Processing system, processing method, and processing program

Abstract

To provide a processing system capable of ensuring output accuracy of information on a travel lane where a host vehicle is traveling.SOLUTION: A processor of a processing system executes steps of: acquiring marker information Im provided by recognizing a lane marker by sensing from a host vehicle, the lane marker defining each of travel lanes parallel to each other on a travel road where the host vehicle is traveling; acquiring target information It provided by recognizing a target vehicle by sensing from the host vehicle, the target vehicle traveling in one of the travel lanes on the travel road where the host vehicle is traveling; acquiring estimation information Ie provided by estimating an unrecognized marker unrecognized in the marker information Im, as the lane marker defining the travel lane where the target vehicle indicated by the target information It is traveling; and identifying a host lane, as the travel lane where the host vehicle is traveling, from the marker information Im with the estimation information Ie added thereto, and outputting lane identification information Ii.SELECTED DRAWING: Figure 4

Description

[Technical Field]

[0001] The present disclosure relates to processing techniques for assisting vehicle driving. [Background technology]

[0002] The technology disclosed in Patent Document 1 evaluates the likelihood of the host vehicle's position for each of the multiple parallel driving lanes based on detection information of the white lines that separate the lane on the road on which the host vehicle is traveling, and determines the lane in which the host vehicle is actually traveling. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Publication No. 2019-28856 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the technology disclosed in Patent Document 1 is based on the premise that all white lines of each driving lane can be recognized from the detection information. Therefore, if it becomes difficult to recognize some white lines, there is a concern that the driving lane in which the vehicle is traveling may be misjudged.

[0005] An object of the present disclosure is to provide a processing system that ensures the output accuracy of information related to the lane in which a host vehicle is traveling. Another object of the present disclosure is to provide a processing method that ensures the output accuracy of information related to the lane in which a host vehicle is traveling. Yet another object of the present disclosure is to provide a processing program that ensures the output accuracy of information related to the lane in which a host vehicle is traveling. [Means for solving the problem]

[0006] The technical means of the present disclosure for solving the problems will be described below. Note that the claims and the reference characters in parentheses in this section indicate the correspondence with the specific means described in the embodiments described later in detail, and do not limit the technical scope of the present disclosure.

[0007] A first aspect of the present disclosure is A processing system having a processor (12) for performing driving-related processing related to the driving of a host vehicle (2) traveling on a roadway (9) having a plurality of parallel traveling lanes (90), The processor Acquiring marker information (Im) of lane markers (900) that demarcate each driving lane on a driving road on which the host vehicle is traveling, recognized by sensing from the host vehicle; Acquiring target information (It) recognized by sensing from the host vehicle about a target vehicle (30) traveling in any of the travel lanes on a travel road on which the host vehicle is traveling; Acquiring estimated information (Ie) that estimates an unrecognized marker (900b) that is not recognized in the marker information as a lane marker that defines a driving lane in which a target vehicle represented by the target information is traveling; The host vehicle is configured to identify a host lane (90a) that is a traveling lane in which the host vehicle is traveling from the marker information to which the estimated information is added, and to output lane identification information (Ii).

[0008] A second aspect of the present disclosure is A processing method executed by a processor (12) to perform driving-related processing related to the driving of a host vehicle (2) traveling on a roadway (9) having a plurality of parallel driving lanes (90), comprising: Acquiring marker information (Im) of lane markers (900) that demarcate each driving lane on a driving road on which the host vehicle is traveling, recognized by sensing from the host vehicle; Acquiring target information (It) recognized by sensing from the host vehicle about a target vehicle (30) traveling in any of the travel lanes on a travel road on which the host vehicle is traveling; Acquiring estimated information (Ie) that estimates an unrecognized marker (900b) that is not recognized in the marker information as a lane marker that defines a driving lane in which a target vehicle represented by the target information is traveling; and identifying a host lane (90a) that is a driving lane in which the host vehicle is traveling from the marker information to which the estimated information has been added, and outputting lane identification information (Ii).

[0009] A third aspect of the present disclosure is A processing program stored in a storage medium (10) for performing driving-related processing related to the driving of a host vehicle (2) traveling on a road (9) having a plurality of parallel driving lanes (90), the processing program including instructions to be executed by a processor (12) that performs the driving-related processing, Acquiring marker information (Im) of lane markers (900) that demarcate each driving lane on a driving road on which the host vehicle is traveling, recognized by sensing from the host vehicle; Acquiring target information (It) recognized by sensing from the host vehicle about a target vehicle (30) traveling in any of the travel lanes on a travel road on which the host vehicle is traveling; Acquiring estimated information (Ie) that estimates an unrecognized marker (900b) that is not recognized in the marker information as a lane marker that defines a driving lane in which a target vehicle represented by the target information is traveling; The host vehicle is traveling in a host lane (90a) in response to the marker information to which the estimated information has been added, and the ...

