Mobile object control device, mobile object control method, and program

Abstract

To avoid a collision with a second moving body and further avoid a collision with a third moving body in consideration of movement of the third moving body traveling in a direction opposite to a traveling direction of a first moving body even when the second moving body crossing a road suddenly enters in front of the first moving body under control.SOLUTION: The processor is configured to calculate a first time until a second moving object crossing a road on which a first moving object is present collides with the first moving object, calculate a second time until a third moving object traveling in a direction opposite to a traveling direction of the first moving object collides with the first moving object, determine a target position for avoiding the second moving object and the third moving object based on at least the first time and the second time, and move the first moving object toward the target position.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a mobile object control device, a mobile object control method, and a program. [Background technology]

[0002] In recent years, efforts to provide access to sustainable transport systems that take into consideration vulnerable transport participants have become more active. To achieve this, we are focusing on research and development into preventive safety technologies to further improve road safety and convenience.

[0003] Meanwhile, in preventive safety technology, there are known technologies for avoiding contact with other vehicles attempting to cross a road (hereinafter referred to as crossing vehicles) and for avoiding collision with oncoming vehicles (see, for example, Patent Documents 1 and 2). [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Japanese Patent Application Laid-Open No. 2015-170233 [Patent Document 2] Japanese Patent Application Laid-Open No. 2015-123929 Summary of the Invention [Problem to be solved by the invention]

[0005] However, in the conventional technology, when avoiding a collision with a crossing vehicle, the presence of an oncoming vehicle cannot be taken into consideration, and as a result, there is a problem that even if a crossing vehicle can be avoided, the oncoming vehicle cannot be avoided, or even if an oncoming vehicle can be avoided, the crossing vehicle cannot be avoided. Furthermore, such a problem is not limited to vehicles, but is common to other moving bodies (mobility).

[0006] In order to solve the above-mentioned problems, the present application aims to avoid a collision with a second moving body (e.g., a crossing vehicle) attempting to cross a road, even if the second moving body suddenly moves in front of a first moving body under control, while taking into consideration the movement of a third moving body (e.g., an oncoming vehicle) traveling in a direction opposite to the traveling direction of the first moving body, and also to avoid a collision with the third moving body, thereby contributing to the development of a sustainable transportation system. [Means for solving the problem]

[0007] A mobile object control device, a mobile object control method, and a program according to the present invention employ the following configurations.

[0008] A first aspect of the present invention is a mobile body control device comprising: a first calculation unit that calculates a first time remaining until a collision occurs between a second moving body crossing a road on which a first moving body is located and the first moving body; a second calculation unit that calculates a second time remaining until a collision occurs between a third moving body traveling in the opposite direction to the traveling direction of the first moving body and the third moving body that may collide by avoiding the second moving body; a determination unit that determines a target position for avoiding the second moving body and the third moving body based on at least the first time and the second time; and a driving control unit that moves the first moving body toward the target position.

[0009] In the second aspect, in the first aspect, the first calculation unit calculates the first time for each of a plurality of search points set on the route along which the second moving body is traveling, and the determination unit determines one of the plurality of search points as the target position based on the first time calculated for each of the plurality of search points.

[0010] A third aspect is that, in the first or second aspect, the second calculation unit calculates the second time for each of a plurality of search points set on the route along which the second moving body is traveling, and the determination unit determines one of the plurality of search points as the target position based on the second time calculated for each of the plurality of search points.

[0011] A fourth aspect is the first or second aspect, further comprising a third calculation unit that calculates a third time that is left as a margin for the first moving body to reach the boundary from the target position based on the distance from the target position to the boundary of the road, and the determination unit determines the target position based on the first time, the second time, and the third time.

[0012] The fifth aspect is the fourth aspect, wherein the third calculation unit calculates the third time for each of a plurality of search points set on the route along which the second moving body is traveling, and the determination unit determines one of the plurality of search points as the target position based on the third time calculated for each of the plurality of search points.

[0013] A sixth aspect is the fourth aspect, wherein the determination unit determines the target position based on maximizing an evaluation function that includes the first time, the second time, and the third time as explanatory variables.

[0014] The seventh aspect is the sixth aspect, wherein the determination unit determines some or all of the weighting coefficients for the first time, the second time, and the third time included as the explanatory variables in the evaluation function depending on the environment surrounding the first moving body.

[0015] The eighth aspect is the seventh aspect, wherein the determination unit reduces the weighting coefficient of the third time compared to the weighting coefficients of the first time and / or the second time when there is no obstacle outside the boundary that obstructs the travel of the first moving body.

[0016] The ninth aspect is the seventh aspect, wherein the determination unit increases the weighting coefficient of the third time compared to the weighting coefficient of the first time and / or the second time when there is an obstacle outside the boundary that obstructs the travel of the first moving body.

[0017] In a tenth aspect, in the fourth aspect, when the third time is equal to or greater than a predetermined time, the driving control unit moves the first moving body toward the target position, then decelerates and stops the first moving body, and when the third time is less than the predetermined time, after moving the first moving body toward the target position, causes the first moving body to return toward the lane on which the first moving body was traveling before moving the first moving body toward the target position.

[0018] In an eleventh aspect, in the first or second aspect, a generation unit is further provided that generates an ideal route, which is a route from the current position of the first moving body to the target position, and the driving control unit moves the first moving body toward the target position so that the first moving body follows the ideal route based on the attitude and position of the first moving body relative to the ideal route.

[0019] A twelfth aspect is a mobile body control method using a computer, which includes calculating a first time remaining until a first moving body collides with a second moving body crossing a road on which the first moving body is located; calculating a second time remaining until a third moving body traveling in the opposite direction to the traveling direction of the first moving body and which may collide with the first moving body by avoiding the second moving body; determining a target position for avoiding the second moving body and the third moving body based on at least the first time and the second time; and moving the first moving body toward the target position.

