Information processing device

Abstract

To provide an information processor capable of performing processing based on location information of a target object, even when the target object cannot be detected by a camera.SOLUTION: An information processor according to an embodiment of the present disclosure includes a determination unit, a calculation unit, and an estimation unit. The determination unit determines whether or not map information includes an object corresponding to a first target object based on vehicle position information obtained through communication with the outside and first distance information to the first target object obtained from a distance image generated based on a stereo image. When the map information is determined to include an object corresponding to the first target object, the calculating unit calculates second distance information between the first target object and a second target object having a predetermined relation to the first target object based on the map information. The estimation unit estimates location information of the second target object based on the first distance information and the second distance information.SELECTED DRAWING: Figure 3

Description

Technical Field

[0001] The present disclosure relates to an information processing device mounted on a vehicle.

Background Art

[0002] A method of imaging the front of a vehicle using a camera and detecting a target based on the image obtained thereby is known (see, for example, Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Patent Document 3

Summary of the Invention

Problems to be Solved by the Invention

[0004] For example, when the target is an object drawn on the road surface (e.g., a stop line), the target may become difficult to see due to aging, be hidden behind an object, or be covered with snow or the like. In that case, it is difficult to detect the target with a camera. Therefore, there has been a problem that when the target cannot be detected by the camera, processing based on the position information of the target cannot be performed. Therefore, it is desirable to provide an information processing device capable of performing processing based on the position information of the target even when the target cannot be detected by the camera.

Means for Solving the Problems

[0005] An information processing device according to one embodiment of the present disclosure comprises a detection unit, a determination unit, a calculation unit, and an estimation unit. The detection unit detects first distance information to a first target object based on a distance image generated based on a stereo image. The determination unit determines whether or not an object corresponding to the first target object is included in the map information based on vehicle position information obtained through communication with an external source and the first distance information detected by the detection unit. If the determination unit determines that an object corresponding to the first target object is included in the map information, the calculation unit calculates second distance information between the first target object and a second target object having a predetermined relationship with the first target object, based on the map information. The estimation unit estimates the position information of the second target object based on the first distance information detected by the detection unit and the second distance information calculated by the calculation unit. The first target is one that is relatively easy to image using a stereo camera. The second target is one that is relatively difficult to image using a stereo camera. [Brief explanation of the drawing]

[0006] [Figure 1] This figure shows an example of a schematic configuration of a driving control system according to one embodiment of the present disclosure. [Figure 2] This figure shows an example of a functional block of the driving control system in Figure 1. [Figure 3] This is a diagram to explain the estimation of the stop line position. [Figure 4] This is a diagram to explain the estimation of the stop line position. [Figure 5] This diagram illustrates an example of a procedure for estimating the position of the stop line. [Figure 6] This diagram illustrates how to estimate the position of a stop line when multiple stop lines are present ahead. [Figure 7] This diagram illustrates the estimation of the stop line position when multiple driving lanes exist. [Modes for carrying out the invention]

[0007] The embodiments of this disclosure will be described in detail below with reference to the drawings.

[0008] <1. Embodiment> [Example Configuration] Figures 1 and 2 show a schematic configuration example of a driving control system 1 according to one embodiment of the present disclosure. The driving control system 1 includes, for example, a driving control device 10 mounted on each of a plurality of vehicles 100, and a control device 200 provided in a network environment NW to which the plurality of driving control devices 10 are connected via wireless communication, as shown in Figures 1 and 2. The driving control device 10 corresponds to one specific example of the "information processing device" of the present disclosure.

[0009] The control device 200 sequentially integrates and updates road map information transmitted from the driving control devices 10 of each vehicle 100, and transmits the updated road map information to each vehicle 100. The control device 200 includes, for example, a road map information integration ECU 201 and a transceiver 202.

[0010] The Road Map Boundary Information Integration ECU 201 integrates road map information collected from multiple vehicles 100 via the transceiver 202 and sequentially updates the road map information surrounding the vehicles on the road. The road map information consists of, for example, a dynamic map and mainly comprises static and quasi-static information that constitutes road information, and quasi-dynamic and dynamic information that mainly constitutes traffic information.

