Walking estimation device

Abstract

A travel path estimation device (10) is provided with: an external condition detection unit (2) that is mounted on a vehicle (1) and detects external conditions around the vehicle (1); a travel state detection unit (3) that detects the travel state of the vehicle (1); and a controller (5). The controller (5): stores map information; estimates the travel path along which the vehicle (1) should travel, at prescribed intervals on the basis of the external conditions detected by the external condition detection unit (2); identifies a trajectory actually traveled by the vehicle (1), on the basis of the travel state detected by the travel state detection unit (3); determines whether or not the estimated travel path coincides with the identified trajectory; and associates and stores the determination result with the map information.

Description

[Technical Field]

[0001] The present invention relates to a route estimation device that estimates a route on which a vehicle having an automatic driving function or a driving assistance function should travel. [Background technology]

[0002] Conventionally, there is known a device for automatically driving a vehicle (see, for example, Patent Document 1). The device described in Patent Document 1 compares three-dimensional point cloud data acquired during driving with a pre-established three-dimensional point cloud map that includes information on roads and the like, and acquires three-dimensional point cloud data of static objects such as roads from the three-dimensional image data generated by fusing two-dimensional image data acquired during driving with the three-dimensional point cloud data.

[0003] The widespread adoption of vehicles with autonomous driving and driving assistance functions will improve the safety and convenience of the entire transportation society, leading to the realization of a sustainable transportation system. Furthermore, the improvement of transportation efficiency and smoothness will reduce CO2 emissions and lessen the burden on the environment. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Publication No. 2020-85886 Summary of the Invention [Problem to be solved by the invention]

[0005] It is desirable to be able to continue automatic driving and driving assistance for a vehicle even in areas where there is no pre-established map information, but when using pre-established map information as in the device described in Patent Document 1 above, it is difficult to continue automatic driving and driving assistance in such areas. [Means for solving the problem]

[0006] The roadway estimation device according to one aspect of the present invention includes an external environment detection unit that detects an external environment around the vehicle, a driving state detection unit that detects a driving state of the vehicle, and A storage unit in which map information is stored in advance is included. and a controller. , outside estimating a route along which the vehicle should travel at a predetermined interval based on the external environment detected by the external environment detection unit; The route information is added to the map information in association with the vehicle position information at the time when the route is estimated; The vehicle's actual travel path is identified based on the travel state detected by the travel state detection unit. , run road The track Determine whether it matches the trace, If it is determined that there is no match The judgment result In situations where route estimation is difficult, the route information is associated with the vehicle's position information at the time of estimation. Map information Based on the result of the judgment, it is decided whether or not to allow the generation of a road map based on the road. do. [Effects of the Invention]

[0007] According to the present invention, it is possible to improve the continuity of automatic vehicle driving and driving assistance even in areas where there is no pre-established map information. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a block diagram schematically showing the configuration of a roadway estimation device according to an embodiment of the present invention; [Figure 2A] FIG. 10 is a diagram showing an example of a running path when an estimated running path and an actual trajectory match. [Figure 2B] FIG. 10 is a diagram showing an example of a trajectory when an estimated path and an actual trajectory coincide with each other. [Figure 3A] FIG. 10 is a diagram showing an example of a running path when the estimated running path and the actual trajectory do not match. [Figure 3B] FIG. 10 is a diagram showing an example of a trajectory when the estimated path does not match the actual trajectory. [Figure 4] FIG. 10 is a diagram showing an example of a determination result stored in association with map information. [Figure 5] FIG. 10 is a diagram for explaining whether autonomous driving or driving assistance is possible based on the determination result. [Figure 6A] FIG. 10 is a diagram for explaining the exclusion of a lane estimated at a specific time. [Figure 6B]FIG. 10 is a diagram for explaining generation of a road map. [Figure 7] FIG. 10 is a diagram for explaining calculation of reliability based on a determination result. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, an embodiment of the present invention will be described with reference to Figs. 1 to 7. A route estimation device according to an embodiment of the present invention is applied to a vehicle having a driving assistance function that provides driving assistance to the driver of the vehicle or controls driving actuators so that the vehicle is driven automatically, and estimates the route along which the vehicle should travel. "Driving assistance" in this embodiment includes driving assistance that assists the driver in driving operations and autonomous driving that drives the vehicle automatically without the driver's driving operations, and corresponds to autonomous driving levels 1 to 4 defined by the SAE, and "autonomous driving" corresponds to autonomous driving level 5.

