figure 1] Figure 1 is a block diagram showing a schematic configuration of a vehicle equipped with a driving support device according to a first embodiment. [Figure 2] Figure 2 is a functional configuration diagram of an autonomous driving ECU according to the first embodiment. [Figure 3] Figure 3 is a flowchart showing processing by the autonomous driving ECU according to the first embodiment. [Figure 4]Figure 4 is a graph showing the time-series variation of the area change amount and the vehicle speed in the second embodiment. [Figure 5] Figure 5 is a flowchart showing processing by the automated driving ECU of the second embodiment. [Figure 6] Figure 6 is an explanatory diagram of the prior art. [Figure 7] Figure 7 is an explanatory diagram of the prior art. [Modes for Carrying Out the Invention]

[0020] Hereinafter, embodiments of the driving assistance device and the like of the present invention will be described with reference to the accompanying drawings.

[0021] (First Embodiment) Figure 1 is a block diagram showing a schematic configuration of a vehicle equipped with the driving assistance device of the first embodiment.

[0022] Vehicle 1 (host vehicle) is an automated driving vehicle. The vehicle 1 is equipped with a plurality of ECUs (Electronic Control Units) to control each unit. Each ECU includes a microcomputer (microcontroller unit), and the microcomputer incorporates, for example, a CPU, a non-volatile memory such as a flash memory, and a volatile memory such as a DRAM (Dynamic Random Access Memory).

[0023] The plurality of ECUs include a drive ECU 11, a steering ECU 12, a brake ECU 13, a meter ECU 14, and a body ECU 15. They are connected so as to be capable of communication according to the CAN (Controller Area Network) communication protocol.

[0024] The drive ECU 11 is a control unit that controls the drive unit 21. The drive unit 21 may be configured to have an engine as a drive source, or a motor as a drive source, or both an engine and a motor as drive sources. The drive unit 21 may include a transmission that changes the speed of the driving force from the drive source and outputs it, if necessary.

[0025] The steering ECU 12 is a control unit that controls the steering device 22. The steering device 22 is, for example, an electric power steering device that applies torque from an electric motor to the steering mechanism. The steering mechanism includes, for example, a rack and pinion type steering gear, and is configured such that when the rack axis moves in the vehicle width direction due to the torque of the electric motor, the left and right steering wheels steer to the left and right in accordance with the movement of the rack axis.

[0026] The brake ECU 13 is a control unit that controls the braking system 23. The braking system 23 may be hydraulic or electric. For example, if the braking system 23 is hydraulic, it is equipped with a brake actuator, and the function of this brake actuator is to distribute hydraulic pressure to the wheel cylinders of the brakes provided on each wheel, and this hydraulic pressure is used to apply braking force from each brake to the wheels, including the drive wheels.

[0027] The meter ECU 14 is a control unit that controls various parts of the meter panel (not shown). The meter panel is equipped with instruments that display vehicle speed and engine speed, as well as displays such as liquid crystal displays for displaying various information. The meter ECU 14 is also connected to an emergency stop switch 24 that is operated to instruct an emergency stop in automatic driving mode.

[0028] The body ECU 15 is a control unit that controls various parts that need to operate even when the ignition switch of vehicle 1 is off, such as the left and right turn signals and door lock motors.

[0029] Furthermore, the multiple ECUs include an autonomous driving ECU 31 (driving assistance device), a lidar ECU 32, and a monocular camera ECU 33, which serve as control units for the autonomous driving function.

[0030] The autonomous driving ECU31 is the control center for autonomous driving control. The autonomous driving ECU31 is connected to each of the ECUs 11 to 15 via CAN communication.

[0031] The autonomous driving ECU 31 is connected to a LiDAR (Light Detection and Ranging) 34, for example, via an Ethernet® standard communication cable. The LiDAR 34 emits laser light in all 360 degrees, receives reflected light from objects within its search range with an optical sensor, and outputs a detection signal corresponding to that reflected light. The detection signal from the LiDAR 34 is input to the autonomous driving ECU 31.

[0032] Furthermore, a GPS receiver 35 is connected to the autonomous driving ECU 31, for example, via a USB (Universal Serial Bus) communication cable. The GPS receiver 35 is a receiver that receives positioning signals from GPS (Global Positioning System) satellites. The positioning signals received by the GPS receiver 35 are input from the GPS receiver 35 to the autonomous driving ECU 31.

