Vehicle control devices
The vehicle control device enhances trajectory prediction and collision determination by using high-precision map data and real-world object information to correct trajectory predictions, ensuring accurate and timely collision avoidance.
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- DAIHATSU MOTOR CO LTD
- Filing Date
- 2022-04-08
- Publication Date
- 2026-07-02
AI Technical Summary
Conventional vehicle control devices inaccurately predict the trajectory of moving objects due to delayed predictions or widened collision prediction ranges, leading to reduced accuracy in determining collision possibilities, especially when objects deviate from expected paths or speed changes.
A vehicle control device that predicts and corrects the trajectory of moving objects using high-precision map data and real-world object information, incorporating trajectory prediction and correction units to determine collision possibilities with high accuracy, and adjusts collision prevention functions based on these predictions.
Accurately predicts the trajectory of moving objects and determines collision possibilities with high precision, enabling early and effective collision avoidance through adjusted collision prevention operations.
Smart Images
Figure 0007883875000001 
Figure 0007883875000002 
Figure 0007883875000003
Abstract
Description
Technical Field
[0001] The present invention relates to a vehicle control device that can accurately predict the trajectory of a moving object target and accurately determine the possibility of a collision.
Background Art
[0002] Conventional vehicle control devices detect the respective moving speeds and moving directions of a vehicle and a moving object target, predict the possibility of a collision between the vehicle and the moving object target based on the moving speeds and moving directions, and output a collision warning to alert the driver of the vehicle and activate an automatic brake when there is a possibility of a collision between the vehicle and the moving object target (see Patent Document 1).
Prior Art Documents
Patent Documents
[0003]
Patent Document 1
Summary of the Invention
Problems to be Solved by the Invention
[0004] By the way, in a conventional vehicle control device, the movement trajectory (orbit) of a moving object target is predicted using the movement vector (moving speed and moving direction) of the moving object target based on the speed, acceleration, relative position with respect to the host vehicle, etc. of the moving object target, and the possibility of a collision with the host vehicle is determined based on this prediction result.
[0005] For this reason, in a conventional vehicle control device, for example, even though a moving object target trying to turn right is indicated by a direction indicator or a right turn indication is marked on the lane on the road, the moving object target has to be determined to go straight, so after the moving object target actually turns right, it is determined that there is a possibility of a collision, the prediction of the movement trajectory of the moving object target is delayed, or it is necessary to widen the collision prediction range including a right turn for prediction, so the prediction accuracy has to be lowered.
[0006] Furthermore, even though stop lines are marked on the road, if the prediction is made that the moving target will continue to move at the same speed, the predicted speed will differ, resulting in an inaccurate predicted trajectory for the moving target and inevitably lowering the prediction accuracy.
[0007] The present invention has been made in view of the above, and aims to provide a vehicle control device that can accurately predict the trajectory of a moving target and accurately determine the possibility of a collision. [Means for solving the problem]
[0008] To solve the above-mentioned problems and achieve the objective, the vehicle control device according to the present invention is a vehicle control device mounted on a vehicle that predicts and determines the possibility of collision between the vehicle and a moving object, comprising: a trajectory prediction unit that predicts the trajectory of the moving object including the time change, including real objects present on the actual road, and the trajectory including the time change of the moving object predicted by the trajectory prediction unit At an intersection The aforementioned moving target The markings of the direction indicators installed therein and the position of the moving object within the lane width Based The moving target follows one of the following paths: a straight path, a right-turn path, or a left-turn path. The system includes a prediction correction unit that performs corrections, and a collision prediction unit that determines there is a possibility of collision when the difference between the arrival time of the moving object and the arrival time of the vehicle, up to the point where the vehicle reaches the intersection of the planned route for moving the vehicle to the target location and the trajectory including the time change of the moving object, is less than or equal to a predetermined value.
[0009] Furthermore, the vehicle control device according to the present invention includes a collision prevention function control unit mounted on the vehicle that controls the operation of a collision prevention function that avoids collisions with moving targets or reduces damage caused by collisions, and the collision prevention function control unit changes the reference operation timing of the collision prevention function based on the prediction result corrected by the prediction correction unit.