[0010] In this way, in the first to third aspects, marker information is acquired by sensing lane markers that define multiple parallel driving lanes on the driving road on which the host vehicle is traveling. At the same time, in the first to third aspects, target information is acquired by sensing a target vehicle traveling in one of the driving lanes on the driving road from the host vehicle. Therefore, in the first to third aspects, estimated information is acquired that estimates unrecognized markers that are not recognized in the marker information as lane markers that define the driving lane in which the target vehicle represented by the target information is traveling. This makes it possible to accurately identify the host lane, which is the driving lane in which the host vehicle is traveling, from the marker information in which the unrecognized markers are complemented by the addition of estimated information. Therefore, it is possible to ensure the output accuracy of lane identification information that identifies the host lane. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a block diagram illustrating a physical configuration of a processing system according to one embodiment. [Figure 2] FIG. 1 is a schematic diagram illustrating a traveling environment of a host vehicle to which an embodiment is applied. [Figure 3] FIG. 1 is a block diagram illustrating a functional configuration of a processing system according to an embodiment. [Figure 4] 1 is a flowchart illustrating a process flow according to one embodiment. [Figure 5] FIG. 1 is a schematic diagram illustrating a processing flow according to an embodiment. [Figure 6] FIG. 1 is a perspective view illustrating a processing flow according to an embodiment. [Figure 7] FIG. 1 is a schematic diagram illustrating a processing flow according to an embodiment. [Figure 8] FIG. 1 is a schematic diagram illustrating a processing flow according to an embodiment. [Figure 9] FIG. 1 is a schematic diagram illustrating a processing flow according to an embodiment. [Figure 10] FIG. 1 is a schematic diagram illustrating a processing flow according to an embodiment. [Figure 11] FIG. 1 is a schematic diagram illustrating a processing flow according to an embodiment. [Figure 12] FIG. 1 is a schematic diagram illustrating a processing flow according to an embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, an embodiment of the present disclosure will be described with reference to the drawings.

[0013] A processing system 1 according to one embodiment shown in FIG. 1 performs driving-related processing related to the operation of a host vehicle 2. At least a portion of the processing system 1 is mounted on the host vehicle 2. The host vehicle 2 to which the processing system 1 is applied may be capable of achieving a level of automated driving defined, for example, in SAE J3016 or the like, in which a manual driving assistance task exists that assists an operator in performing manual driving operations along with an automated driving task. Here, the host vehicle 2 is a road user, such as an automobile or truck. From a perspective centered on the host vehicle itself, the host vehicle 2 may also be referred to as an ego-vehicle. Therefore, in this embodiment, the driver who sits in the driver's seat and is capable of performing manual driving operations as the operator of the host vehicle 2 is the target of driving assistance through the driving-related processing.

[0014] As shown in Fig. 2, a traffic scene in which other road users 3 other than the host vehicle 2 exist is assumed in the traffic environment in which the host vehicle 2 travels. The other road users 3 include non-vulnerable road users and vulnerable road users according to their vulnerability levels. A non-vulnerable road user is at least one type of target vehicle 30, such as a car, a truck, a motorcycle, a bicycle, or a micromobility vehicle. A vulnerable user is a human being, such as a pedestrian.

[0015] 1, a host vehicle 2 is equipped with an actuator system 4, a sensor system 5, a communication system 6, and an information presentation system 7, along with at least a part of a processing system 1. However, FIG. 1 representatively shows an example in which the entire processing system 1 is equipped in the host vehicle 2, as an example implemented in the form of a device such as a control device (e.g., a control circuit, etc.) or a semiconductor device (e.g., a semiconductor chip, etc.).

[0016] The actuator system 4 is configured to be able to control the host vehicle 2 based on a control command provided by the processing system 1. The actuator system 4 may be at least one type of power train actuator, such as an internal combustion engine or a motor-generator-motor. The actuator system 4 may be at least one type of braking actuator, such as a brake unit. The actuator system 4 may be at least one type of steering actuator, such as a power steering unit.

[0017] The sensor system 5 senses the external and internal environments of the host vehicle 2 to obtain sensing information that can be used by the processing system 1. To this end, the sensor system 5 includes an external sensor 50 and an internal sensor 52.

[0018] The external sensor 50 senses targets that exist in the external world of the host vehicle 2. The target sensing type external sensor 50 is at least one type of sensor selected from the group consisting of an in-vehicle camera, LiDAR (light detection and ranging / laser imaging detection and ranging), radar, and sonar. The target sensing type external sensor 50 may be implemented in a combination of multiple types so as to be capable of sensing the front, side, and rear directions of the host vehicle 2.