[0020] A thirteenth aspect is a program to be executed by a computer, the program including: calculating a first time remaining as a margin of error before a first moving body collides with a second moving body crossing a road on which the first moving body is located; calculating a second time remaining as a margin of error before a first moving body collides with a third moving body traveling in the opposite direction to the direction of travel of the first moving body and which may collide with the first moving body by avoiding the second moving body; determining a target position for avoiding the second moving body and the third moving body based on at least the first time and the second time; and moving the first moving body toward the target position. [Effects of the Invention]

[0021] According to any of the above aspects, even if a second moving body (e.g., a crossing vehicle) attempting to cross a road suddenly moves in front of a first moving body under control, the system aims to avoid a collision with the second moving body while also taking into account the movement of a third moving body (e.g., an oncoming vehicle) traveling in a direction opposite to the direction of travel of the first moving body, and also to avoid a collision with the third moving body. [Brief explanation of the drawings]

[0022] [Figure 1] 1 is a configuration diagram of a mobile object control system 1 that uses an automatic driving control device 100 according to the present embodiment. [Figure 2] 3 is a flowchart showing an example of a series of processing steps performed by the automatic driving control device 100 according to the present embodiment. [Figure 3] FIG. 1 is a diagram illustrating an example of a scene in which a crossing vehicle Mcross and an oncoming vehicle Moncome are present ahead of a host vehicle Mown. [Figure 4] FIG. 2 is a diagram for explaining a method for setting a plurality of search points P. [Figure 5] FIG. 10 is a diagram for explaining a method for calculating a lateral time margin. [Figure 6] FIG. 10 is a diagram for explaining a method for calculating a vertical time margin. [Figure 7]FIG. 10 is a diagram for explaining a method for calculating a deviation time margin. [Figure 8] 1 is a diagram illustrating an example of a scene in which an obstacle OBS that obstructs the travel of the host vehicle Mown is present outside the road boundary. [Figure 9] FIG. 2 is a diagram for explaining a method for making the vehicle Mown follow an ideal route. [Figure 10] FIG. 10 is a diagram illustrating an example of a scene in which the host vehicle Mown is returned to the original lane. DETAILED DESCRIPTION OF THE INVENTION

[0023] Hereinafter, with reference to the drawings, embodiments of a mobile object control device, a mobile object control method, and a program of the present invention will be described. The mobile object control device of the embodiment is applied to, for example, an autonomous vehicle. Autonomous driving means, for example, controlling one or both of the vehicle's speed and steering to control the driving of the vehicle. The above-mentioned vehicle driving control includes various driving controls such as an Adaptive Cruise Control System (ACC), a Traffic Jam Pilot (TJP), an Auto Lane Changing System (ALC), a Collision Mitigation Brake System (CMBS), and a Lane Keeping Assistance System (LKAS). The driving of an autonomous vehicle may be controlled by manual driving by an occupant (driver).

[0024] [Overall configuration] 1 is a configuration diagram of a mobile object control system 1 that uses an automatic driving control device 100 according to this embodiment. A mobile object on which the mobile object control system 1 is installed is typically an automobile.

[0025] An automobile is, for example, a two-, three-, or four-wheeled vehicle, and its drive source is an internal combustion engine such as a diesel engine or a gasoline engine, an electric motor, or a combination of these. The electric motor operates using electric power generated by a generator connected to the internal combustion engine, or discharged electric power from a secondary battery or a fuel cell.

[0026] The mobile body on which the mobile body control system 1 is mounted is not limited to an automobile, but may be any vehicle-type mobile body that runs by an electric motor driven by power supplied from a battery, such as an electrically assisted bicycle. Furthermore, the mobile body on which the mobile body control system 1 is mounted is not limited to a vehicle-type mobile body, but may be other electric mobility such as a mobile robot. Hereinafter, as an example, the mobile body on which the mobile body control system 1 is mounted will be described as an automobile, and the automobile on which the mobile body control system 1 is mounted will be referred to as "host vehicle M". own " will be explained. own is an example of a "first moving body."

[0027] The mobile object control system 1 includes, for example, a camera 10, a radar device 12, a LIDAR (Light Detection and Ranging) 14, an object recognition device 16, a communication device 20, an HMI (Human Machine Interface) 30, a vehicle sensor 40, a navigation device 50, an MPU (Map Positioning Unit) 60, a driving operator 80, a driver monitor camera 90, an automatic driving control device 100, a driving force output device 200, a braking device 210, and a steering device 220. These devices and equipment are connected to each other via multiple communication lines such as a CAN (Controller Area Network) communication line, serial communication lines, a wireless communication network, etc. The configuration shown in FIG. 1 is merely an example, and some of the configuration may be omitted, or other configurations may be added. The automatic driving control device 100 is an example of a "mobile object control device."

[0028] The camera 10 is a digital camera that uses a solid-state image sensor such as a CCD (Charge Coupled Device) or a CMOS (Complementary Metal Oxide Semiconductor). own For example, the vehicle M ownWhen capturing an image of the area ahead of the vehicle M, the camera 10 is attached to the top of the front windshield or the back of the rearview mirror. own When capturing an image of the rear of the vehicle M, the camera 10 is attached to the upper part of the rear windshield, etc. own When capturing an image of the right or left side of the vehicle M, the camera 10 is attached to the right or left side of the vehicle body or door mirror. own The camera 10 may be a stereo camera.

[0029] The radar device 12 detects the position of the host vehicle M own The radar device 12 radiates radio waves such as millimeter waves to the vicinity of the vehicle M and detects radio waves reflected by the object (reflected waves) to detect at least the position (distance and direction) of the object. own The radar device 12 may detect the position and velocity of an object by a frequency modulated continuous wave (FM-CW) method.