[0010] Furthermore, in the vehicle control device according to the present invention, the trajectory prediction unit uses high-precision map data to acquire the position and content of real-world objects present on the actual road and predicts the trajectory including the time change of the moving object.
[0011] Furthermore, in the vehicle control device according to the present invention, the trajectory prediction unit uses the data of the captured image to obtain the position and content of real objects present on the actual road and predicts the trajectory including the time change of the moving object. [Effects of the Invention]
[0012] According to the present invention, the trajectory of a moving target can be predicted with high accuracy, and the possibility of a collision can be determined with high accuracy. [Brief explanation of the drawing]
[0013] [Figure 1] Figure 1 is a block diagram showing the control configuration of the vehicle according to this embodiment. [Figure 2] Figure 2 is a functional block diagram showing the configuration of the autonomous driving ECU of the vehicle according to this embodiment. [Figure 3] Figure 3 is an explanatory diagram that explains the trajectory prediction of a moving target based on the behavior of real-world objects and moving targets at an intersection. [Figure 4] Figure 4 is a time chart showing an example of the timing of alarm and automatic braking activation. [Figure 5] Figure 5 is a flowchart showing the collision avoidance function control processing procedure by the safety confirmation unit. [Figure 6] Figure 6 is a functional block diagram showing the configuration of the automatic driving ECU of a vehicle according to a modified example of this embodiment. [Modes for carrying out the invention]
[0014] Hereinafter, embodiments of the vehicle control device according to the present invention will be described in detail with reference to the drawings. In this embodiment, an example is given of a vehicle 1 equipped with an autonomous driving function and equipped with the vehicle control device, but the invention is not limited to this.
[0015] <Overall vehicle configuration> FIG. 1 is a block diagram showing a control configuration of a vehicle according to the present embodiment. The vehicle 1 shown in FIG. 1 is a vehicle equipped with an automatic driving function that enables automatic driving without requiring a user's driving operation. As shown in FIG. 1, the vehicle 1 includes a plurality of ECUs (Electronic Control Units) for controlling each part. Each ECU includes a microcomputer (Micro Controller Unit), and the microcomputer incorporates, for example, a CPU (Central Processing Unit), a non-volatile memory such as a flash memory, and a volatile memory such as a DRAM (Dynamic Random Access Memory).
[0016] Specifically, as shown in FIG. 1, the vehicle 1 includes a drive ECU 11, a steering ECU 12, a brake ECU 13, a meter ECU 14, a body ECU 15, a communication ECU 16, and an automatic driving ECU 31. Each ECU is connected via a bus line 19 so as to be able to communicate with each other. The bus line 19 realizes communication based on a serial communication protocol such as CAN (Controller Area Network). Note that it is not limited to CAN, and other serial communication protocols may be applied.
[0017] In addition, the vehicle 1 includes a LiDAR (Light Detection And Ranging) ECU 32 and a monocular camera ECU 33 connected to the automatic driving ECU 31. Further, the vehicle 1 includes a driving device 21, a steering device 22, a braking device 23, an emergency stop switch 24, a communication device 26, an omnidirectional LiDAR 34, a positioning signal receiving unit 35, a vehicle speed sensor 36, a display device 37, a speaker 38, a LiDAR 42, and a monocular camera 43.
[0018] The drive ECU 11 is an ECU that controls the driving device 21 of the vehicle 1. The driving device 21 includes at least one of an engine or a motor as a driving source. Further, the driving device 21 includes a transmission that shifts and outputs the driving force from the driving source as necessary.
[0019] The steering ECU 12 is an ECU that controls the steering device 22 of the vehicle 1. The steering device 22 is, for example, an electric power steering device that transmits the torque of an electric motor to a steering mechanism. The steering mechanism includes, for example, a rack and pinion type steering gear. When the rack shaft moves in the vehicle width direction by the torque of the electric motor, the left and right steering wheels are configured to steer left and right as the rack shaft moves.
[0020] The brake ECU 13 is an ECU that controls the braking device 23 of the vehicle 1. The braking device 23 may be hydraulic or electric. For example, when the braking device 23 is hydraulic, the braking device 23 includes a brake actuator, and the function of the brake actuator distributes hydraulic pressure to the wheel cylinders of the brakes provided on each wheel, and applies braking force to the wheels including the drive wheels by the hydraulic pressure.