[0019] The internal sensor 52 senses a specific physical quantity of motion related to vehicle motion in the internal world of the host vehicle 2. The internal sensor 52 of the motion sensing type is at least one of, for example, a speed sensor, an acceleration sensor, a gyro sensor, and an inertial sensor. The internal sensor 52 may sense the operation or state of occupants, including the driver, in the internal world of the host vehicle 2. The internal sensor 52 of the occupant sensing type is at least one of, for example, an accelerator pedal sensor, a brake pedal sensor, a shift sensor, a steering angle sensor, a steering torque sensor, an occupant camera, and an occupant seat switch.

[0020] The communication system 6 acquires communication information usable by the processing system 1 through wireless communication. The communication system 6 may receive positioning signals from satellites of a global navigation satellite system (GNSS) present in the external world of the host vehicle 2. The positioning type communication system 6 is, for example, a GNSS receiver. The communication system 6 may transmit and receive communication signals to and from a V2X system present in the external world of the host vehicle 2. The V2X communication type communication system 6 is, for example, at least one of a dedicated short range communications (DSRC) communication device and a cellular V2X (C-V2X) communication device. The communication system 6 may transmit and receive communication signals to and from a mobile terminal present in the internal world of the host vehicle 2. The terminal communication type communication system 6 is, for example, at least one of a Bluetooth (registered trademark) device, a Wi-Fi (registered trademark) device, an infrared communication device, etc.

[0021] The information presentation system 7 presents notification information to occupants, including the driver, in the host vehicle 2. The information presentation system 7 may present the notification information by stimulating the vision of the occupants in the host vehicle 2. The visual presentation type information presentation system 7 is, for example, at least one of an in-vehicle monitor, a head-up display (HUD), a combination meter, a navigation unit, and an illumination unit. The information presentation system 7 may present the notification information by stimulating the auditory sense of the occupants. The auditory presentation type information presentation system 7 is, for example, at least one of a speaker, a buzzer, a vibration unit, and the like.

[0022] The processing system 1 is connected to an actuator system 4, a sensor system 5, a communication system 6, and an information presentation system 7 via at least one of, for example, a local area network (LAN), a wire harness, an internal bus, or a wireless communication line. The processing system 1 is configured to include at least one dedicated computer.

[0023] The dedicated computer constituting the processing system 1 may be a locator ECU (electronic control unit) that estimates the self-position of the host vehicle 2. The dedicated computer constituting the processing system 1 may be a navigation ECU that navigates a driving route in driving control of the host vehicle 2. The dedicated computer constituting the processing system 1 may be an integration ECU that integrates driving control of the host vehicle 2.

[0024] The dedicated computer constituting the processing system 1 may be a sensing ECU that processes sensing information in the operation control of the host vehicle 2. The dedicated computer constituting the processing system 1 may be a recognition ECU that recognizes the external world in the operation control of the host vehicle 2. The dedicated computer constituting the processing system 1 may be a planning ECU that plans the operation control of the host vehicle 2. The dedicated computer constituting the processing system 1 may be an actuator ECU that controls the actuator system 4 as part of the operation control of the host vehicle 2.

[0025] The dedicated computer constituting the processing system 1 may be an information management ECU that controls the information presentation system 7 as part of the driving control of the host vehicle 2. The dedicated computer constituting the processing system 1 may also be at least one external computer that constitutes, for example, an external center or a mobile terminal that can communicate via the communication system 6.

[0026] The dedicated computer constituting the processing system 1 has at least one memory 10 and one processor 12. The memory 10 of the processing system 1 is at least one type of non-transitory tangible storage medium, such as a semiconductor memory, a magnetic medium, or an optical medium, that non-temporarily stores computer-readable programs, data, etc. The processor 12 includes at least one type of core, such as a central processing unit (CPU), a graphics processing unit (GPU), or a reduced instruction set computer (RISC)-CPU.

[0027] At least one memory 10 in the processing system 1 stores map information that can be used by the system 1. The memory 10 that stores the map information may function as a DB for a locator that estimates the self-position of the host vehicle 2. The memory 10 that stores the map information may also function as a DB for a navigation unit that navigates the driving route of the host vehicle 2.

[0028] The memory 10 storing the map information may download digital maps, for example, by V2X communication with an external center via the communication system 6, and sequentially update the map information. The map information is converted into two-dimensional or three-dimensional data representing the external environment in which the host vehicle 2 is traveling. Digital data of a high-precision map may be used as the three-dimensional map information. Such map information includes road information representing at least one of the following: the location, shape, and size of roads.

[0029] Here, the road information may represent at least one type of road structure information, such as the number of lanes, position, width, length, shape, driving direction, curvature (or radius), and nodes, regarding the driving lanes 90 that constitute the driving path 9 on the road on which the vehicles 2, 30 are currently traveling and will travel in the future, as shown in Figure 2. The road information may also represent at least one type of marking information, such as the position, width, length, shape, and curvature (or radius), regarding signs attached to the road and lane markers (i.e., dividing lines) 900 that divide the driving lanes 90 as shown in Figure 2. In addition to the above, the road information may represent at least one type of structure information, such as the position, shape, and size, regarding buildings and traffic lights facing the road.