[0010] Among the various types of autonomous driving and driving assistance, steering assistance, which assists with steering, is highly effective in reducing the burden on the driver, and therefore there is a need for continued assistance not only on expressways where lane markings are in place, but also at intersections on ordinary roads where lane markings are not in place. However, while high-precision maps used for autonomous driving and driving assistance have been created for areas with high traffic volume, such as expressways and urban areas, they have not been created for areas with low traffic volume, such as residential areas and suburbs. In addition, road structures may change due to construction work or other reasons after the latest high-precision maps have been created.

[0011] Therefore, in order to improve the continuity of automated driving and driving assistance even in areas where no pre-established high-precision maps have been created, it is necessary for each vehicle to independently estimate the route it should travel on while traveling using an on-board sensor, etc. In this embodiment, the route estimation device is configured as follows so that the continuity of automated driving and driving assistance can be improved even in areas where no pre-established map information has been created by estimating the route the vehicle should travel on using an on-board sensor, etc.

[0012] Fig. 1 is a block diagram showing a schematic configuration of a roadway estimation device 10 according to an embodiment of the present invention. As shown in Fig. 1, the roadway estimation device 10 includes an external situation detection unit 2, a driving state detection unit 3, a driving actuator 4, and a controller 5, which are mounted on a vehicle 1. The external situation detection unit 2, the driving state detection unit 3, and the driving actuator 4 are connected to the controller 5.

[0013] The external situation detection unit 2 is mounted on the vehicle 1 and detects the external situation around the vehicle 1, particularly the situation ahead. The external situation detection unit 2 is configured by a camera having an imaging element such as a CCD or CMOS and capturing an image of the area around the vehicle 1. The external situation detection unit 2 may be configured by a millimeter wave radar that irradiates millimeter waves (radio waves) and measures the distance and direction to an object from the time it takes for the irradiated waves to hit the object and return. The external situation detection unit 2 may be configured by a lidar (LiDAR) that irradiates laser light and measures the distance and direction to an object from the time it takes for the irradiated light to hit the object and return.

[0014] Based on the external situation detected by the external situation detection unit 2, it is possible to recognize the road surface on which the vehicle can travel, the travel lanes defined by dividing lines and structures, and obstacles on the road including traffic participants such as surrounding vehicles and pedestrians, and to estimate the travel path EL on which the vehicle 1 should travel. More specifically, it is possible to estimate the travel path EL(t) from the current position P(t) of the vehicle 1 at a predetermined time t to at least a predetermined distance ahead that can be detected by the external situation detection unit 2.

[0015] The driving condition detection unit 3 detects driving conditions such as the driving speed and traveling direction of the vehicle 1. The driving condition detection unit 3 is configured, for example, by an inertial measurement unit (IMU) that detects rotational angular velocities around three axes, namely, the vertical direction of the center of gravity of the vehicle 1, the traveling direction, and the vehicle width direction, and accelerations in three axial directions. The driving condition detection unit 3 may also be configured by wheel speed sensors that detect the rotational speeds of each wheel of the vehicle 1. The driving condition detection unit 3 may also include a positioning unit that measures the current position (latitude, longitude) of the vehicle 1 based on positioning signals from positioning satellites.

[0016] Based on the traveling state detected by the traveling state detection unit 3, the amount of movement of the vehicle 1 for each predetermined time period can be calculated, and the trajectory AL traveled by the vehicle 1 can be identified. For example, the actual trajectory AL(t) traveled by the vehicle 1 from the predetermined time point t at which the traveling path EL of the vehicle 1 is estimated to the present time can be identified. The actual trajectory AL traveled by the vehicle 1 may be identified by connecting the vehicle positions for each predetermined time period.

[0017] The traveling actuator 4 includes a steering mechanism such as a steering gear that steers the vehicle 1, a drive mechanism such as an engine or motor that drives the vehicle 1, and a braking mechanism such as a brake that brakes the vehicle 1.

[0018] The controller 5 includes a computer having a processing unit 6 such as a CPU, a storage unit 7 such as RAM and ROM, an I / O interface, and other peripheral circuits. The controller 5 is configured as part of a group of multiple electronic control units (ECUs) that are mounted on the vehicle 1 and control the operation of the vehicle 1, for example. The storage unit 7 of the controller 5 stores in advance general map information used by the navigation device for route guidance from the current location of the vehicle 1 to the destination. The storage unit 7 also stores high-precision maps for autonomous driving.