[0021] The meter ECU 14 is an ECU that controls each part of the meter panel of the vehicle 1. The meter panel includes instruments that display the vehicle speed and engine speed, and a display such as a liquid crystal display for displaying various information. Further, the meter ECU 14 is connected to an emergency stop switch 24 that is operated to instruct an emergency stop of the automatic driving.
[0022] The body ECU 15 is an ECU that controls the left and right winkers and door lock motors, etc. that need to operate even when the ignition switch of the vehicle is off.
[0023] The communication ECU 16 is an ECU that controls the communication inside the vehicle 1 and the communication outside the vehicle 1. The communication ECU 16 controls the internal communication via the bus line 19 and controls a communication device 26 that performs communication processing with the outside.
[0024] The autonomous driving ECU 31 is the central ECU for autonomous driving control and is an example of a vehicle control device. The autonomous driving ECU 31 is also equipped with a memory 41. The memory 41 is a non-volatile storage device such as flash memory that stores high-precision map data, which will be described later.
[0025] As shown in Figure 1, the autonomous driving ECU 31 is connected to a lidar ECU 32, a monocular camera ECU 33, an omnidirectional lidar 34, a positioning signal receiver 35, a vehicle speed sensor 36, a display device 37, and a speaker 38.
[0026] The Rider ECU 32 is an ECU that receives and processes detection signals detected by each Rider 42, for example, six Riders 42 (FR, FM, FL, RR, RM, RL), which are connected to it. The Rider ECU 32 is also connected to the Autonomous Driving ECU 31 via, for example, an Ethernet® standard communication cable, and transmits processed data of the detection signals received from the Riders 42 to the Autonomous Driving ECU 31. The Rider 42 is a device that measures the distance and direction to an object by irradiating a search area with laser light, receiving reflected light from an object within the search area, and outputting a detection signal corresponding to the reflected light. The Riders 42 are positioned, for example, at the left, center, and right ends of the front bumper and the left, center, and right ends of the rear bumper of the vehicle 1. Note that the number and placement of the Riders 42 are not limited to those described above, and different numbers and placement locations may be used.
[0027] The monocular camera ECU 33 is connected to the monocular camera 43 and generates image data by receiving and processing the image signals of still images captured by the monocular camera 43. The monocular camera ECU 33 is also connected to the automatic driving ECU 31 via a communication cable, for example, a USB (Universal Serial Bus) standard, and transmits the processed image data received from the monocular camera 43 to the automatic driving ECU 31. The monocular camera 43 is a camera capable of continuously capturing still images of at least one of the search ranges in front of or behind the vehicle 1 at a predetermined frame rate.
[0028] The omnidirectional lidar 34 is a device that emits laser light in all 360 degrees, receives reflected light from objects within the search range, and outputs a detection signal corresponding to that reflected light. The omnidirectional lidar 34 is connected to the automatic driving ECU 31 via, for example, an Ethernet communication cable, and outputs the detection signal to the automatic driving ECU 31. The detection signal detected by the omnidirectional lidar 34 is converted into point cloud data representing the object by the automatic driving ECU 31.
[0029] The positioning signal receiving unit 35 is a receiving device that receives positioning signals from positioning satellites based on GNSS (Global Navigation Satellite System). The positioning signal receiving unit 35 is connected to the automatic driving ECU 31 via, for example, a USB communication cable, and outputs the received positioning signals to the automatic driving ECU 31. The automatic driving ECU 31 detects the location of the vehicle 1 based on the positioning signals received from the positioning signal receiving unit 35. An example of GNSS is GPS (Global Positioning System).
[0030] The vehicle speed sensor 36 is installed, for example, near the wheels of vehicle 1 and generates a vehicle speed pulse indicating the rotational speed or rotational number of the wheel. The vehicle speed sensor 36 is connected to the automatic driving ECU 31 in a communicative manner and outputs the generated vehicle speed pulse to the automatic driving ECU 31. The automatic driving ECU 31 determines the vehicle speed of vehicle 1 by counting the vehicle speed pulses received from the vehicle speed sensor 36.