[0030] 1 executes a plurality of instructions included in a processing program stored as software in memory 10. In this way, processing system 1 constructs a plurality of functional blocks for performing driving-related processing in host vehicle 2. The plurality of functional blocks constructed by processing system 1 in this way include a recognition block 100 and a control block 120, as shown in FIG.

[0031] The recognition block 100 acquires sensing information from the sensor system 5. The recognition block 100 acquires communication information from the communication system 6. The recognition block 100 acquires map information stored in the memory 10 by reading it from the memory 10. The recognition block 100 acquires past information of control commands given to the host vehicle 2 by the control block 120 from the memory 10. The recognition block 100 processes this acquired information individually and then fuses it to recognize the state of the external and internal environments for each driving scene of the host vehicle 2 and generate recognition information.

[0032] Specifically, the recognition block 100 generates recognition information by recognizing a target that exists in the external world of the host vehicle 2. The recognition information regarding the target may represent at least one type of physical quantity of motion, such as a separation distance, a direction of motion, a relative velocity, a relative acceleration, and a time to collision. Here, the recognition block 100 of this embodiment generates recognition information regarding the target so as to include target information It representing the physical quantity of motion of the target vehicle 30 among the sensing information recognized by sensing from the external sensor 50 in the host vehicle 2. The recognition information regarding the target may represent a classification of targets clustered based on such physical quantities of motion.

[0033] The recognition block 100 generates recognition information by recognizing the road on which the host vehicle 2 is traveling. The recognition information regarding the road may represent road information equivalent to the map information described above. However, in the recognition block 100 of this embodiment, the recognition information regarding the road is generated so as to include marker information Im representing the lane markers 900 from the sensing information recognized by sensing from the external sensor 50 of the host vehicle 2. At the same time, the recognition block 100 of this embodiment generates the recognition information regarding the road so as to include lane structure information Is representing the driving lane 90 from the road structure information recognized by reading map information from the memory 10 separately from the sensing information.

[0034] The recognition block 100 may generate recognition information by localization that recognizes the self-state including the self-position of the host vehicle 2. The recognition information regarding the self-state may represent at least one type of self-state, such as the self-position, attitude angle, steering angle, speed, acceleration, jerk, and yaw rate, which appear in the host vehicle 2 in accordance with the control command from the control block 120.

[0035] In the recognition block 100, sub-blocks such as a reading sub-block 101, a sensing sub-block 102, an estimation sub-block 103, and an identification sub-block 104 are constructed as shown in Fig. 3. The driving-related processing performed by the cooperation of the functions of these sub-blocks 101, 102, 103, and 104 will be described in detail later.

[0036] 3 acquires recognition information from the recognition block 100. The control block 120 acquires past information on control commands to the host vehicle 2 by reading it from the memory 10. Based on this acquired information, the control block 120 plans a target driving trajectory for future travel of the host vehicle 2. In this case, the driving trajectory specifies the time-series changes for each control period expected in the future beyond the present regarding the motion parameters that are targeted as the self-state of the host vehicle 2.

[0037] The control block 120 generates control commands to be set in the host vehicle 2 based on the recognition information and past information on control commands from the recognition block 100, as well as trajectory information related to the planned driving trajectory. At this time, control commands are generated to be sent to the actuator system 4 so as to control driving behavior according to the autonomous driving level adjusted to suit the driving scene, either the autonomous driving task or the manual driving assistance task in the host vehicle 2. The data of the control commands generated in this way is stored in the memory 10.

[0038] (Processing flow) Of the blocks 100 and 120 described above, the processing method for performing driving-related processing of the host vehicle 2 by cooperation of the sub-blocks 101, 102, 103, and 104 in the recognition block 100 is executed according to the processing flow shown in Figure 4. This processing flow is repeatedly executed while the host vehicle 2 is running. In the following explanation, each "S" in the processing flow refers to multiple steps executed by multiple instructions included in the processing program.

[0039] 3 acquires lane structure information Is, which indicates all of the driving lanes 90 that should exist on the road 9 on which the host vehicle 2 is traveling, as recognition information recognized by reading map information stored in memory 10. At this time, the lane structure information Is includes the number of lanes Ns of the driving lanes 90 on the road 9 on which the host vehicle 2 is traveling, as shown in FIG. 5. In addition, the lane structure information Is includes the legally prescribed driving direction Ds for each of the driving lanes 90 on the road 9 on which the host vehicle 2 is traveling, as shown in FIG. 5.