[0030] LIDAR14 is the vehicle M own The LIDAR 14 irradiates light around the subject vehicle M and measures the scattered light of the irradiated light. The LIDAR 14 detects the distance to the subject vehicle M based on the time from light emission to light reception. The irradiated light may be, for example, a pulsed laser beam. The LIDAR 14 detects the distance to the subject vehicle M based on the time from light emission to light reception. own It can be attached at any point.

[0031] The object recognition device 16 performs sensor fusion processing on the detection results from some or all of the camera 10, radar device 12, and LIDAR 14 to recognize the position, type, speed, etc. of the object. The object recognition device 16 outputs the recognition results to the autonomous driving control device 100. Alternatively, the object recognition device 16 may output the detection results from the camera 10, radar device 12, and LIDAR 14 directly to the autonomous driving control device 100. In this case, the object recognition device 16 may be omitted from the mobile object control system 1.

[0032] The communication device 20 communicates with the vehicle M using, for example, a cellular network, a Wi-Fi network, Bluetooth (registered trademark), DSRC (Dedicated Short Range Communication), etc. own The vehicle communicates with other vehicles in the vicinity, or communicates with various server devices via a wireless base station.

[0033] HMI30 is the vehicle M own The HMI 30 presents various information to the occupants (including the driver) of the vehicle and accepts input operations by the occupants. The HMI 30 may include, for example, a display, a speaker, a buzzer, a touch panel, a microphone, switches, keys, and the like.

[0034] The vehicle sensor 40 detects the vehicle M own a vehicle speed sensor for detecting the speed of the vehicle, an acceleration sensor for detecting the acceleration, a yaw rate sensor for detecting the angular velocity around the vertical axis, and own This includes a direction sensor that detects the direction of the

[0035] The navigation device 50 includes, for example, a GNSS (Global Navigation Satellite System) receiver 51, a navigation HMI 52, and a route determination unit 53. The navigation device 50 stores first map information 54 in a storage device such as an HDD (Hard Disk Drive) or a flash memory.

[0036] The GNSS receiver 51 detects the location of the vehicle M based on signals received from the GNSS satellites. own Identify the location of the vehicle M own The position may be determined or supplemented by an INS (Inertial Navigation System) that uses the output of the vehicle sensor 40.

[0037] The navigation HMI 52 includes a display device, a speaker, a touch panel, keys, etc. The navigation HMI 52 may be partially or entirely common with the HMI 30 described above. For example, the occupant may input information about the vehicle M to the HMI 30. ownInstead of or in addition to inputting the destination of the vehicle M own You may also enter your destination.

[0038] The route determination unit 53 determines, for example, the route of the vehicle M identified by the GNSS receiver 51. own The route from the position (or any input position) to the destination input by the occupant using the HM 30 or the navigation HMI 52 (hereinafter referred to as the route on the map) is determined by referring to the first map information 54.

[0039] The first map information 54 is information that represents road shapes using, for example, links indicating roads and nodes connected by the links. The first map information 54 may also include information such as road curvature and POI (Point of Interest) information. The route on the map is output to the MPU 60.

[0040] The navigation device 50 may provide route guidance using the navigation HMI 52 based on the route on the map. The navigation device 50 may be realized, for example, by the functions of a terminal device such as a smartphone or tablet device carried by the occupant. The navigation device 50 may transmit the current position and destination to a navigation server via the communication device 20 and obtain a route equivalent to the route on the map from the navigation server.

[0041] The MPU 60 includes, for example, a recommended lane determination unit 61, and stores second map information 62 in a storage device such as an HDD or flash memory. The recommended lane determination unit 61 divides the route on the map provided by the navigation device 50 into a plurality of blocks (for example, by dividing it into 100 m intervals in the vehicle travel direction), and determines a recommended lane for each block by referring to the second map information 62. The recommended lane determination unit 61 determines which lane from the left the vehicle should travel in. When there is a branch point on the route on the map, the recommended lane determination unit 61 determines the recommended lane for the vehicle M. own However, the recommended lane is determined so that the vehicle can travel along a reasonable route to the branch destination.

[0042] The second map information 62 is map information with higher accuracy than the first map information 54. The second map information 62 includes, for example, information on the center of lanes or information on lane boundaries. The second map information 62 may also include road information, traffic regulation information, address information (address and postal code), facility information, telephone number information, etc. The second map information 62 may be updated as needed by the communication device 20 communicating with other devices.

[0043] The driving operators 80 include, for example, an accelerator pedal, a brake pedal, a shift lever, a steering wheel, a special steering wheel, a joystick, and other operators. The driving operators 80 are equipped with sensors that detect the amount of operation or the presence or absence of operation, and the detection results are output to the automatic driving control device 100 or some or all of the driving force output device 200, the braking device 210, and the steering device 220.

[0044] For example, a sensor attached to the steering wheel (hereinafter referred to as the steering sensor) detects a weak current generated when a passenger touches the steering wheel. The steering sensor may also detect the steering torque generated around the rotation axis (shaft) of the steering wheel. When the steering sensor detects the current or steering torque, it outputs a signal indicating the detection result to the automatic driving control device 100.

[0045] The driver monitor camera 90 is a own The driver monitor camera 90 is a camera that captures images of the interior of the vehicle. The driver monitor camera 90 is a digital camera that uses a solid-state image pickup device such as a CCD or CMOS. own When the image of the interior of the vehicle is captured, the image data is output to the automatic driving control device 100.

[0046] The autonomous driving control device 100 includes, for example, a processing unit 110 and a storage unit 130. The processing unit 110 includes, for example, a recognition unit 112, a first calculation unit 114, a second calculation unit 116, a third calculation unit 118, a determination unit 120, a generation unit 122, and a driving control unit 124.