[0011] Static information consists of information that requires updates at a frequency of less than one month, such as roads, road structures, lane information, road surface information, and permanent regulatory information. Structures included in static information include, for example, traffic lights, intersections, road signs, and stop lines. Static information is further linked to multiple structures that are highly related to each other. For example, an intersection and the traffic lights, road signs, and stop lines installed at that intersection are linked to each other. If a road has multiple lanes, the stop lines may be linked to each lane. Each structure included in the static information is assigned a position coordinate (location information) in the dynamic map.

[0012] Semi-static information consists of information that requires updates within one hour, such as traffic restriction information due to road construction or events, wide-area weather information, and congestion forecasts. Semi-dynamic information consists of information that requires updates within one minute, such as actual congestion conditions and driving restrictions at the time of observation, temporary driving obstructions such as fallen objects or obstacles, actual accident conditions, and local weather information.

[0013] Dynamic information consists of information that requires updates every second, such as information transmitted and exchanged between moving objects, information on currently displayed traffic signals, information on pedestrians and cyclists in intersections, and information on vehicles proceeding straight through intersections.

[0014] This road map information is maintained and updated at intervals until the next information is received from each vehicle 100, and the updated road map information is transmitted to each vehicle 100 as appropriate via the transceiver 202.

[0015] The driving control device 10 includes a driving environment recognition unit 11 and a locator unit 12 as units for recognizing the driving environment around the vehicle 100. The driving control device 10 also includes a driving control unit (hereinafter referred to as "driving_ECU") 22, an engine control unit (hereinafter referred to as "E / G_ECU") 23, a power steering control unit (hereinafter referred to as "PS_ECU") 24, and a brake control unit (hereinafter referred to as "BK_ECU") 25. These control units 22 to 25 are connected together with the driving environment recognition unit 11 and the locator unit 12 via an in-vehicle communication line such as CAN (Controller Area Network).

[0016] The traveling ECU 22 controls the vehicle 100, for example, according to the driving mode. Examples of the driving mode include a manual driving mode and a driving control mode. The manual driving mode is a driving mode that requires steering by the driver, and is, for example, a driving mode in which the host vehicle is driven according to driving operations such as a steering operation, an accelerator operation, and a brake operation by the driver. The driving control mode is a driving mode that supports the driver in order to enhance the safety of pedestrians, vehicles, etc. around the vehicle 100 (the host vehicle) in the driving operation by the driver. In the driving control mode, the traveling ECU 22 controls the vehicle 100 so that, for example, when the vehicle 100 (the host vehicle) approaches an intersection and the traffic signal provided at the intersection changes from green to yellow and then to red, the vehicle 100 stops at a stop line near the intersection. The detailed processing content in the driving control mode will be described in detail later. The traveling ECU 22 corresponds to a specific example of the "determination unit", "calculation unit", and "estimation unit" of the present disclosure.

[0017] A throttle actuator 27 is connected to the output side of the E / G ECU 23. This throttle actuator 27 opens and closes the throttle valve of an electronic control throttle provided in the throttle body of the engine, and generates a desired engine output by adjusting the intake air flow rate by opening and closing the throttle valve according to a drive signal from the E / G ECU 23.

[0018] An electric power steering motor 28 is connected to the output side of the PS ECU 24. This electric power steering motor 28 applies a steering torque with the rotational force of the motor to the steering mechanism, and in autonomous driving, lane center maintenance control for maintaining travel in the current travel lane and lane change control for moving the host vehicle to an adjacent lane (lane change control for overtaking, etc.) are executed by controlling the operation of the electric power steering motor 28 according to a drive signal from the PS ECU 24.

[0019] A brake actuator 29 is connected to the output side of the BK_ECU25. This brake actuator 29 adjusts the brake hydraulic pressure supplied to the brake wheel cylinders located on each wheel. When the brake actuator 29 is driven by a drive signal from the BK_ECU25, the brake wheel cylinders generate braking force on each wheel, forcibly decelerating the vehicle.

[0020] The driving environment recognition unit 11 is fixed, for example, to the upper center of the front part inside the vehicle 100. This driving environment recognition unit 11 includes an in-vehicle camera (stereo camera) consisting of a main camera 11a and a sub-camera 11b, an image processing unit (IPU) 11c, and a driving environment detection unit 11d.

[0021] The main camera 11a and sub-camera 11b are autonomous sensors that sense the real space around the vehicle 100. The main camera 11a and sub-camera 11b are positioned symmetrically on either side of the central part of the vehicle 100 in the width direction, and capture stereo images of the area in front of the vehicle 100 from different viewpoints.