[0040] 4, in S20 following S10 in the processing flow, the read sub-block 101 in FIG. 3 determines whether the number of lanes Ns indicated by the lane structure information Is acquired in S10 based on the map information in the memory 10 is more than one (i.e., two or more in FIG. 4). If a positive determination is made because the number of lanes Ns indicated by the lane structure information Is is more than one, that is, because the host vehicle 2 is traveling on a road 9 (see FIG. 2) with multiple parallel traveling lanes 90, the processing flow proceeds to S30 and S40. The transitions to S30 and S40 may be performed in parallel or sequentially.

[0041] In S30, the sensing sub-block 102 in Fig. 3 acquires target information It, which recognizes the target vehicle 30 traveling in one of the travel lanes 90 on the travel path 9 on which the host vehicle 2 is traveling, as recognition information recognized by sensing from the external sensor 50. At this time, the target information It includes a movement direction Dt of the target vehicle 30 traveling in the same host lane 90a as the host vehicle 2 and / or a target lane 90b different from the host vehicle 2 on the travel path 9 on which the host vehicle 2 is traveling, as shown in Fig. 6. Therefore, the movement direction Dt may be recognized by, for example, performing vector analysis on sensing information in multiple frames of camera images or the like regarding the movement of the target vehicle 30.

[0042] 4, in S40, the sensing sub-block 102 in FIG. 3 acquires marker information Im that recognizes lane markers 900 that demarcate each travel lane 90 on the travel road 9 on which the host vehicle 2 is traveling, as recognition information recognized by sensing from the external sensor 50. At this time, the lane markers 900 may be recognized based on a recognition model such as a machine learning model, so that whether the lane markers 900 are continuous lines or discontinuous lines, the lane markers 900 may be regarded as continuous line lane markers 900 and reflected in the marker information Im (see FIGS. 7 to 9, described below). Therefore, in S40 of this embodiment, based on this recognition, erroneous recognition information Imm regarding lane markers 900 that are determined to have been erroneously recognized is excluded from the marker information Im (see FIGS. 8 and 9, described below).

[0043] Specifically, when excluding the erroneous information Imm in S40, the lane width Wl of the driving lane 90, which is defined as the distance between the widthwise centers of the lane markers 900 represented by the marker information Im before the elimination, is recognized as shown in Figures 7 and 8. The recognized lane width Wl includes the lane width Wla between the lane markers 900 that define the host lane 90a in which the host vehicle 2 is traveling from both sides. Therefore, in S40, it is determined whether the absolute value (i.e., magnitude) of the difference between the lane width Wla of the host lane 90a and the lane width Wl of each driving lane 90 is within an allowable range.

[0044] 7 and 8 show marker information Im obtained by converting sensing information, such as a camera image, viewed from the host vehicle 2 into bird's-eye view information from above to improve the accuracy of determining the difference between the lane widths Wl and Wla. The difference between the lane widths Wl and Wla may be determined using the marker information Im without such viewpoint conversion. In either case, the acceptable range may be set to, for example, 0.5 meters or less, so that erroneous information Imm related to the lane marker 900 can be extracted.

[0045] Therefore, in S40, if a positive determination is made that all differences between the lane width Wla and the lane width Wl are within the allowable range, as in the case of Figure 7, the process of excluding the misidentification information Imm from the marker information Im is skipped. On the other hand, if a negative determination is made that at least one difference between the lane width Wla and the lane width Wl is outside the allowable range, as in the case of Figure 8, the recognition information of the lane marker 900af, which is located farther away from the host lane 90a among the lane markers 900a that define the driving lane 90 that is outside the allowable range, is extracted as the misidentification information Imm. In S40, the misidentification information Imm thus extracted is excluded from the marker information Im, as shown in Figure 9.

[0046] As shown in Fig. 4, when both S30 and S40 are completed, the processing flow proceeds to S50. In S50, the estimation sub-block 103 in Fig. 3 estimates an unrecognized marker 900b that is unrecognized in the marker information Im obtained by S40 as a lane marker 900 that defines the target lane 90b in which the target vehicle 30, represented by the target information It obtained by S30, is traveling (see Figs. 10 and 11, which will be described later). Therefore, in S50, the estimation sub-block 103 acquires estimation information Ie for identifying the estimated unrecognized marker 900b.

[0047] Specifically, in the estimation of the unrecognized marker 900b in S50, it is determined whether a lane marker 900 is recognized on the opposite side of the target vehicle 30 represented by the target information It from S30 from the host lane 90a in the marker information Im from S40, as shown in Figures 10 and 11. At this time, the accuracy of the determination may be improved by using at least one of the movement direction Dt of the target vehicle 30 represented by the target information It from S30 and the lane width Wla of the host lane 90a represented by the marker information Im from S40 (see Figures 7 and 9 described above).

[0048] 10 and 11 show marker information Im obtained by converting, from a viewpoint, sensing information viewed from the host vehicle 2, such as a camera image, into bird's-eye view information from above in order to improve the estimation accuracy of the unrecognized marker 900b. Note that the unrecognized marker 900b may be estimated from the marker information Im without such viewpoint conversion.