[0047] These components of the processing unit 110 are realized by, for example, a hardware processor such as a central processing unit (CPU) or a graphics processing unit (GPU) executing a program (software). Some or all of these components may be realized by hardware (including circuitry) such as a large-scale integration (LSI), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a system-on-chip (SOC), or may be realized by a combination of software and hardware. The program may be stored in advance in a storage device (a storage device having a non-transitory storage medium) such as a hard disk drive (HDD) or flash memory of the automatic driving control device 100, or may be stored in a removable storage medium such as a DVD or CD-ROM, and installed in the HDD or flash memory of the automatic driving control device 100 by inserting the storage medium (non-transitory storage medium) into a drive device.

[0048] The storage unit 130 is realized by the various storage devices described above. The storage unit 130 is realized by, for example, a HDD, a flash memory, an EEPROM (Electrically Erasable Programmable Read Only Memory), a ROM (Read Only Memory), or a RAM (Random Access Memory). The storage unit 130 stores, for example, programs that are read and executed by a processor.

[0049] The recognition unit 112 recognizes the vehicle M own The robot recognizes the surrounding situation or environment. An AI (Artificial Intelligence) model may be used for this recognition. As the AI ​​model, for example, a deep neural network such as an encoder, a decoder, or a transformer may be adopted.

[0050] For example, the recognition unit 112 recognizes the position of the vehicle M based on information input from the camera 10, the radar device 12, and the LIDAR 14 via the object recognition device 16. own The objects recognized by the recognition unit 112 include, for example, bicycles, motorcycles, four-wheeled vehicles, pedestrians, road signs, road markings, dividing lines, utility poles, guardrails, fallen objects, and the like.

[0051] The recognition unit 112 also recognizes the position, speed, acceleration, and other conditions of the object. own The position on the relative coordinate system (i.e., the position of the vehicle M) is determined by taking the representative point (such as the center of gravity or the center of the drive shaft) as the origin. own The object's position may be expressed as a representative point such as the center of gravity or a corner of the object, or as a represented area. The "state" of the object may include the object's acceleration, jerk, or "behavioral state" (e.g., whether or not it is changing lanes or about to do so).

[0052] In addition, the recognition unit 112 may, for example, own For example, the recognition unit 112 recognizes the lane in which the vehicle M is traveling (hereinafter referred to as the vehicle lane) and adjacent lanes adjacent to the vehicle lane. own The system recognizes the vehicle's current lane and adjacent lanes by comparing the patterns of road dividing lines around the vehicle with those of surrounding roads.

[0053] The recognition unit 112 may recognize road boundaries (road boundaries) including road shoulders (including guidance strips and breakdown lanes), curbs, medians, guardrails, etc., in addition to road dividing lines, to recognize lanes such as the vehicle's own lane and adjacent lanes. ownThe recognition unit 112 may also take into account the position of the vehicle and the processing results of the INS. The recognition unit 112 may also recognize stop lines, obstacles, red lights, toll booths, and other road phenomena.

[0054] When recognizing the own lane, the recognition unit 112 recognizes the own vehicle M relative to the own lane. own The recognition unit 112 recognizes the relative position and attitude of the vehicle M. own The deviation of the reference point from the center of the lane, and the distance from the center of the lane to the vehicle M own The angle of the vehicle M relative to the lane is defined as the angle of the vehicle M relative to the lane. own Alternatively, the recognition unit 112 may recognize the relative position and attitude of the vehicle M relative to either side edge of the lane (a road dividing line or a road boundary). own The position of the reference point of the vehicle M relative to the lane own It may be recognized as a relative position of

[0055] For example, the recognition unit 112 recognizes the vehicle M own The object existing around the cross may be recognized.

[0056] Crossing vehicle M cross The vehicle M own For example, the vehicle M own When the road on which the vehicle M exists is a priority road and there is another vehicle approaching the priority road or slowing down or stopping before the priority road, the recognition unit 112 recognizes the other vehicle as a crossing vehicle M cross At this time, the recognition unit 112 may recognize the other vehicle as a crossing vehicle M by taking into consideration whether or not the turn signal lamp of the other vehicle is activated. cross Furthermore, the recognition unit 112 may recognize that the road on which the other vehicle is present is a road on which the own vehicle M is present. own When a crossing exists on a road (priority road) and extends to the opposite side, forming a crossroad, other vehicles may be crossed by vehicle M. cross Note that even if the other vehicle does not actually cross the priority road, the recognition unit 112 may recognize it as a crossing vehicle M only if there is a probability that it will cross the priority road. cross Crossing vehicle Mcross is an example of a "second moving body."

[0057] Furthermore, the recognition unit 112 recognizes the vehicle M own As an object existing around the oncome may be recognized.

[0058] Oncoming vehicle M oncome The vehicle M own The vehicle is traveling in the opposite direction to the vehicle M. own Crossing vehicle M cross For example, the recognition unit 112 recognizes other vehicles in the oncoming lane as oncoming vehicles M oncome The velocity vector may be recognized as own The other vehicle in the opposite direction is the oncoming vehicle M oncome Oncoming vehicle M oncome is an example of a "third moving body."

[0059] The first calculation unit 114 calculates the speed of the host vehicle M own Vehicle M is crossing in front of cross and oncoming vehicle M oncome If the recognition unit 112 recognizes that the horizontal time margin exists, the horizontal time margin is calculated.

[0060] The lateral time margin is the time required for crossing vehicles M cross and vehicle M own More specifically, the lateral time margin is the time remaining until a collision occurs between a crossing vehicle M going straight and a crossing vehicle M going straight. cross Collision with own vehicle M own When the vehicle deviates from its lane to avoid the collision, the vehicle M own A crossing vehicle M approaches relatively from the side (i.e., from the lateral direction) of cross and vehicle M own The lateral time margin is the time remaining until the collision. A specific method for calculating the lateral time margin will be described later. The lateral time margin is an example of the "first time."

[0061] The second calculation unit 116 calculates the vehicle M ownVehicle M is crossing in front of cross and oncoming vehicle M oncome If the recognition unit 112 recognizes that the vertical time margin exists, the vertical time margin is calculated.