[0022] The IPU 11c generates a distance image based on a pair of stereo images of the area in front of the vehicle 100 obtained by capturing images with the main camera 11a and the sub-camera 11b, and calculates the distance image from the amount of displacement of the corresponding object's position.

[0023] The driving environment detection unit 11d determines, for example, the lane markings that demarcate the road around the vehicle 100 based on the distance image received from the IPU 11c. The driving environment detection unit 11d further determines, for example, the road curvature [1 / m] of the markings that demarcate the left and right sides of the road (driving lane) on which the vehicle 100 is traveling, and the width between the left and right markings (vehicle width). The driving environment detection unit 11d further detects lanes and three-dimensional objects such as structures present around the vehicle 100 by, for example, performing predetermined pattern matching on the distance image.

[0024] In the detection of three-dimensional objects by the driving environment detection unit 11d, for example, the type of three-dimensional object, the distance to the three-dimensional object, the speed of the three-dimensional object, and the relative speed between the three-dimensional object and the vehicle 100 (own vehicle) are detected. Examples of three-dimensional objects to be detected include traffic lights, intersections, road signs, stop lines, other vehicles, and pedestrians. If the three-dimensional object is the "first target object" of this disclosure, the distance to the three-dimensional object becomes the "first distance information" of this disclosure. The driving environment detection unit 11d corresponds to one specific example of the "detection unit" of this disclosure. The driving environment detection unit 11d outputs the detected three-dimensional object information to the driving ECU 22, for example.

[0025] The locator unit 12 estimates the position of vehicle 100 (own vehicle position) on a road map and has a locator calculation unit 13 for estimating the own vehicle position. Sensors necessary for estimating the position of vehicle 100 (own vehicle position) are connected to the input side of this locator calculation unit 13. Such sensors include, for example, an acceleration sensor 14, a vehicle speed sensor 15, a gyro sensor 16, and a GNSS receiver 17. The acceleration sensor 14 detects the longitudinal acceleration of vehicle 100. The vehicle speed sensor 15 detects the speed of vehicle 100. The gyro sensor 16 detects the angular velocity or angular acceleration of vehicle 100. The GNSS receiver 17 receives positioning signals transmitted from multiple positioning satellites. In addition, a transceiver 18 is connected to the locator calculation unit 13 for sending and receiving information with the control device 200 and with other vehicles 100.

[0026] Furthermore, a high-precision road map database 19 is connected to the locator calculation unit 13. The high-precision road map database 19 is a large-capacity storage medium such as an HDD, and stores high-precision road map information (dynamic map). This high-precision road map information, for example, similar to the road map information included in the Road Map Information Integration_ECU201, mainly consists of static and quasi-static information that constitutes road information, and quasi-dynamic and dynamic information that mainly constitute traffic information.

[0027] The locator calculation unit 13 includes, for example, a map information acquisition unit 13a, a vehicle position estimation unit 13b, and a driving environment recognition unit 13c.

[0028] The vehicle position estimation unit 13b acquires the position coordinates of the vehicle 100 (own vehicle) based on the positioning signal received by the GNSS receiver 17. These position coordinates correspond to one specific example of "vehicle position information acquired through communication with an external party" in this disclosure. The vehicle position estimation unit 13b also performs map matching of the acquired position coordinates onto route map information to estimate the vehicle's position on the road map. The map information acquisition unit 13a acquires map information for a predetermined range including the vehicle 100 (own vehicle) from the map information stored in the high-precision road map database 19, based on the position coordinates of the vehicle 100 (own vehicle) acquired by the vehicle position estimation unit 13b.

[0029] In environments where the GNSS receiver 17 cannot receive effective positioning signals from positioning satellites due to reduced sensitivity, such as when driving in a tunnel, the vehicle position estimation unit 13b switches to autonomous navigation, which estimates the vehicle's position based on the vehicle speed detected by the vehicle speed sensor 15, the angular velocity detected by the gyro sensor 16, and the longitudinal acceleration detected by the acceleration sensor 14, thereby estimating the vehicle's position on the road map.

[0030] As described above, the vehicle position estimation unit 13b estimates the position of the vehicle 100 on the road map (own vehicle position) based on the positioning signal received by the GNSS receiver 17 or information detected by the gyro sensor 16, etc. Based on the estimated own vehicle position on the road map, it determines the type of road on which the vehicle 100 (own vehicle) is traveling.