[0049] Therefore, in S50, if a lane marker 900 is recognized on the opposite side of the host lane 90a of the target vehicle 30 as in the case of Fig. 10 and a positive determination is made, estimation of the unrecognized marker 900b is skipped and estimated information Ie is generated without identifying the unrecognized marker 900b. On the other hand, if a negative determination is made because a lane marker 900 is not recognized on the opposite side of the host lane 90a of the target vehicle 30 as in the case of Fig. 11, the unrecognized lane marker 900 that should have been recognized is estimated as the unrecognized marker 900b. For the unrecognized marker 900b estimated in this way, estimated information Ie is generated to represent at least one of the following: position, width, length, shape, and curvature (or radius), for example.

[0050] 4, in S60 following S50 in the processing flow, the identification sub-block 104 in Fig. 3 identifies the host lane 90a in which the host vehicle 2 is traveling from updated marker information Ime obtained by adding estimated information Ie obtained by S50 to marker information Im obtained by S40. Therefore, in S60, lane identification information Ii for notifying the identified host lane 90a is output as data by the identification sub-block 104.

[0051] Specifically, when the marker information Im is updated in S60, the parallel number Nme of the traveling lanes 90 between the lane markers 900 including the unrecognized marker 900b, as represented by the estimation information Ie when the unrecognized marker 900b is estimated in S50, is recognized as shown in FIG. 12. Therefore, the parallel number Nme of the traveling lanes 90 recognized to include the target lane 90b that should be separated by the unrecognized marker 900b is added to the updated marker information Ime along with the estimation information Ie. Furthermore, the parallel number Nme represented by the updated marker information Ime is compared with the number of lanes Ns represented by the lane structure information Is in S20 (see FIG. 5, described above). As a result, when the parallel number Nme matches the number of lanes Ns, the updated marker information Ime is used to identify the host lane 90a.

[0052] However, in S60 when the parallel number Nme does not match the lane number Ns, the updated marker information Ime from the most recent S60 among the S60s in which the parallel number Nme matched the lane number Ns in the past processing flow is provided to identify the host lane 90a. Also, in S60, if it is determined in S50 that the unrecognized marker 900b has not been identified, the unidentified marker information Ie is added, and the updated marker information Ime containing the parallel number Nme of the marker information Im recognized in S40 is used for matching and identification in the same way as in the case of estimating the unrecognized marker 900b.

[0053] In identifying the host lane 90a from the updated marker information Ime, S60 also compares the travel direction Ds of each travel lane 90 represented by the lane structure information Is obtained by S20 with the movement direction Dt of the target vehicle 30 represented by the target information It obtained by S30. As a result, the accuracy of identifying the target lane 90b, 90a, in which the target vehicle 30 is traveling and whose movement direction Dt matches the travel direction Ds, is ensured based on the updated marker information Ime for each lane marker 900 that defines the host lane 90a. In particular, when an unrecognized marker 900b is estimated by S50, the host lane 90a can be identified with high accuracy based on the updated marker information Ime that includes estimation information Ie of the marker 900b that defines the target lane 90b with the matching directions Ds and Dt. In addition, the identification of the host lane 90a by S60 may be performed based on at least one of recognition information representing the vehicle's own status including its own position and recognition information representing a landmark as a structure, in addition to being based on the updated marker information Ime.

[0054] 3 in S60 is generated to represent the position of the identified host lane 90a. Therefore, in S60, the lane identification information Ii may be output by visually presenting (i.e., navigation displaying) the identified position of the host lane 90a from the information presentation system 7 together with the host vehicle 2's own position in the lane 90a. In S60, the identified position of the host lane 90a may be stored in the memory 10 together with the host vehicle 2's own position in the lane 90a, thereby enabling the lane identification information Ii to be output so that it can be used by the subsequent block 120 of the recognition block 100. In S60, the identified position of the host lane 90a may be transmitted via the communication system 6 together with the host vehicle 2's own position in the lane 90a, thereby enabling the lane identification information Ii to be output to an external center and / or the target vehicle 30.

[0055] 4, when the output of the lane identification information Ii by S60 is completed, the execution of the current processing flow is terminated. Note that, if a negative determination is made in S20 above because the number of lanes Ns indicated by the lane structure information Is is single (i.e., 1), the execution of the current processing flow is terminated after the output processing of the lane identification information Ii equivalent to S60 is performed with the single travel lane 90 as the host lane 90a.

[0056] (Action and effect) The effects of the present embodiment described above will be explained below.