[0062] The longitudinal time margin is the time between oncoming vehicles M oncome and vehicle M own More specifically, the longitudinal time margin is the time remaining until a collision occurs between a crossing vehicle M and a vehicle traveling straight ahead. cross Collision with own vehicle M own To avoid this, the vehicle deviates from its lane and hits the oncoming vehicle M oncome When the vehicle moves into the oncoming lane where the vehicle M own An oncoming vehicle M approaches relatively from the front (i.e., longitudinal direction) of oncome and vehicle M own The vertical time margin is the time remaining until the collision. A specific method for calculating the vertical time margin will be described later. The vertical time margin is an example of the "second time."

[0063] The third calculation unit 118 calculates the vehicle M own Vehicle M is crossing in front of cross and oncoming vehicle M oncome If the recognition unit 112 recognizes that the deviation time margin exists, the deviation time margin is calculated.

[0064] The deviation time margin is the time when the vehicle M own is the target position P tar From the candidate position (search point P described later), own The time remaining until the target position P reaches the boundary of the road where P exists. tar That is, crossing vehicle M cross and oncoming vehicle M oncome In order to avoid a collision with both the vehicle M own The deviation time margin is an example of the "third time."

[0065] The determination unit 120 determines the crossing vehicle M based on the lateral time margin, the longitudinal time margin, and the deviation time margin. cross and oncoming vehicle Moncome In order to avoid a collision with both the vehicle M own Target position P to move tar Determine.

[0066] The generation unit 122 generates a map of the host vehicle M own The ideal route (also called a target trajectory) for the vehicle M to travel automatically (without relying on the driver's operation) is generated. own The position element that determines the position of the future vehicle M own and a speed element that defines the speed of the

[0067] For example, the generation unit 122 own A plurality of points (trajectory points) that the host vehicle M should reach in order are determined as position elements of the ideal route. The trajectory points are determined by the host vehicle M at predetermined travel distances (for example, several meters). own The predetermined travel distance may be calculated, for example, based on the distance traveled along the ideal route.

[0068] The generation unit 122 determines the target speed v and the target acceleration α for each predetermined sampling time (for example, about a few tenths of a second) as the speed elements of the ideal route. own In this case, the target velocity v and the target acceleration α are determined by the sampling time and the interval between trajectory points.

[0069] For example, when the recognition unit 112 recognizes a lane boundary, the generation unit 122 basically determines the recommended lane determined by the recommended lane determination unit 61 within the recognized lane boundary. own In this case, the generation unit 122 generates an ideal route for the host vehicle M to automatically travel. own Specifically, the generation unit 122 may generate an ideal route so that the crossing vehicle M can respond to the surrounding situation when the crossing vehicle M automatically travels in the recommended lane. cross and oncoming vehicle M oncomeThe target position P tar When the target position P tar Heading towards your vehicle M own An ideal path for moving the object may be generated.

[0070] The driving control unit 124 drives the vehicle M along the ideal route (target trajectory) generated by the generation unit 122 at the scheduled time. own The traveling driving force output device 200, the braking device 210, and the steering device 220 are controlled so that the

[0071] The driving control unit 124 acquires the ideal route from the generation unit 122 and stores it in the memory of the storage unit 130.

[0072] The driving control unit 124 controls one or both of the traveling driving force output device 200 and the braking device 210 based on speed elements (for example, target speed v and target acceleration α) included in the ideal route stored in memory.

[0073] The driving control unit 124 controls the steering device 220 according to positional elements included in the ideal route stored in memory (for example, the curvature κ of the ideal route, the steering displacement amount u according to the position of the trajectory point, etc.).

[0074] The speed control and steering control are realized by, for example, a combination of feedforward control and feedback control. own The system combines feedforward control based on the curvature of the road ahead with feedback control based on the deviation from the ideal path.

[0075] The driving force output device 200 is ownThe driving force output device 200 outputs a driving force (torque) for the vehicle to travel to the driving wheels. The driving force output device 200 includes, for example, a combination of an internal combustion engine, an electric motor, a transmission, etc., and a power ECU (Electronic Control Unit) that controls these. The power ECU controls the above components according to information input from the driving control unit 124 or information input from the driving operator 80.

[0076] Brake device 210 includes, for example, a brake caliper, a cylinder that transmits hydraulic pressure to the brake caliper, an electric motor that generates hydraulic pressure in the cylinder, and a brake ECU. The brake ECU controls the electric motor according to information input from the driving control unit 124 or information input from the driving operation device 80, so that a brake torque corresponding to the braking operation is output to each wheel. Brake device 210 may include a backup mechanism that transmits hydraulic pressure generated by operation of a brake pedal included in the driving operation device 80 to the cylinder via a master cylinder. Note that brake device 210 is not limited to the configuration described above, and may also be an electronically controlled hydraulic brake device that controls an actuator according to information input from the driving control unit 124 to transmit hydraulic pressure from a master cylinder to the cylinder.

[0077] The steering device 220 includes, for example, a steering ECU and an electric motor. The electric motor applies a force to a rack and pinion mechanism to change the direction of the steered wheels. The steering ECU drives the electric motor in accordance with information input from the driving control unit 124 or information input from the driving operator 80 to change the direction of the steered wheels.

[0078] [Processing flow] Hereinafter, a series of processing flows performed by the automatic driving control device 100 according to this embodiment will be described using flowcharts. Fig. 2 is a flowchart showing an example of a series of processing flows performed by the automatic driving control device 100 according to this embodiment. The processing of this flowchart is executed, for example, when an emergency avoidance condition is satisfied.

[0079] The emergency avoidance conditions include, for example, (1) the vehicle M own Vehicle M is crossing in front of cross and oncoming vehicle M oncome (2) the presence of a crossing vehicle M cross and oncoming vehicle M oncome The TTC (Time To Collision) for the collision is 2.0 seconds or more.