[0031] The display device 37 is a display device such as an LCD (Liquid Crystal Display) or OELD (Organic Electro-Luminescent Display) installed on the dashboard or other location inside the vehicle 1, which displays map information and object recognition information. The display device 37 is connected to the autonomous driving ECU 31 in a communicative manner.
[0032] Speaker 38 is an acoustic device installed inside the vehicle 1 that outputs sound and voice. Speaker 38 is connected to the automatic driving ECU 31 in a communicative manner.
[0033] <Configuration of the Autonomous Driving ECU> Figure 2 is a functional block diagram showing the configuration of the autonomous driving ECU of the vehicle according to this embodiment. As shown in Figure 2, the autonomous driving ECU 31 includes a position estimation unit 51, an object recognition unit 53, a surrounding information integration unit 54, a route planning unit 55, a safety confirmation unit 56, a vehicle control unit 57, an output control unit 58, and a storage unit 59.
[0034] The position estimation unit 51 is a functional unit that estimates the position (self-position) of vehicle 1 by matching the positioning signal received from the positioning signal receiving unit 35 with high-precision map data, which is data from the high-precision map D stored in the storage unit 59. The high-precision map data is information from a high-precision three-dimensional map and includes information such as road width, lane markings, shoulder lines, stop lines at intersections (signals), right-turn indicators on right-turn lanes and left-turn indicators on left-turn lanes, pedestrian crossings, signs, guardrails, curbs, sidewalks, and traffic lights. The position estimation unit 51 outputs the estimated self-position information to the surrounding information integration unit 54. The position estimation unit 51 may also improve the accuracy of self-position estimation by using detection signals received from the omnidirectional lidar 34. The high-precision map data is also referenced by the safety confirmation unit 56. Furthermore, the high-precision map D is updated in near real-time by the communication device 26 via the communication ECU 16.
[0035] The object recognition unit 53 is a functional unit that recognizes moving objects (obstacles such as vehicles, motorcycles, pedestrians, buildings, and curbs) based on image data generated by the monocular camera ECU 33 and information on the distance to the moving object (obstacles such as vehicles, motorcycles, pedestrians, and buildings) obtained from detection signals received from the omnidirectional lidar 34. The object recognition unit 53 outputs information on the recognized moving object to the surrounding information integration unit 54 and also to the safety confirmation unit 56.
[0036] The surrounding information integration unit 54 is a functional unit that creates surrounding information integration map data by placing (integrating) object targets such as vehicle 1, other two-wheeled vehicles, and pedestrians on the map shown by the high-precision map data stored in the storage unit 59, based on the object recognition results of the object recognition unit 53, the self-position estimation results of the position estimation unit 51, and data received from the rider ECU 32. This surrounding information integration map data includes the location and content of real-world objects on the actual road shown by the high-precision map data. The surrounding information integration unit 54 outputs the created surrounding information integration map data to the route planning unit 55 and the safety confirmation unit 56.
[0037] The route planning unit 55 is a functional unit that plans a route for moving vehicle 1 to a target location, including target speeds at each point along the planned route, based on the surrounding information integration map data created by the surrounding information integration unit 54. The route planning unit 55 creates planned route data including the planned route and target speeds, and outputs it to the safety confirmation unit 56, the vehicle control unit 57, and the output control unit 58.
[0038] The safety confirmation unit 56 is a functional unit that confirms the safety of the vehicle 1 on its planned route based on the surrounding information integration map data created by the surrounding information integration unit 54 and the planned route data created by the route planning unit 55. Based on the predicted trajectory (planned route) of the vehicle 1 including its time changes and the predicted trajectory of the moving object including its time changes, the safety confirmation unit 56 determines the possibility of a collision between the vehicle 1 and the moving object, and generates the timing for the operation of collision prevention functions (warning and automatic braking) to avoid a collision with the moving object or mitigate damage caused by a collision. The warning timing is output to the output control unit 58, and the automatic braking operation timing is output to the vehicle control unit 57. The safety confirmation unit 56 also receives input from the object recognition unit 53, such as the behavior of the turn signals. In addition, the vehicle speed of the vehicle 1 is input to the safety confirmation unit 56 from the vehicle speed sensor 36. Note that, as described above, the location and content of real-world objects may be obtained directly from high-precision map data instead of from the surrounding information integration map data.