[0031] The driving environment recognition unit 13c uses road map information acquired through external communication (vehicle-to-infrastructure communication and vehicle-to-vehicle communication) via the transceiver 18 to update the road map information stored in the high-precision road map database 19 to the latest state. This information update is performed not only on static information but also on quasi-static information, quasi-dynamic information, and dynamic information. As a result, the road map information is composed of road information and traffic information acquired through communication with the outside of the vehicle, and information on moving objects such as vehicles traveling on the road is updated in near real time.

[0032] The driving environment recognition unit 13c verifies road map information based on the driving environment information recognized by the driving environment recognition unit 11 and updates the road map information stored in the high-precision road map database 19 to the latest state. This information update is performed not only on static information but also on quasi-static information, quasi-dynamic information, and dynamic information. As a result, information on moving objects such as vehicles traveling on the road, as recognized by the driving environment recognition unit 11, is updated in real time.

[0033] The updated road map information is then transmitted to the control device 200 and surrounding vehicles of the vehicle 100 (the vehicle itself) via vehicle-to-infrastructure and vehicle-to-vehicle communication through the transceiver 18.

[0034] Furthermore, the driving environment recognition unit 13c outputs map information within a predetermined range, including the vehicle's position estimated by the vehicle position estimation unit 13b, from the updated road map information, along with the vehicle's position (vehicle position information), to the driving_ECU 22.

[0035] Next, we will explain the ECU22 in detail.

[0036] Figure 3 is a diagram illustrating the estimation of the stop line position. Figure 3 shows an example of the road conditions in front of vehicle 100 (the vehicle itself), including vehicle 100 (the vehicle itself). In Figure 3, vehicle 100 (the vehicle itself) is equipped with a driving control device 10 and is traveling on a road with one lane in each direction. In front of vehicle 100 (the vehicle itself) is an intersection, which has traffic lights and a stop line. In Figure 3, "CAM" refers to the position information written adjacent to CAM, which is position information obtained based on image data obtained from a stereo camera. In Figure 3, "MAP" refers to the position information written adjacent to MAP, which is position information included in the road map information stored in the high-precision road map database 19.

[0037] A stereo camera installed on vehicle 100 (the vehicle itself) captures images of the area in front of vehicle 100 (the vehicle itself), and outputs the resulting stereo image to the IPU 11c. The stereo image includes at least an intersection and the traffic light TL (first target object) and stop line SL (second target object) installed corresponding to that intersection. The traffic light TL is a target object that is relatively easier to capture by the stereo camera compared to the stop line SL. Conversely, the stop line SL is a target object that is relatively more difficult to capture by the stereo camera compared to the traffic light TL.

[0038] As shown in Figure 3, if the road conditions allow for the visibility of the stop line, there is a high probability that the stop line will be included in the stereo image in a visible state. In this case, the driving environment detection unit 11d can directly detect the stop line. At this time, the driving ECU 22 may obtain the position of the stop line SL (Xc1, Yc1) based on the distance to the stop line SL detected by the driving environment detection unit 11d, the map information obtained from the driving environment recognition unit 13c, and the vehicle's own position (vehicle position information). Here, Xc1 is the longitude information in the road map information stored in the high-precision road map database 19. Yc1 is the latitude information in the road map information stored in the high-precision road map database 19.

[0039] However, for example, as shown in Figure 4, in road conditions where the stop line SL is not visible, the driving environment detection unit 11d is highly likely to be unable to detect the stop line SL in the stereo image. The driving ECU 22 anticipates such situations and is equipped with a function that allows it to estimate the stop line position even when it is unable to obtain information about the stop line SL from the driving environment detection unit 11d. In Figure 4, "EST" refers to position information estimated using information different from the position information of the road map information stored in the high-precision road map database 19, which is described adjacent to the EST. The procedure for estimating the stop line position by the driving ECU 22 will be explained below using Figure 5.

[0040] Figure 5 shows an example of the procedure for estimating the stop line position. First, the stereo camera acquires a stereo image and outputs it to the IPU 11c. The IPU 11c generates a distance image based on the stereo image acquired by the stereo camera and outputs it to the driving environment detection unit 11d. The driving environment detection unit 11d performs predetermined pattern matching on the distance image generated by the IPU 11c to detect the signal light TL (step S101). Alternatively, the driving environment detection unit 11d may detect the signal light TL by performing predetermined pattern matching on at least one of the stereo image and the distance image.