[0080] First, the recognition unit 112 recognizes a crossing vehicle M cross A plurality of search points P are set on the traveling route of the crossing vehicle M (step S100). cross and oncoming vehicle M oncome The point is to search for a position where a collision with the vehicle can be avoided.

[0081] FIG. 3 shows the vehicle M own Vehicle M is crossing in front of cross and oncoming vehicle M oncome 1 is a diagram showing an example of a scene in which a host vehicle M own is the velocity v own Crossing vehicle M cross is the velocity v own with a velocity v in the direction crossing the cross Oncoming vehicle M oncome is the velocity v own and in the opposite direction with velocity v oncome It is running at.

[0082] FIG. 4 is a diagram for explaining a method for setting a plurality of search points P. For example, cross On the path of travel of vehicle M, cross The velocity v cross A search point P is set in the direction of at a predetermined sampling period.

[0083] Next, the recognition unit 112 recognizes the crossing vehicle M cross Among the multiple search points P set on the travel path of i (Step S102).

[0084] Next, the first calculation unit 114 calculates the selected search point P i to your vehicle M own The horizontal time margin when the vehicle moves is calculated (step S104).

[0085] 5 is a diagram for explaining a method for calculating the lateral time margin. For example, the first calculation unit 114 calculates the lateral time margin according to Equation (1).

[0086]

number

[0087] t in Equation (1) cross_allow is the horizontal time margin, and t cross and t own It is calculated as the difference between t in Equation (1). cross is the crossing vehicle M cross From the current position of i Distance d to cross , crossing vehicle M cross The velocity v cross The time is calculated by dividing the t in formula (1) by own is the vehicle M own From the current position of i Distance d to own The vehicle M own The velocity v own The time is calculated by dividing by

[0088] Next, the second calculation unit 116 calculates the selected search point P i to your vehicle M own The vertical time margin when the object moves is calculated (step S106).

[0089] 6 is a diagram for explaining a method for calculating the vertical time margin. For example, the second calculation unit 116 calculates the vertical time margin according to Equation (2).

[0090]

number

[0091] t in formula (2) oncome_allow is the vertical time margin, and t oncome and t own It is calculated as the difference between t in formula (2). oncome is the oncoming vehicle M oncome The distance d from the current position to the collision point (relay point) Qi oncome the oncoming vehicle M oncome The velocity v oncome The time is calculated by dividing by

[0092] The collision point Qi is the point where the vehicle M own From the current position of i On the route to, an oncoming vehicle M traveling straight on the oncoming lane oncome and search point P i Vehicle M heading towards own In other words, the collision point Qi is the position where the host vehicle M own Search point P seen from the current position of i direction and the oncoming vehicle M oncome This is the position where the direction of travel of the vehicle intersects with that of the vehicle traveling in the oncoming lane.

[0093] t in formula (2) own is the vehicle M own The distance d from the current position to the collision point Qi own The vehicle M own The velocity v own The time is calculated by dividing by

[0094] Next, the third calculation unit 118 calculates the selected search point P i to your vehicle M own The deviation time margin after the movement is calculated (step S108).

[0095] 7 is a diagram for explaining a method for calculating the deviation time margin. For example, the third calculation unit 118 calculates the deviation time margin according to Equation (3).

[0096]

number

[0097] t in Equation (3) courseout_allow is the deviation time margin, and d x v x It can be calculated by dividing by d x is the search point P i is the distance from the road boundary to the x is the search point P i When the vehicle M reaches own The velocity v own The cosine component of (=v own × cosθ). In other words, the deviation time margin t courseout_allow is the vehicle M own is the search point P i After reaching own It is calculated as the time it takes to go off course when moving in a straight line at a constant speed.

[0098] Next, the determination unit 120 determines the lateral time margin t cross_allow , vertical time margin t oncome_allow , and deviation time margin t courseout_allow From the search point P i An evaluation value (also called a score) for each is calculated (step S110).

[0099] For example, the determination unit 120 determines the search point P i The evaluation value may be calculated.

[0100]

number

[0101] As shown in equation (4), the evaluation function J includes the lateral time margin t cross_allow , vertical time margin t oncome_allow , and deviation time margin t courseout_allow is included as an explanatory variable. K in equation (4) is the deviation time margin t courseout_allow In equation (4), the lateral time margin tcross_allow and the vertical time margin t oncome_allow The weighting coefficients are both 1, but are not limited to this. For example, these weighting coefficients are courseout_allow The weighting coefficient K may be any variable.

[0102] For example, the determination unit 120 determines the horizontal time margin t cross_allow , vertical time margin t oncome_allow , and deviation time margin t courseout_allow Some or all of the weighting coefficients are used by the host vehicle M own The time may be determined depending on the surrounding environment.

[0103] For example, if the vehicle M is outside the road boundary, own If there is no obstacle OBS that obstructs the travel of the vehicle, the determination unit 120 determines the lateral time margin t cross_allow and / or longitudinal time margin t oncome_allow Compared with the weighting factor of courseout_allow The weighting coefficient K of the evaluation function J can be reduced. courseout_allow The weight of becomes relatively small, and the horizontal time margin t cross_allow and / or longitudinal time margin t oncome_allow The longer the time, the larger the evaluation value tends to be.

[0104] Vehicle M own Obstacles OBS that obstruct the travel of the vehicle M include, for example, pedestrians, guardrails, gutters, curbs, soundproof walls, etc. own Non-obstacles that do not impede the travel of vehicles include, for example, road dividing lines painted on the road surface as guidance strips or breakdown lanes, and road shoulders paved with resin, earth, wood, gravel, etc.

[0105] In addition, for example, if the vehicle M is outside the road boundary, own If there is an obstacle OBS that obstructs the travel of the vehicle, the determination unit 120 determines the lateral time margin t cross_allow and / or longitudinal time margin t oncome_allow Compared with the weighting factor of courseout_allowThe weighting coefficient K of the deviation time margin t courseout_allow The weight of becomes relatively large, and the deviation time margin t courseout_allow The longer the time, the larger the evaluation value tends to be.