[0039] The safety confirmation unit 56 includes a trajectory prediction unit 60, a prediction correction unit 61, a collision prediction unit 62, and an operation timing generation unit 63. The trajectory prediction unit 60 predicts the trajectory of a moving target, including the time change of real objects present on the actual road.
[0040] For example, as shown in Figure 3, when vehicle 1 approaches an intersection, if it recognizes vehicle 101, a moving object, on the opposite lane, it obtains the speed and direction of vehicle 101. If there is a real-world object, such as a right-turn marking on a right-turn lane, and vehicle 101 is on the right-turn lane, it predicts that vehicle 101 will turn right. That is, from the predicted trajectories of vehicle 101—straight trajectory R1, right-turn trajectory R2, and left-turn trajectory R3—it selects trajectory R1. However, at this point, the direction of movement of vehicle 101 is in the direction of trajectory R1, which leads to the prediction of an incorrect trajectory.
[0041] Furthermore, when it is recognized that vehicle 102, which is a moving target, is entering the intersection, the system acquires the vehicle's speed and direction of movement, and predicts that vehicle 102 will come to a stop based on the location and content of real-world objects, such as the stop line LS. In other words, it predicts that vehicle 102 will slow down and come to a stop. In this case, vehicle 1 will travel on the priority road and will not slow down significantly. On the other hand, vehicle 102 will come to a stop, and the time change of track R11 will be slower than when the stop line LS does not exist. Note that if the stop line LS is not recognized, the time change of track R11 will be incorrect.
[0042] The prediction correction unit 61 corrects the trajectory, including the time change of the moving object predicted by the trajectory prediction unit 60, based on the behavior of the moving object. For example, as shown in Figure 3, if the turn signal of vehicle 101 is indicating a right turn, the trajectory of vehicle 101 is predicted to be trajectory R2. In this case, even if there is no right turn marking on the right turn lane, it can be predicted that vehicle 101 will turn right and take the trajectory of trajectory R2. This behavior may also include cases where vehicle 101 is close to the center line, in which case it is predicted that vehicle 101 will turn right on trajectory R2.
[0043] The collision prediction unit 62 predicts the trajectory of vehicle 1, including its time-varying movement, based on the planned route, vehicle speed, and acceleration during the vehicle's autonomous driving. It also obtains the predicted trajectory of the moving object, including its time-varying movement, from the trajectory prediction unit 60 and determines the possibility of a collision between vehicle 1 and the moving object. Specifically, the collision prediction unit 62 determines that there is a possibility of a collision if the difference between the arrival time of the moving object and the arrival time of vehicle 1, up to the intersection of the planned route and the moving object's trajectory, is less than or equal to a predetermined value. Here, the trajectory prediction unit 60 and the prediction correction unit 61 predict the trajectory of the moving object, including its time-varying movement, early and with high accuracy by knowing the behavior of real-world objects and the moving object, thus enabling the possibility of a collision to be determined early and with high accuracy.
[0044] The operating timing generation unit 63 generates the timing for the alarm and automatic braking when the collision prediction unit 62 determines that there is a possibility of a collision. Specifically, the operating timing generation unit 63 first generates the operating timing shown in Figure 4. The operating timing is formed in the order of alarm timing time t1, primary braking timing time t2, and secondary braking timing time t3. If a possibility of collision is predicted at the current time t0, an alarm is issued from time t1, which is time T1 back from the time t10 when the vehicle stops, corresponding to the time to collision (TTC). In addition, the primary brake is activated from time t2, which is time (T2 + T3) back from the time to brake (TTB), and the secondary brake, which is stronger than the primary brake, is activated from time t3. The primary and secondary brakes are a single time, and the automatic braking is activated from time t2. The secondary brake can be further changed to the maximum brake as time progresses, depending on the stopping position.
[0045] Here, the previously generated operating timing was a reference operating timing generated based on the speed and direction of movement of the moving target, the speed and direction of movement of vehicle 1, and the relative distance. However, the operating timing generation unit 63 generates an operating timing that modifies the reference operating timing based on the prediction results corrected by the prediction correction unit 61.