[0041] If a traffic light TL can be detected in step S101 (step S102; Y), the driving environment detection unit 11d calculates the distance D1 from the vehicle 100 (own vehicle) to the traffic light TL (step S103). The driving environment detection unit 11d calculates the distance D1, for example, based on the distance image. The driving environment detection unit 11d outputs the distance D1 to the driving_ECU22, associating it with the identifier of the traffic light TL.

[0042] The driving ECU 22 acquires map information within a predetermined range, including the vehicle's position estimated by the vehicle position estimation unit 13b, and the vehicle's position (vehicle position information) from the driving environment recognition unit 13c. The driving ECU 22 performs traffic light TL matching based on the distance D1 and traffic light TL identifier acquired from the driving environment detection unit 11d, and the map information and vehicle position (vehicle position information) acquired from the driving environment recognition unit 13c (step S105).

[0043] Specifically, the driving_ECU22 determines whether the map information acquired from the driving environment recognition unit 13c contains anything corresponding to a traffic light TL detected by the driving environment recognition unit 13c. For example, the driving_ECU22 acquires a location (xb1, yb1) at a distance D1 from the vehicle's own position (vehicle position information) from the map information acquired from the driving environment recognition unit 13c as the location of the traffic light TL acquired by the stereo camera. Here, xb1 is the longitude information in the road map information stored in the high-precision road map database 19. yb1 is the latitude information in the road map information stored in the high-precision road map database 19.

[0044] Next, the driving_ECU22 determines whether or not an object corresponding to the traffic light TL is included within a predetermined distance (threshold) from the location (xb1, yb1) of the traffic light TL in the map information acquired from the driving environment recognition unit 13c. For example, when the driving_ECU22 detects a traffic light TL at location (Xb1, Yb1) within the above range in the map information acquired from the driving environment recognition unit 13c, it acquires that location (Xb1, Yb1) as the location of the traffic light TL in the map information acquired from the driving environment recognition unit 13c. Here, Xb1 is the longitude information in the road map information stored in the high-precision road map database 19. Yb1 is the latitude information in the road map information stored in the high-precision road map database 19.

[0045] The driving ECU 22 may set the "predetermined distance" used for determination to a constant value regardless of the magnitude of the distance D1 obtained from the driving environment detection unit 11d. The driving ECU 22 may decrease the "predetermined distance" used for determination as the distance D1 obtained from the driving environment detection unit 11d decreases over time. The driving ECU 22 may continuously (smoothly) change the "predetermined distance" used for determination to a smaller value as the distance D1 decreases. The driving ECU 22 may intermittently (stepwise) change the "predetermined distance" used for determination to a smaller value as the distance D1 decreases. The reason for changing the "predetermined distance" in this way is to enable more accurate matching as the vehicle 100 (own vehicle) approaches the traffic light TL.

[0046] If the signal light TL is matched (step S106; Y), the driving_ECU22 obtains the position information (Xc1, Yc1) of the stop line SL corresponding to the signal light TL at position (Xb1, Yb1) from the map information obtained from the driving environment recognition unit 13c (step S107). At this time, if the driving_ECU22 has obtained the position (Xc1, Yc1) of the stop line SL corresponding to the signal light TL at position (Xb1, Yb1) (step S108; Y), it calculates the relative distance D2 (second distance information) between the signal light TL and the stop line SL based on the map information obtained from the driving environment recognition unit 13c (step S109). Specifically, the driving_ECU22 calculates the relative distance D2 using the position of the signal light TL (Xb1, Yb1) and the position of the stop line SL (Xc1, Yc1).

[0047] The driving ECU22 estimates the position of the stop line SL (xc1, yc1) using the vehicle's position (vehicle position information), distance D1, and relative distance D2 (step S110). However, as shown in Figure 4, if the road conditions make the stop line SL invisible, that is, if the stop line SL cannot be detected from the image data obtained by the stereo camera, the driving ECU22 is highly likely to have not been able to obtain the position of the stop line SL (Xc1, Yc1). In such cases, the driving ECU22 uses the estimated position (xc1, yc1) as the position information of the stop line SL.