[0106] Figure 8 shows the road boundary where the vehicle M own 1 is a diagram showing an example of a situation where an obstacle OBS that obstructs the travel of the vehicle is present. In the example shown in the figure, a pedestrian is present outside the road boundary. In such a case, among the multiple search points P, the deviation time margin t courseout_allow is a long search point P i In other words, the evaluation value of the host vehicle M own is the search point P i After reaching own The search point P that takes the longest time to go off course when moving in a straight line at a constant speed i The higher the value, the larger the calculated evaluation value.

[0107] Next, the determination unit 120 determines whether the crossing vehicle M cross It is determined whether or not evaluation values ​​have been calculated for all of the search points P set on the travel route (step S112).

[0108] If the evaluation values ​​have not been calculated for all of the plurality of search points P, the determination unit 120 returns the process to S102. i+1 is selected, and the new search point P i+1 An evaluation value is calculated for

[0109] On the other hand, when the evaluation values ​​are calculated for all of the plurality of search points P, the determination unit 120 determines the search point P with the largest evaluation value from among the plurality of search points P. max and select the search point P max target position P tar (step S114).

[0110] Next, the generation unit 122 calculates the target position P tar Heading towards your vehicle M ownAn ideal path for moving the robot is generated (step S116).

[0111] Next, the driving control unit 124 aligns the vehicle M with the ideal route. own While tracking the target position P tar To vehicle M own (step S118).

[0112] Figure 9 shows the ideal route of the vehicle M own In the figure, x represents the width direction (horizontal direction) of the road, and z represents the extension direction (vertical direction) of the road. For example, when the vehicle M own If is a two-wheeled vehicle, the state (position and attitude) of the vehicle is calculated by Equation (5).

[0113]

number

[0114] θ(k) is the position of the vehicle M at a certain trajectory point k. own θ* represents the attitude angle of the host vehicle M own represents the target angle with respect to the z-axis of the host vehicle M own φ(k) represents the velocity of the vehicle M at a certain trajectory point k. own represents the steering angle input. L represents the wheelbase. d represents the distance from the ideal path.

[0115] Under the above preconditions, the driving control unit 124 calculates the steering angle input φ that minimizes the evaluation function J shown in Equation (6), where K is a gain.

[0116]

number

[0117] The first term of the evaluation function J in Equation (6) represents the square of the difference θ*-θ(k+1) between the attitude angle θ(k+1) of the vehicle one step ahead and the target angle θ*. The second term represents the difference between the ideal path and the host vehicle M own represents the square of the difference d(k+2) between the current position and the position two steps ahead. The steering angle φ(k) is calculated by minimizing this evaluation function J, which takes into account vehicle dynamics. In this case, the weight is selected as the difference between the current position and the ideal path multiplied by a constant.

[0118] Next, the driving control unit 124 cross and oncoming vehicle M oncome In other words, the driving control unit 124 determines whether or not the avoidance of the collision with the host vehicle M has been completed (step S120). own is the target position P tar It is determined whether or not

[0119] Crossing vehicle M cross and oncoming vehicle M oncome If the avoidance of the collision with the crossing vehicle M has not been completed, the driving control unit 124 returns the process to S100. cross and oncoming vehicle M oncome During the period until the collision with the crossing vehicle M is avoided, cross and oncoming vehicle M oncome Depending on the change in the position and speed of each point, the lateral time margin t cross_allow , vertical time margin t oncome_allow , and deviation time margin t courseout_allow As a result, the evaluation value of each search point P changes, so the target position P tar is re-determined and the ideal route is re-generated. cross and oncoming vehicle M oncome The ideal path is optimized in real time until collision avoidance is completed.

[0120] Meanwhile, crossing vehicle M cross and oncoming vehicle M oncome When the avoidance of the collision with the target vehicle is completed, the driving control unit 124 determines the deviation time margin t courseout_allowIn other words, the operation control unit 124 determines whether the target position P tar It is determined whether there is sufficient time between reaching the road boundary and reaching the target point.

[0121] Deviation time margin t courseout_allow is equal to or greater than the predetermined time, that is, the target position P tar , and there is sufficient time between reaching the target position P tar to your vehicle M own After moving, the robot is decelerated and stopped (step S124).

[0122] On the other hand, the deviation time margin t courseout_allow is less than the predetermined time, that is, the target position P tar , the driving control unit 124 determines whether the target position P tar to your vehicle M own After moving the vehicle, the vehicle M returns to the original lane. own (Step S126). The original lane is the target position P tar Towards your vehicle M own Before moving the vehicle M own is the lane the vehicle was traveling in. This completes the processing of this flowchart.

[0123] Figure 10 shows the state of the vehicle M in the original lane. own 1 is a diagram showing an example of a scene where the target position P tar , the driving control unit 124 determines whether the vehicle has reached the target position P tar Towards your vehicle M own Before moving the vehicle M own The vehicle M was traveling in the lane own Move.

[0124] According to the embodiment described above, the automatic driving control device 100 detects a crossing vehicle M cross and vehicle M ownThe lateral time margin t is the time remaining before the collision cross_allow (an example of the "first time") is calculated. Furthermore, the automatic driving control device 100 calculates the oncoming vehicle M oncome and vehicle M own The vertical time margin t is the time remaining before the collision oncome_allow (an example of the "second time") is calculated. cross_allow and longitudinal time margin t oncome_allow Based on this, crossing vehicle M cross and oncoming vehicle M oncome Target position P to avoid tar and its target position P tar Towards your vehicle M own Move.

[0125] With this configuration, the crossing vehicle M cross (an example of a "second moving body") is the vehicle M own (an example of a "first moving body") suddenly enters in front of the oncoming vehicle M oncome (an example of a "third moving body"), cross While avoiding a collision with the oncoming vehicle M oncome Collisions with other vehicles can also be avoided.