[0046] For example, the warning timing is changed depending on whether vehicle 1 is on a priority road or not. The warning timing is also changed based on the azimuth and lateral position errors from the center of the high-precision map D. Alternatively, the warning timing is changed based on the presence or absence of traffic lights or stop lines. These warning timings are delayed from the normal timing when it is safe. This ensures that the appropriate activation timing is achieved.
[0047] The operating timing generation unit 63 outputs the generated operating timing alarm timing to the collision prevention control unit 65 of the output control unit 58, and outputs the brake timing to the collision prevention control unit 64 of the vehicle control unit 57.
[0048] The output control unit 58 is a functional unit that controls the display on the display device 37 and the audio output of the speaker 38. For example, the output control unit 58 displays the surrounding information integration map data created by the surrounding information integration unit 54, the planned route data created by the route planning unit 55, etc., on the display device 37. Also, when the safety confirmation unit 56 inputs an alarm timing, the output control unit 58, via the collision prevention control unit 65, will, for example, output a warning sound to the speaker 38 indicating the possibility of a collision, or display a warning on the display device 37, or provide both warnings, in order to avoid a collision between the vehicle 1 and the moving object. If only one of the following occurs, the speaker 38 outputs an alarm sound or the display device 37 displays a warning, the user may operate the emergency stop switch 24 accordingly and, although not shown, operate the brake operation unit (brake pedal) and accelerator operation unit (accelerator pedal), etc., to manually avoid a collision between the vehicle 1 and the moving object.
[0049] The vehicle control unit 57 controls the movement of vehicle 1 by outputting commands to the drive ECU 11, steering ECU 12, brake ECU 13, etc., so that vehicle 1 can travel along the planned route while avoiding collisions with moving targets or mitigating damage caused by collisions with moving targets, based on the planned route data created by the route planning unit 55 and the safety confirmation results of vehicle 1 on the planned route by the safety confirmation unit 56. The collision prevention control unit 64 activates the primary brake and secondary brake upon receiving the brake timing generated by the operation timing generation unit 63.
[0050] Furthermore, the safety confirmation unit 56 and the collision prevention control units 64 and 65 function as collision prevention function control units that control the operation of the collision prevention function, which avoids collisions between the vehicle 1 and moving targets or mitigates damage caused by collisions.
[0051] <Collision prevention function control processing> Figure 5 is a flowchart showing the collision prevention function control processing procedure by the safety confirmation unit 56. As shown in Figure 5, first, the safety confirmation unit 56 obtains the position of the moving target based on the recognition result from the object recognition unit 53 (step S101). Then, the safety confirmation unit 56 obtains information on real-world objects from the high-precision map data of the high-precision map (step S102).
[0052] Subsequently, the trajectory prediction unit 60 predicts the trajectory of the moving target, including the time change, along with the position and content of real-world objects (step S103). Furthermore, the prediction correction unit 61 acquires the behavior of the moving target and corrects the trajectory, including the time change of the moving target, predicted by the trajectory prediction unit 60, based on the behavior of the moving target (step S104). Meanwhile, the safety confirmation unit 56 predicts the trajectory of vehicle 1 based on the route plan from the route planning unit 55 and the vehicle speed from the vehicle speed sensor 36 (step S105).
[0053] Subsequently, the collision prediction unit 62 predicts and determines whether or not there is a possibility of collision between the vehicle 1 and the moving target (step S106). If there is no possibility of collision (step S106: No), this process is terminated.
[0054] On the other hand, if there is a possibility of collision (step S106: Yes), the operating timing generation unit 63 generates a reference operating timing for the warning and automatic braking (step S107), and then generates an operating timing with a modified reference operating timing based on the prediction result from the prediction correction unit 61 (step S108). Then, the operating timing generation unit 63 outputs the warning timing of the generated operating timing to the collision prevention control unit 65 as an operation request, and outputs the brake timing of the generated operating timing to the collision prevention control unit 64 as an operation request (step S109), and ends this process. This process is repeated at predetermined intervals.