[0019] Figures 2A and 2B are diagrams showing an example of a case where the estimated path EL(t) at a given time t matches the actual trajectory AL(t), and Figures 3A and 3B are diagrams showing an example of a case where the path EL(t) does not match the trajectory AL(t).

[0020] 2A and 3A, the processing unit 6 of the controller 5 estimates the route EL along which the vehicle 1 should travel, based on the external situation detected by the external situation detection unit 2. More specifically, the processing unit 6 estimates the route EL(t) from the current position P(t) of the vehicle 1 at a predetermined time t to a predetermined distance ahead. The estimation of the route EL is performed at predetermined intervals (for example, the detection interval of the external situation detection unit 2, the control interval of the controller 5, the communication interval between the external situation detection unit 2 and the controller 5, etc.).

[0021] The information on the estimated path EL(t) is associated with map information and stored in the storage unit 7. More specifically, the information is added to the map information in association with position information on the current position P(t) of the vehicle 1 at the time t when the path EL(t) is estimated.

[0022] 2B and 3B, the processing unit 6 of the controller 5 identifies the actual trajectory AL when the vehicle 1 traveled with the driver's involvement, based on the traveling state detected by the traveling state detection unit 3, and determines whether the identified trajectory AL matches the estimated traveling path EL. More specifically, the processing unit 6 identifies the actual trajectory AL(t) when the vehicle 1 traveled with the driver's involvement over a section from the current position P(t) of the vehicle 1 at the time t when the traveling path EL(t) was estimated to a predetermined distance ahead, and determines whether the actual trajectory AL(t) falls within the range of the estimated traveling path EL(t).

[0023] Note that driving involving the driver includes driving in which the driver drives manually without receiving driving assistance, and driving in which the driver drives manually with receiving driving assistance.

[0024] As shown in Figure 2B, when the actual trajectory AL(t) of the vehicle 1 driven by the driver is within the range of the estimated path EL(t), it is determined that the estimated path EL(t) matches the identified path AL(t), or that the path estimation was appropriate.

[0025] On the other hand, as shown in Fig. 3B, when the actual trajectory AL(t) when the vehicle 1 traveled with the driver's involvement does not fall within the range of the estimated path EL(t), it is determined that the estimated path EL(t) does not match the specified trajectory AL(t). In this way, when the estimated path EL and the trajectory AL when the vehicle 1 actually traveled with the driver's involvement do not match, it is highly likely that the path estimation was inappropriate, and the scene is treated as a difficult scene for the external situation detection unit 2 to estimate the path.

[0026] Such a determination result is associated with map information together with information on the estimated traveling path EL(t) and stored in the storage unit 7. More specifically, the determination result is associated with position information on the current position P(t) of the vehicle 1 at the time t when the traveling path EL(t) is estimated, and is added to the map information together with the information on the estimated traveling path EL(t).

[0027] If the estimated path EL does not match the trajectory AL when the driver is actually driving, the detection result by the external situation detection unit 2 at or around the time t when such a path EL(t) is estimated may be transmitted to an external analysis device, etc. In this case, data on only scenes that are difficult for the external situation detection unit 2 to estimate the path can be efficiently collected from a large number of vehicles 1, and factors that make the path estimation inappropriate can be analyzed.

[0028] Fig. 4 is a diagram showing an example of the determination result stored in association with map information. As shown in Fig. 4, the map information stored in the storage unit 7 of the controller 5 is added with information on the determination result as to whether or not the scene is difficult for the external situation detection unit 2 to estimate the route, corresponding to the vehicle position at each predetermined period in an area where the vehicle 1 has actually traveled with the driver's involvement.

[0029] Figure 5 is a diagram for explaining whether autonomous driving or driving assistance is possible based on the judgment results, and shows a situation in which vehicle 1 is using autonomous driving or driving assistance in an area in which vehicle 1 has previously driven with the driver involved.

[0030] 5, the processing unit 6 of the controller 5 estimates the roadway EL based on the external conditions detected by the external condition detection unit 2, and determines whether to continue or suspend the currently used autonomous driving or driving assistance based on past determination results on the road of the vehicle 1. In other words, it determines whether to permit control of the driving actuator 4 based on the roadway EL estimated based on the external conditions detected by the external condition detection unit 2 at each point on the road.