[0126] (Other embodiments) Other embodiments will be described below. In the above-described embodiment, the crossing vehicle M cross and oncoming vehicles M oncome The presence and status of other vehicles are mainly determined by the vehicle M. own However, the present invention is not limited to this. For example, the presence and status of other vehicles may be recognized by wirelessly communicating with the other vehicles via the communication device 20.

[0127] In the above-described embodiment, the automatic driving control device 100 controls the host vehicle M own The automatic driving control device 100 is then installed in the host vehicle M ownHowever, the present invention is not limited to this. For example, a remote server may control the vehicle M. own In this case, for example, the server at the remote location may remotely control the vehicle M. own Various information is collected from the horizontal time margin t cross_allow , vertical time margin t oncome_allow , deviation time margin t courseout_allow , target position P tar , calculate the ideal path, and transmit these calculation results to the host vehicle M own may be provided to.

[0128] In addition, the vehicle M own The automatic driving control device 100 mounted on the vehicle M own Instead of recognizing the surrounding situation of the vehicle M, a remote server own The surrounding situation recognition result may be received.

[0129] The above describes the form for carrying out the present invention using an embodiment, but the present invention is not limited to such an embodiment, and various modifications and substitutions can be made within the scope that does not deviate from the gist of the present invention. [Explanation of symbols]

[0130] 1...mobile object control system, 10...camera, 12...radar device, 14...finder, 16...object recognition device, 20...communication device, 30...HMI, 40...vehicle sensor, 50...navigation device, 60...MPU, 80...driving operator, 90...driver monitor camera, 100...automatic driving control device, 110...processing unit, 112...recognition unit, 114...first calculation unit, 116...second calculation unit, 118...third calculation unit, 120...determination unit, 122...generation unit, 124...driving control unit, 130...storage unit, M...own vehicle

Claims

1. a first calculation unit that calculates a first time remaining as a margin until a collision between a second moving object crossing a road on which a first moving object is present and the first moving object; a second calculation unit that calculates a second time remaining as a margin until a collision between the first moving body and a third moving body that is traveling in a direction opposite to a traveling direction of the first moving body and that may collide with the third moving body by avoiding the second moving body; a determination unit that determines a target position for avoiding the second moving object and the third moving object based on at least the first time period and the second time period; a driving control unit that moves the first moving body toward the target position; A mobile object control device comprising:

2. the first calculation unit calculates the first time for each of a plurality of search points set on a route along which the second moving object is traveling; the determination unit determines one of the plurality of search points as the target position based on the first time calculated for each of the plurality of search points. The mobile object control device according to claim 1 .

3. the second calculation unit calculates the second time for each of a plurality of search points set on a route along which the second moving object travels; the determination unit determines one of the plurality of search points as the target position based on the second time calculated for each of the plurality of search points. The mobile object control device according to claim 1 or 2.

4. a third calculation unit that calculates a third time period that is left as a margin until the first moving object reaches the boundary from the target position based on a distance from the target position to the boundary of the road, the determination unit determines the target position based on the first time, the second time, and the third time. The mobile object control device according to claim 1 or 2.

5. the third calculation unit calculates the third time for each of a plurality of search points set on a route along which the second moving body is traveling; the determination unit determines one of the plurality of search points as the target position based on the third time calculated for each of the plurality of search points. The mobile object control device according to claim 4.

6. the determination unit determines the target position based on maximization of an evaluation function that includes the first time, the second time, and the third time as explanatory variables. The mobile object control device according to claim 4.

7. the determination unit determines some or all of the weighting coefficients of the first time, the second time, and the third time included as the explanatory variables in the evaluation function in accordance with an environment surrounding the first moving object. The mobile object control device according to claim 6.

8. the determination unit, when there is no obstacle outside the boundary that obstructs the travel of the first moving object, reduces the weighting coefficient of the third time compared to the weighting coefficient of the first time and / or the second time. The mobile object control device according to claim 7.

9. the determination unit, when an obstacle that obstructs travel of the first moving object is present outside the boundary, increases the weighting coefficient of the third time compared to the weighting coefficient of the first time and / or the second time. The mobile object control device according to claim 7.

10. The operation control unit If the third time is equal to or longer than a predetermined time, the first moving body is moved toward the target position, and then the first moving body is decelerated and stopped; if the third time is less than the predetermined time, after moving the first moving body toward the target position, returning the first moving body toward the lane in which the first moving body was traveling before moving the first moving body toward the target position; The mobile object control device according to claim 4.

11. a generating unit that generates an ideal path that is a path from a current position of the first moving body to the target position; the driving control unit moves the first moving body toward the target position so that the first moving body follows the ideal path, based on an attitude and a position of the first moving body with respect to the ideal path; The mobile object control device according to claim 1 or 2.

12. A mobile object control method using a computer, comprising: calculating a first time remaining as a margin of time until a collision occurs between the first moving body and a second moving body crossing a road on which the first moving body is located; calculating a second time remaining as a margin until the first moving body collides with a third moving body that is traveling in the opposite direction to the traveling direction of the first moving body and that may collide with the third moving body by avoiding the second moving body; determining a target position for avoiding the second moving body and the third moving body based on at least the first time and the second time; moving the first moving body toward the target position; A mobile object control method comprising:

13. A program to be executed by a computer, calculating a first time remaining as a margin of time until a collision occurs between the first moving body and a second moving body crossing a road on which the first moving body is located; calculating a second time remaining as a margin until the first moving body collides with a third moving body that is traveling in the opposite direction to the traveling direction of the first moving body and that may collide with the third moving body by avoiding the second moving body; determining a target position for avoiding the second moving body and the third moving body based on at least the first time and the second time; moving the first moving body toward the target position; Programs including.

Images