[0033] The Rider ECU 32 is connected to the Autonomous Driving ECU 31 via, for example, an Ethernet communication cable. Six Riders 36 are connected to the Rider ECU 32. Each Rider 36 emits laser light into a search area, receives reflected light from objects within that search area using an optical sensor, and outputs a detection signal corresponding to that reflected light. The Riders 36 are positioned, for example, at the left, center, and right ends of the front bumper and the left, center, and right ends of the rear bumper of the vehicle 1. The detection signals output from each Rider 36 are input to the Rider ECU 32. The Rider ECU 32 processes the detection signals output from each Rider 36 and transmits the data obtained from this processing to the Autonomous Driving ECU 31.

[0034] The monocular camera ECU 33 is connected to the autonomous driving ECU 31 via, for example, a USB standard communication cable. A monocular camera 37 is connected to the monocular camera ECU 33. The monocular camera 37 is a camera capable of continuously capturing still images of the search range in front of the vehicle 1 at a predetermined frame rate. The monocular camera ECU 33 receives the image signals of the still images continuously output from the monocular camera 37. The monocular camera ECU 33 processes the image signals input from the monocular camera 37 and transmits the resulting image data to the autonomous driving ECU 31.

[0035] The following explanation will also refer to Figure 2. Figure 2 is a functional configuration diagram of the autonomous driving ECU 31 of the first embodiment. The autonomous driving ECU 31 has the following functional configuration: acquisition unit 311, object recognition unit 312, region generation unit 313 (generation unit), calculation unit 314, path generation unit 315, setting unit 316, and control unit 317. These functional configurations are implemented either in software through program processing or in hardware such as logic circuits.

[0036] The autonomous driving ECU 31 also includes a self-position estimation unit that estimates the position (self-position) of the vehicle 1 based on information from the omnidirectional lidar 34 and GPS receiver 35, but a detailed explanation of these will be omitted. Furthermore, in the following explanation, parked vehicles will be used as the main example of a target.

[0037] The acquisition unit 311 acquires various information from various components. For example, the acquisition unit 311 acquires information about targets in at least the direction of travel of the vehicle 1 from the rider ECU 32, monocular camera ECU 33, omnidirectional rider 34, etc.

[0038] The object recognition unit 312 recognizes other vehicles, pedestrians, and other objects (objects) from information about the distance to objects (vehicles, pedestrians, buildings, curbs, and other targets (obstacles)) obtained from the detection signals of the omnidirectional LiDAR 34, as well as from images captured by the monocular camera 37.

[0039] The region generation unit 313 generates a region corresponding to the object recognized by the object recognition unit 312. For example, the region generation unit 313 generates a rectangular region A corresponding to the roadside parking space C2 shown in Figure 6.

[0040] The calculation unit 314 calculates the size of the region generated by the region generation unit 313. For example, the calculation unit 314 calculates the area of ​​the rectangular region A shown in Figure 6. The calculation period is, for example, several tens to several hundred milliseconds. Note that the "size of the region" to be calculated is not limited to area, but may also be volume, etc.

[0041] The route generation unit 315 generates a route from the current location of vehicle 1 to the destination based on various information such as map data and the location of vehicle 1.

[0042] The setting unit 316 sets the vehicle speed of vehicle 1 according to the amount of change over time in the size of the region calculated by the calculation unit 314. For example, the setting unit 316 sets the vehicle speed of its own vehicle to be lower the larger the amount of change in the size of the region. A specific example will be described below.

[0043] Assume that the area calculated by the calculation unit 314 is accumulated in a time series. In that case, the setting unit 316 calculates, for example, the variance of the area over the most recent 10 seconds (the sum of the squares of the "difference from the mean" divided by the number of data points) (var), and determines the vehicle speed (vel) using the following formula (1). vel= max(ConstVel*(ConstVar-var),0)...Equation (1)

[0044] Here, ConstVel and ConstVar are fixed values ​​set in advance. Also, max(a,b) is a function that takes the maximum value of a and b.

[0045] According to equation (1), when the variance (var) is large (i.e., the area of ​​the rectangle is unstable over time), the vehicle speed (vel) decreases. Conversely, when the variance (var) is small (i.e., the area of ​​the rectangle is stable over time), the vehicle speed (vel) increases.