[0057] In this embodiment, marker information Im is acquired by sensing lane markers 900 that define each of a plurality of parallel driving lanes 90 on the driving road 9 on which the host vehicle 2 is traveling. At the same time, target information It is also acquired by sensing a target vehicle 30 that is traveling in one of the driving lanes 90 on the driving road 9, the target vehicle 2. Therefore, according to this embodiment, estimated information Ie is acquired by estimating unrecognized markers 900b that are not recognized in the marker information Im as lane markers 900 that define the driving lane 90 (target lane 90b in this embodiment) in which the target vehicle 30 represented by the target information It is traveling. This allows the host lane 90a, which is the driving lane 90 on which the host vehicle 2 is traveling, to be accurately identified from marker information Im (updated marker information Ime in this embodiment) in which the unrecognized markers 900b are supplemented by the addition of estimated information Ie. Therefore, it is possible to ensure the output accuracy of the lane identification information Ii that identifies the host lane 90a.

[0058] According to this embodiment, estimated information Ie is acquired that estimates an unrecognized marker 900b on the opposite side of the host lane 90a from the target vehicle 30 represented by the target information It. Even if an unrecognized marker 900b occurs due to, for example, the distance from the host vehicle 2 across the target vehicle 30 and / or the target vehicle 30 forming a blind spot from the host vehicle 2, the host lane 90a can be accurately identified from the marker information Im that is supplemented for the marker 900b. Therefore, by effectively utilizing the target information It that recognizes the target vehicle 30, it is possible to ensure the output accuracy of lane identification information Ii that identifies the host lane 90a.

[0059] In this embodiment, lane structure information Is, including the driving direction Ds of the driving lane 90 on the driving road 9 on which the host vehicle 2 is traveling, is acquired from a memory 10 in which the information Is is stored in the host vehicle 2. At the same time, target information It, including the movement direction Dt of the target vehicle 30, is also acquired. Therefore, in this embodiment, the movement direction Dt represented by the target information It is compared with the driving direction Ds represented by the lane structure information Is. This adds estimated information Ie about unrecognized markers 900b that define the driving lane 90 on which the target vehicle 30 is traveling, whose movement direction Dt matches the driving direction Ds, to the marker information Im, thereby improving the accuracy of the identified host lane 90a. This makes it possible to provide reliability to the effect of ensuring the output accuracy of lane identification information Ii that identifies the host lane 90a.

[0060] In this embodiment, lane structure information Is, including the lane number Ns of the travel lane 90 on the travel road 9 on which the host vehicle 2 is traveling, is acquired from a memory 10 in which the lane structure information Is is stored in the host vehicle 2. According to this embodiment, the number of parallel lanes Nme of the travel lanes 90 between each lane marker 900 recognized from the marker information Im to which the estimated information Ie of the unrecognized marker 900b is added is compared with the lane number Ns represented by the lane structure information Is. This ensures the accuracy of the identified host lane 90a by also confirming that the movement direction Dt matches the driving direction Ds for the marker information Im to which the estimated information Ie of the unrecognized marker 900b is added and in which the parallel number Nme matches the lane number Ns. This improves the reliability of the effect of ensuring the output accuracy of the lane identification information Ii that identifies the host lane 90a.

[0061] In this embodiment, attention is paid to the difference between the lane width Wla between the lane markers 900 that define the host lane 90a on both sides of the host vehicle 2, and the lane width Wl between each lane marker 900 represented by the marker information Im. Specifically, if the difference between the lane widths Wla and Wl is outside the allowable range, the recognition information of the lane marker 900af, which is located farther away from the host lane 90a than the lane marker 90a on both sides that is outside the allowable range, is excluded from the marker information Im. This prevents a situation in which the erroneous recognition of a lane marker 900 affects the identification of the host lane 90a from the marker information Im. Therefore, it is possible to prevent a decrease in the output accuracy of the lane identification information Ii that identifies the host lane 90a due to the erroneous recognition of the lane marker 900.

[0062] (Other embodiments) Although one embodiment has been described above, the present disclosure should not be construed as being limited to the embodiment described above, and can be applied to various embodiments within the scope that does not deviate from the gist of the present disclosure.

[0063] In a modified example, the dedicated computer constituting the processing system 1 may have at least one of a digital circuit and an analog circuit as a processor. Here, the digital circuit is at least one of the following: an application specific integrated circuit (ASIC), a field programmable gate array (FPGA), a system on a chip (SOC), a programmable gate array (PGA), and a complex programmable logic device (CPLD). Such a digital circuit may also have a memory that stores a program.

[0064] In the modified example of S40, the extraction process and the exclusion process of the misidentification information Imm may be omitted. In the modified example of S60, the process of checking the parallel number Nme against the number of lanes Ns may be omitted. In the modified example of S60, the process of checking the movement direction Dt against the running direction Ds may be omitted.