[0048] On the other hand, if the signal light TL cannot be matched (step S106;N), or if the position (Xc1,Yc1) of the stop line SL corresponding to the signal light TL at position (Xb1,Yb1) cannot be obtained (step S108;Y), the driving_ECU22 determines whether the relative distance D2 has been calculated in the past (step S111). If the result is that the relative distance D2 has been calculated in the past (step S111;Y), the driving_ECU22 estimates the position (xc1,yc1) of the stop line SL using the previously calculated relative distance D2, the vehicle's position (vehicle position information), and distance D1 (step S110). If the relative distance D2 has never been calculated in the past (step S111;N), the driving_ECU22 terminates the estimation of the stop line SL position.

[0049] [effect] Next, the effects of the driving control system 1 according to one embodiment of the present disclosure will be described.

[0050] In this embodiment, it is determined whether or not an object corresponding to the traffic signal TL is included in the map information, based on the position coordinates of the vehicle 100 (own vehicle) and the distance D1 to the traffic signal TL obtained from a distance image generated based on the stereo image. If it is determined that an object corresponding to the traffic signal TL is included in the map information, the relative distance D2 between the traffic signal TL and the stop line SL which has a predetermined relationship with the traffic signal TL is calculated based on the map information. The position information of the stop line SL is estimated based on the distance D1 and the relative distance D2. Thus, in this embodiment, the position of the stop line SL is not calculated based on the stereo image, but is calculated using the relative distance D2 calculated based on the map information. As a result, even if the stop line SL cannot be detected in the stereo image, the position of the stop line SL can be estimated. As a result, processing can be performed based on the position information of the stop line SL.

[0051] In this embodiment, traffic signals TL and stop lines SL are associated with each other in the map information. As a result, the position of the stop line SL corresponding to the detected traffic signal TL can be determined simply by referring to the map information, allowing the position of the stop line SL to be estimated with less computation.

[0052] In this embodiment, the map information acquired from the driving environment recognition unit 13c determines whether or not an object corresponding to a traffic signal TL is included within a predetermined distance range from the location (xb1, yb1) of the traffic signal TL. By using this determination method, it is possible to detect traffic signal TLs included in the map information, taking into account the accuracy of the location (xb1, yb1) of the traffic signal TL obtained from the stereo camera.

[0053] In this embodiment, in the determination method described above, the predetermined distance (threshold) decreases as the distance D1 decreases. By changing the predetermined distance (threshold) in this way, the position of the traffic light TL on the map can be detected with high accuracy as the vehicle 100 (own vehicle) approaches the traffic light TL.

[0054] <2. Variant> Although the present disclosure has been described above with reference to embodiments, the present disclosure is not limited to these embodiments, and various modifications are possible.

[0055] [Differentiation A] In the above embodiment, for example, suppose there are multiple stop lines in front of the vehicle 100, as shown in Figure 6. In this case, the driving_ECU22 may select the relatively closer stop line SL as the stop line SL corresponding to the traffic light TL. However, in the map information acquired from the driving environment recognition unit 13c, the relatively closer stop line is not associated with the stop line SL corresponding to the traffic light TL. Therefore, by using the information about the correspondence with the traffic light TL included in the map information acquired from the driving environment recognition unit 13c, the driving_ECU22 can correctly select the relatively farther stop line SL, rather than the relatively closer stop line, as the stop line SL corresponding to the traffic light TL.

[0056] Furthermore, it is possible that the map information acquired from the driving environment recognition unit 13c does not specify a stop line SL corresponding to a traffic light TL. For example, this possibility arises when information about the correspondence with a traffic light TL is not included in the map information when a traffic light TL is newly installed or relocated. Therefore, if the driving environment detection unit 11d detects multiple stop lines in front of a traffic light TL, the driving_ECU 22 may select the stop line closest to the traffic light TL from among the multiple stop lines detected by the driving environment detection unit 11d in front of the traffic light TL as the stop line SL corresponding to the traffic light TL.

[0057] [Variation B] In the above embodiment and modified example A, for example, as shown in Figure 7, suppose that vehicle 100 (own vehicle) is traveling in one of several lanes (driving lanes). In this case, the driving_ECU22 may select a stop line SL in a different lane (driving lane) than the one in which vehicle 100 (own vehicle) is traveling as the stop line SL corresponding to the traffic signal TL. Therefore, the driving_ECU22 can correctly select a stop line SL corresponding to the lane (driving lane) in which vehicle 100 (own vehicle) is traveling by using the information about lanes (driving lanes) included in the correspondence with traffic signal TL, which is included in the map information acquired from the driving environment recognition unit 13c.