[0046] Furthermore, if the rectangular area becomes too unstable over time, it is easy to implement behaviors such as setting the vehicle speed (vel) to 0 (vehicle stopping).

[0047] The control unit 317 controls the movement of the vehicle 1 by controlling the drive ECU 11, steering ECU 12, brake ECU 13, etc., based on the route generated by the route generation unit 315 and the vehicle speed set by the setting unit 316.

[0048] Figure 3 is a flowchart showing the processing performed by the autonomous driving ECU 31 of the first embodiment. Here, explanations of matters not directly related to the present invention (such as self-position estimation) are omitted as appropriate.

[0049] In step S1, the acquisition unit 311 acquires information on parked vehicles in at least the direction of travel of vehicle 1 from the rider ECU 32, monocular camera ECU 33, omnidirectional rider 34, etc.

[0050] Next, in step S2, the region generation unit 313 generates a region (rectangle) corresponding to the parked vehicle acquired in step S1.

[0051] Next, in step S3, the calculation unit 314 calculates the size of the region generated in step S2 (for example, the rectangular area). The calculated information (rectangular area) is stored in the memory unit of the autonomous driving ECU 31.

[0052] Next, in step S4, the setting unit 316 calculates the area variance from the area information for the past N seconds (for example, the most recent 10 seconds).

[0053] Next, in step S5, the setting unit 316 calculates (sets) the instructed vehicle speed based on, for example, the above-described formula (1).

[0054] Next, in step S6, the control unit 317 controls the vehicle 1 to follow the instructed vehicle speed calculated in step S5.

[0055] Thus, according to the first embodiment, by changing the vehicle speed in accordance with the amount of change in the size of its own domain, the behavior of the autonomous vehicle that detects and avoids targets can be stabilized.

[0056] Furthermore, the lower the vehicle's speed, the higher the detection accuracy of the area corresponding to the target. Therefore, by setting the vehicle's speed lower when the change in the size of the area is large, detection accuracy can be improved and vehicle behavior can be stabilized. More specifically, this is as follows:

[0057] The reason why reducing the vehicle's speed improves the detection accuracy of the area corresponding to the target is, for example, as follows: • Reduced vibration of vehicle 1. - The deflection of the vehicle body is reduced, improving the accuracy of the integrated detection results from multiple sensors mounted on vehicle 1. • The time-series change in the relative positional relationship between vehicle 1 and the parked vehicle becomes smaller.

[0058] Furthermore, if area detection is unstable, reducing the vehicle speed results in safer vehicle behavior for the entire system, which is desirable.

[0059] Furthermore, recent research suggests that parked vehicles are the most frequent cause of manual intervention in autonomous driving. Therefore, the successful automatic avoidance of parked vehicles is of great importance for the practical application of autonomous driving. In other words, with the method of this embodiment, even when area detection is unstable, it may be possible to restore detection stability by sufficiently reducing the vehicle speed, thereby reducing the rate of manual intervention.

[0060] (Second Embodiment) Next, a second embodiment will be described. Explanations of matters similar to those in the first embodiment will be omitted as appropriate. The difference from the first embodiment is that the vehicle speed is changed using a threshold value for the change in area, rather than using the above-mentioned equation (1).

[0061] Figure 4 shows, in the second embodiment, (a) is a graph showing the time-series change in the amount of change in area, and (b) is a graph showing the time-series change in vehicle speed. As shown in (a), when the amount of change in area (size of the region) exceeds the first threshold at time t1, the setting unit 316 sets the vehicle speed of its own vehicle to a lower value than before, as shown in (b). In other words, the set value of the vehicle speed is changed from vehicle speed V1 to vehicle speed V2.

[0062] Furthermore, after setting the vehicle speed of the own vehicle to a low value, if the amount of change in area falls below the second threshold at time t2 as shown in (a), the setting unit 316 sets the vehicle speed of the own vehicle to a higher value than before. In other words, the set value of the vehicle speed is changed from vehicle speed V2 to vehicle speed V1.

[0063] Note that in Figure 4, for the sake of simplicity in illustration and explanation, the vehicle speed is assumed to be constant except when the vehicle speed is changed. However, this is not the only option, and the vehicle speed does not have to be constant.