[0031] More specifically, the system estimates the road EL in the past within a predetermined section on the route of vehicle 1 (for example, a section up to about 300 m ahead from the current position of vehicle 1) and determines whether there is a point that has been determined to be a difficult scene. If there is a point within the predetermined section that has been determined to be a difficult scene, the system notifies the driver and suspends the currently used automated driving or driving assistance. Suspension of the currently used automated driving or driving assistance also includes downgrading from automated driving to driving assistance or downgrading the level of driving assistance.

[0032] For example, if steering assistance is performed based on an inappropriate path EL, an auxiliary steering torque in an inappropriate direction is applied to the steering wheel held by the driver, which requires the driver to correct the torque, thereby placing a burden on the driver. When a point where an inappropriate path EL is likely to be estimated is approached, the driver is notified before the point and automated driving or driving assistance is suspended, thereby preventing unnecessary burden on the driver. Note that the length of the predetermined section used to determine whether automated driving or driving assistance is possible may be changed depending on the shape of the road along the route, the speed limit, etc.

[0033] Because the detection of external conditions by the external condition detection unit 2 has limitations due to factors such as the surrounding environment, it is difficult to always estimate an appropriate roadway EL at some locations. By registering such locations as difficult scenes, roadway estimation by the external condition detection unit 2 can be actively used in situations other than difficult scenes. For example, when recognizing roadway EL based on the detection results by the external condition detection unit 2 using a DNN (Deep Neural Network), if a strict threshold is set that only recognizes roadway EL, roadway EL cannot be recognized at some locations, making roadway estimation unusable. By setting a lenient threshold that allows recognition of things other than roadway EL at some locations and registering locations where inappropriate roadway recognition is likely to occur as difficult scenes, the availability of roadway estimation can be improved for the entire device.

[0034] Fig. 6A is a diagram for explaining the exclusion of the lane EL estimated at specific times t1 to t4, and Fig. 6B is a diagram for explaining the generation of the lane map MAP. As shown in Fig. 6A and Fig. 6B, the processing unit 6 of the controller 5 determines whether or not to permit the generation of the lane map MAP based on the estimated lane EL, based on the determination result stored in the storage unit 7 in association with the map information.

[0035] More specifically, the system determines whether each location where the vehicle 1 has traveled in the past is a difficult scene with the driver's involvement, and allows the use of estimated routes EL at locations other than difficult scenes in generating the route map MAP, while prohibits the use of routes EL estimated at difficult scenes. In the example of Figures 6A and 6B, the route EL(t3) estimated at time t3 at a location determined to be a difficult scene is excluded, and the route map MAP is generated based on the routes EL(t1), EL(t2), and EL(t4) estimated at other locations at times t1, t2, and t4. The generated route map MAP is stored in the memory unit 7 in association with map information.

[0036] During autonomous driving of the vehicle 1, the consistency between the shape of the latest road EL estimated at any time while the vehicle is traveling and the shape of the road EL stored as a road map MAP (or high-precision map) in the memory unit 7 is confirmed. After confirming the consistency between the shape of the latest road EL and the shape of the road EL on the road map MAP (or high-precision map), the processing unit 6 of the controller 5 controls the driving actuator 4 so that the vehicle 1 travels within the estimated road EL.

[0037] 7 is a diagram for explaining the calculation of reliability based on the determination result, and shows an example of reliability calculated after traveling the same location multiple times (four times in FIG. 7). As shown in FIG. 7, the processing unit 6 of the controller 5 calculates the reliability of the estimated path EL based on the determination result stored in association with the map information, and stores the calculated reliability in association with the map information.

[0038] The reliability can be calculated as the ratio of the number of times the appropriate road EL was estimated to the number of times the vehicle traveled in the past. In the example of Figure 7, the reliability of a point where the appropriate road EL was estimated four times out of the past four times is calculated as 100%, the reliability of a point where the appropriate road EL was estimated three times is calculated as 75%, and the reliability of a point where the appropriate road EL was never estimated is calculated as 0%.

[0039] In particular, when autonomous driving is performed, highly reliable route estimation is necessary. By calculating the reliability of route estimation based on the track record of multiple drives performed without autonomous driving and with the driver's involvement, and using the route estimation results only when the reliability exceeds an appropriate threshold, appropriate autonomous driving based on highly reliable route estimation can be performed.

[0040] Furthermore, even if a scene has been judged to be difficult in the past for some reason, if the number of times that path estimation is judged to be appropriate over multiple drives increases, it can be used as an estimated path EL for a highly reliable driving scene. This reduces gaps (interruptions) in the area where path estimation can be used, improving the continuity of autonomous driving and driver assistance.