[0058] Furthermore, in the map information acquired from the driving environment recognition unit 13c, it is possible that only information about the stop line SL corresponding to the traffic light TL is defined for a lane (driving lane) different from the lane (driving lane) in which the vehicle 100 (own vehicle) is traveling. Therefore, if the driving environment detection unit 11d detects multiple lanes (driving lanes), the driving_ECU 22 may estimate the position information of the stop line SL corresponding to the lane (driving lane) in which the vehicle 100 (own vehicle) is traveling, based on the positional relationship between the lane (driving lane) with the stop line corresponding to the traffic light TL and the lane (driving lane) in which the vehicle 100 (own vehicle) is traveling, using the position information of the stop line SL corresponding to the traffic light TL.

[0059] [Differentiation C] In the above embodiments and modifications A and B, traffic lights were given as an example of a target that is relatively easy to image with a stereo camera, and stop lines were given as an example of a target that is relatively difficult to image with a stereo camera. However, in the above embodiments and modifications A and B, the target that is relatively easy to image with a stereo camera may be an intersection or a road sign. Also, in the above embodiments and modifications A and B, the target that is relatively difficult to image with a stereo camera may be a landmark other than a stop line.

[0060] [Differentiation D] In the above embodiments and modified examples A to C, the position coordinates were two-dimensional, but they may also be three-dimensional.

[0061] [Differentiation Example E] In the above embodiments and modifications A to D, the vehicle 100's movement was controlled using the position of the stop line SL. However, in the above embodiments and modifications A to D, the position of the stop line SL may be used for other purposes. For example, in a stereo image, by setting different thresholds for the region within a predetermined distance from the position of the stop line SL at a certain time (the region near the stop line) and the region surrounding the region near the stop line, the stop line in the stereo image can be controlled thereafter. SL It may be helpful to make it easier to detect them.

[0062] Furthermore, the effects described herein are merely illustrative and not limiting, and other effects may also occur. [Explanation of Symbols]

[0063] 1... Driving control system, 10... Driving control device, 11... Driving environment recognition unit, 12... Locator unit, 13... Locator calculation unit, 13a... Map information acquisition unit, 13b... Vehicle position estimation unit, 13c... Driving environment recognition unit 13c, 14... Acceleration sensor, 15... Vehicle speed sensor, 16... Gyro sensor, 17... GNSS receiver, 18... Transmitter / receiver, 19... High-precision road map database, 22... Driving ECU, 23... E / G ECU, 24... PS ECU, 25... BK ECU, 27... Throttle actuator, 28... Electric power steering motor, 29... Brake actuator, 100... Vehicle, 200... Control device, 201... Road map information integration ECU, 202... Transmitter / receiver.

Claims

1. A detection unit that detects first distance information to a first target object based on a distance image generated based on a stereo image, A determination unit determines whether or not an object corresponding to the first target object is included in the map information based on vehicle position information obtained through communication with an external party and the first distance information detected by the detection unit, If the determination unit determines that the map information contains an object corresponding to the first target object, the calculation unit calculates second distance information between the first target object and a second target object having a predetermined relationship with the first target object, based on the map information. An estimation unit estimates the position information of the second target object based on the first distance information detected by the detection unit and the second distance information calculated by the calculation unit. Equipped with, The aforementioned first target is a target that is relatively easy to image using a stereo camera. The second target is a target that is relatively difficult to image using a stereo camera. Information processing device.

2. The calculation unit estimates the position information of the second target object based on the first distance information and the second distance information that has been calculated in the past. The information processing apparatus according to claim 1.

3. In the aforementioned map information, the first target object and the second target object are related to each other. The information processing apparatus according to claim 1 or claim 2.

4. The first target object is a traffic light, The second target is a stop line. The information processing apparatus according to any one of claims 1 to 3.

5. The determination unit determines whether or not an object corresponding to the first target object is included within a predetermined threshold range from the position of the first target object in the map information obtained from the vehicle position information and the first distance information. The information processing apparatus according to any one of claims 1 to 4.

6. The determination unit reduces the threshold as the first distance information becomes shorter. The information processing apparatus according to claim 5.

Images