[0064] Figure 5 is a flowchart showing the processing performed by the autonomous driving ECU 31 of the first embodiment. Steps S1 to S3 are the same as steps S1 to S3 in Figure 3. Note that, in order to simplify the explanation, the flowchart in Figure 5 omits descriptions such as setting the instructed vehicle speed according to the surrounding environment, as in the conventional technology, and controlling vehicle 1 to follow that instructed vehicle speed.

[0065] After step S3, in step S4, the setting unit 316 determines whether the amount of change in area exceeds the first threshold. If yes (time t1 in Figure 4), proceed to step S12; otherwise, return to step S1.

[0066] In step S12, the setting unit 316 sets the instructed vehicle speed of its own vehicle to a small value.

[0067] Next, in step S13, the setting unit 316 determines whether the change in area has fallen below the second threshold. If the answer is yes (time t2 in Figure 4), the process proceeds to step S14; otherwise, it returns to step S13.

[0068] In step S14, the setting unit 316 sets the instructed vehicle speed of its own vehicle to a large value.

[0069] Thus, according to the second embodiment, the detection accuracy of the area corresponding to the target improves as the vehicle speed decreases. Therefore, if the amount of change in the size of the area exceeds the first threshold, the detection accuracy can be improved and the vehicle behavior can be stabilized by setting the vehicle speed to a lower value.

[0070] Furthermore, if the change in the size of the region subsequently falls below the second threshold, it can be assumed that the region detection accuracy has improved. Therefore, by setting a higher vehicle speed, it is possible to stabilize the vehicle's behavior while avoiding situations where the vehicle remains in a low-speed state for longer than necessary.

[0071] In Figure 4, the first and second thresholds are set to different values, thereby preventing frequent changes in vehicle speed. However, this is not the only option; the first and second thresholds may also be set to the same value.

[0072] While several embodiments of the present invention have been described, these embodiments are presented as examples only and are not intended to limit the scope of the invention. These novel embodiments can be carried out in a variety of other forms, and various omissions, substitutions, and modifications can be made without departing from the spirit of the invention. These embodiments and their variations are included in the scope and spirit of the invention, as well as in the claims of the invention and its equivalents.

[0073] Furthermore, the program executed by the automated driving ECU 31 of this embodiment can be provided as an installable or executable file recorded on a recording medium readable by a computer device, such as a CD (Compact Disc)-ROM (Read Only Memory), a flexible disk (FD), a CD-R (Recordable), or a DVD (Digital Versatile Disk). Alternatively, the program may be provided or distributed via a network such as the Internet.

[0074] Furthermore, the targets are not limited to other vehicles such as parked cars, but include all moving objects such as bicycles, motorcycles, pedestrians, and animals (dogs, cats, etc.).

[0075] Furthermore, while area variance was used in the first embodiment, the invention is not limited to this, and other indicators such as the standard deviation of area may be used as long as they correlate with the detection accuracy of the region. [Explanation of Symbols]

[0076] 1...Vehicle, 11...Drive ECU, 12...Steering ECU, 13...Brake ECU, 21...Drive System, 31...Automatic Driving ECU, 32...Lider ECU, 33...Monocular Camera ECU, 34...Omnidirectional Lider, 311...Acquisition Unit, 312...Object Recognition Unit, 313...Region Generation Unit, 314...Calculation Unit, 315...Path Generation Unit, 316...Setting Unit, 317...Control Unit

Claims

1. An acquisition unit that acquires information on targets at least in the direction of travel of the vehicle, A generation unit that generates a region corresponding to the aforementioned target, A calculation unit for calculating the size of the aforementioned region, A setting unit sets the vehicle speed of the vehicle in accordance with an index indicating the instability of the change in the size of the region based on time-series data of the size of the region, A driving assistance device comprising: a control unit that controls the driving of the vehicle based on the vehicle speed set by the setting unit;

2. The driving assistance device according to claim 1, wherein the setting unit sets the vehicle speed of the vehicle to a smaller value the larger the index indicating the instability of the amount of change in the size of the region is.

3. The driving assistance device according to claim 1, wherein the setting unit sets the vehicle speed of the vehicle to a smaller value when an index indicating the instability of the amount of change in the size of the area exceeds a first threshold.

4. The driving assistance device according to claim 3, wherein the setting unit sets the vehicle speed of the vehicle to a small value, and then, when the amount of change in the index indicating the instability of the size of the region falls below a second threshold, sets the vehicle speed of the vehicle to a large value.

Images