[0041] According to this embodiment, the following effects can be achieved. (1) The path estimation device 10 is mounted on the vehicle 1 and includes an external situation detection unit 2 that detects the external situation around the vehicle 1, a driving state detection unit 3 that detects the driving state of the vehicle 1, and a controller 5 (Fig. 1). The controller 5 stores map information, estimates a path EL along which the vehicle 1 should travel at a predetermined interval based on the external situation detected by the external situation detection unit 2, identifies a trajectory AL along which the vehicle 1 actually traveled based on the driving state detected by the driving state detection unit 3, determines whether the estimated path EL matches the identified trajectory AL, and stores the determination result in association with the map information (Fig. 4).

[0042] That is, if the estimated driving path EL does not match the trajectory AL when the driver is actually driving, the scene is registered as a difficult scene where it is highly likely that the driving path estimation by the external situation detection unit 2 was inappropriate. This makes it possible to actively use the estimated driving path EL in scenes other than difficult scenes, thereby improving the continuity of automatic driving and driving assistance of the vehicle 1 even in areas without pre-established map information.

[0043] (2) The path estimation device 10 further includes a driving actuator 4 mounted on the vehicle 1 (FIG. 1). The controller 5 determines whether to permit control of the driving actuator 4 based on the estimated path EL on the path of the vehicle 1, based on the determination result stored in association with the map information (FIG. 5). In other words, the estimated path EL in areas other than difficult scenes can be actively used for automated driving and driving assistance, thereby improving continuity. Furthermore, if there is a difficult scene on the path, the driver is notified in advance and automated driving and driving assistance are suspended, thereby avoiding the occurrence of inappropriate steering assistance and the burden on the driver associated with correcting it.

[0044] (3) The controller 5 determines whether to permit the generation of a route map MAP based on the estimated route EL based on the determination result stored in association with the map information (FIGS. 6A and 6B). In other words, by excluding the route EL estimated in the difficult scene, an accurate route map MAP can be generated. Furthermore, by being able to actively use the route EL estimated in scenes other than the difficult scene in the generation of the route map MAP, the continuity of automated driving and driving assistance can be improved.

[0045] (4) The controller 5 calculates the reliability of the estimated roadway EL based on the determination results stored in association with the map information, and stores the calculated reliability in association with the map information (FIG. 7). That is, the reliability of the roadway estimation for a driving scene is calculated based on multiple determination results when the same driving scene is driven. This makes it possible to use only the roadway EL estimated in a highly reliable driving scene, for example, where the roadway estimation has been determined to be appropriate many times. Furthermore, even if a scene is determined to be difficult due to special circumstances, if the roadway estimation has been determined to be appropriate many times, the estimated roadway EL can be used as the roadway EL estimated in a highly reliable driving scene, thereby further improving the continuity of automated driving and driving assistance.

[0046] The above description is merely an example, and the present invention is not limited to the above-described embodiment and modifications as long as the features of the present invention are not impaired. One or more of the above-described embodiment and modifications can be arbitrarily combined, and modifications can also be combined with each other. [Explanation of symbols]

[0047] 1 vehicle, 2 external situation detection unit, 3 driving state detection unit, 4 driving actuator, 5 controller, 6 processing unit, 7 memory unit, 10 driving path estimation device, AL trajectory, EL driving path, P current position

Claims

1. an external environment detection unit mounted on a vehicle and configured to detect an external environment around the vehicle; a running state detection unit that detects a running state of the vehicle; a controller having a storage unit in which map information is stored in advance, The controller estimating a route along which the vehicle should travel at a predetermined interval based on the external environment detected by the external environment detection unit; adding the information about the route to the map information in association with the position information of the vehicle at the time when the route was estimated; Identifying a path that the vehicle has actually traveled based on the traveling state detected by the traveling state detection unit; determining whether the path matches the trajectory; If it is determined that there is no match, the determination result is associated with the vehicle position information at the time of estimation as a scene that is difficult for road estimation, and is added to the map information together with the road information; A road estimation device that determines whether or not to permit generation of a road map based on the road based on the determination result.

2. The travel path estimation device according to claim 1, The vehicle further includes a traveling actuator mounted on the vehicle, The controller determines whether or not to permit control of the driving actuator based on the route on the route of the vehicle, based on the determination result.

3. In the path estimation device according to claim 1 or 2, The controller Calculating the reliability of the road based on the determination result; The travel path estimation device is characterized in that the reliability is associated with position information of the vehicle at the time of estimation and added to the map information.

Images