[0065] In a modified example, the operator who manually drives and operates the host vehicle 2 to which the processing system 1 is applied may be a remote operator who remotely controls the driving of the host vehicle 2 from an external center. In a modified example, the processing system 1 may be configured to be capable of realizing only automated driving tasks, without any manual driving assistance tasks that assist the operator in manual driving operations. [Explanation of symbols]

[0066] 1: Processing system, 2: Host vehicle, 9: Travel path, 10: Memory, 12: Processor, 30: Target vehicle, 90: Travel lane, 90a: Host lane, 900: Lane marker, 900b: Unrecognized marker, Ds: Travel direction, Dt: Movement direction, Ie: Estimated information, Ii: Lane identification information, Im: Marker information, Is: Lane structure information, It: Target information, Nme: Number of parallel paths, Ns: Number of lanes, Wl, Wla: Lane width

Claims

1. A processing system having a processor (12) for performing driving-related processing related to driving of a host vehicle (2) traveling on a road (9) having a plurality of parallel driving lanes (90), The processor: Acquiring marker information (Im) of lane markers (900) that define each of the driving lanes on the road on which the host vehicle is traveling, recognized by sensing from the host vehicle; Acquiring target information (It) of a target vehicle (30) traveling in any one of the travel lanes on the travel road on which the host vehicle is traveling, recognized by sensing from the host vehicle; acquiring estimated information (Ie) that estimates an unrecognized marker (900b) that is unrecognized in the marker information as the lane marker that defines the driving lane in which the target vehicle represented by the target information is traveling; and identifying a host lane (90a), which is the driving lane in which the host vehicle is traveling, from the marker information to which the estimated information is added, and outputting lane identification information (Ii).

2. The acquisition of the estimated information includes: The processing system according to claim 1 , further comprising: acquiring the estimated information that estimates the unrecognized marker on the opposite side of the host lane across the target vehicle represented by the target information.

3. The processor: The system is further configured to acquire lane structure information (Is) including a driving direction (Ds) of the driving lane on the driving road on which the host vehicle is traveling from a storage medium (10) in the host vehicle, the lane structure information including the driving direction (Ds), The acquisition of the target information includes: acquiring the target information including a direction of movement (Dt) of the target vehicle; The output of the lane identification information is Comparing the travel direction represented by the lane structure information with the movement direction represented by the target information; and identifying the host lane from the marker information to which the estimated information of the unrecognized marker is added, the host lane defining the driving lane in which the target vehicle, whose movement direction matches the driving direction, is traveling.

4. The acquisition of the lane structure information includes: acquiring, from the storage medium, the lane structure information including the number of lanes (Ns) of the driving lanes on the driving road on which the host vehicle is traveling; The output of the lane identification information is comparing the number of lanes represented by the lane structure information with the number of parallel driving lanes (Nme) between each of the lane markers recognized from the marker information to which the estimated information of the unrecognized markers has been added; The processing system according to claim 3 , further comprising: identifying the host lane from the marker information to which the estimated information of the unrecognized marker is added and to which the parallel number matches the number of lanes.

5. The acquisition of the marker information includes: The processing system according to claim 1 or 2, further comprising: excluding from the marker information, when the difference between the lane width (Wla) between the lane markers that define the host lane on both sides in which the host vehicle is traveling and the lane width (Wl) between each of the lane markers represented by the marker information is outside the allowable range, the recognition information of the lane marker on the side that is farther away than the host lane, of the lane markers on both sides that are outside the allowable range.

6. A processing method executed by a processor (12) to perform driving-related processing related to the driving of a host vehicle (2) traveling on a road (9) having multiple parallel driving lanes (90), comprising: Acquiring marker information (Im) of lane markers (900) that define each of the driving lanes on the road on which the host vehicle is traveling, recognized by sensing from the host vehicle; Acquiring target information (It) of a target vehicle (30) traveling in any one of the travel lanes on the travel road on which the host vehicle is traveling, recognized by sensing from the host vehicle; acquiring estimated information (Ie) that estimates an unrecognized marker (900b) that is unrecognized in the marker information as the lane marker that defines the driving lane in which the target vehicle represented by the target information is traveling; and identifying a host lane (90a), which is the driving lane in which the host vehicle is traveling, from the marker information to which the estimated information is added, and outputting lane identification information (Ii).

7. A processing program stored in a storage medium (10) for performing driving-related processing related to the driving of a host vehicle (2) traveling on a road (9) having a plurality of parallel driving lanes (90), the processing program including instructions to be executed by a processor (12) that performs the driving-related processing, Acquiring marker information (Im) of lane markers (900) that define each of the driving lanes on the road on which the host vehicle is traveling, recognized by sensing from the host vehicle; Acquiring target information (It) of a target vehicle (30) traveling in any one of the travel lanes on the travel road on which the host vehicle is traveling, recognized by sensing from the host vehicle; acquiring estimated information (Ie) that estimates an unrecognized marker (900b) that is unrecognized in the marker information as the lane marker that defines the driving lane in which the target vehicle represented by the target information is traveling; A processing program including the instructions for executing the following: identifying a host lane (90a), which is the driving lane in which the host vehicle is traveling, from the marker information to which the estimated information is added, and outputting lane identification information (Ii).

Images