[0055] <Variation> Figure 6 is a functional block diagram showing the configuration of the automated driving ECU of a vehicle according to a modified example of this embodiment. In this modified example, the safety confirmation unit 56 does not use high-precision map data from the high-precision map D, but instead acquires information on real-world objects on the actual road using the object recognition unit 53. Alternatively, a stereo camera or the like may be used to obtain three-dimensional information instead of the monocular camera 43, and object recognition may be performed based on the obtained images. A LiDAR 42 may also be used in combination, or object recognition may be performed using image information obtained by the LiDAR 42.
[0056] While high-precision map D requires map updates, this modified version directly acquires information on real-world locations, enabling real-time, early, and highly accurate trajectory predictions.
[0057] Incidentally, intersections generally lack white lines and are free spaces, making it difficult to predict the trajectory of moving objects. Furthermore, in order to mitigate false collision detections and failures (delays in the timing of activation) of warnings and automatic braking, it is necessary to narrow the range in which the possibility of collision is judged and to judge the possibility of collision when the relative distance between vehicle 1 and the moving object is close. However, this conversely makes it impossible to properly activate warnings and automatic braking.
[0058] In contrast, this embodiment and its modified versions predict the trajectory of a moving target, including changes over time, early and with high accuracy. This allows for the generation of appropriate warnings and automatic braking timings at an early stage. As a result, false collision detections and failures to activate warnings and automatic braking can be reduced.
[0059] The position estimation unit 51, object recognition unit 53, surrounding information integration unit 54, route planning unit 55, safety confirmation unit 56, vehicle control unit 57, and output control unit 58 described above are implemented, for example, by a program executed by the CPU of the automated driving ECU 31 shown in Figure 1. Some or all of these functional units may be implemented by hardware such as logic circuits.
[0060] Furthermore, the storage unit 59 is a functional unit that stores information such as the high-precision map D. The storage unit 59 is implemented by the memory 41 shown in Figure 1. The storage unit 59 may also be implemented by an external storage device such as an HDD (Hard Disk Drive) or SSD (Solid State Drive).
[0061] Furthermore, the functional units of the autonomous driving ECU 31 shown in Figure 2 are conceptual representations of their functions and are not limited to this configuration. For example, multiple functional units shown as independent functional units in Figure 2 may be configured as a single functional unit. Alternatively, the functions of one functional unit in Figure 2 may be divided into multiple functions and configured as multiple functional units.
[0062] Furthermore, while we have used vehicle 1, which is equipped with an autonomous driving function, as an example, this also applies to vehicles that do not have an autonomous driving function but are equipped with a collision avoidance function using collision avoidance control.
[0063] It should be noted that the configurations illustrated in the embodiments and modifications described above are functional schematics and do not necessarily have to be physically represented as shown. In other words, the forms of distribution and integration of each device and component are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various usage situations. [Explanation of Symbols]
[0064] 1 vehicle 31 Autonomous driving ECU 51 Position estimation part 53 Object recognition section 54 Peripheral Information Integration Department 55 Route Planning Department 56 Safety Confirmation Department 57 Vehicle Control Unit 58 Output control unit 59 Memory section 60 Orbital prediction section 61 Prediction Correction Unit 62 Collision prediction unit 63 Operating Timing Generation Unit 64,65 Collision prevention control unit D High-precision map
Claims
1. A vehicle control device mounted on a vehicle that predicts and determines the possibility of a collision between the vehicle and a moving target, A trajectory prediction unit that predicts the trajectory of the moving target, including the time change, including real-world objects present on actual roads, A prediction correction unit corrects the trajectory of the moving object, including the time change of the moving object predicted by the trajectory prediction unit, to one of three trajectories: a straight trajectory, a right-turn trajectory, or a left-turn trajectory, based on the indication of the direction indicator provided on the moving object at the intersection and the position of the moving object within the lane width. A collision prediction unit determines that there is a possibility of collision when the difference between the arrival time of the moving target and the arrival time of the vehicle, up to the point where the vehicle reaches the intersection of the planned route for moving the vehicle to the target location and the trajectory including the time change of the moving target, is less than or equal to a predetermined value. A vehicle control device comprising:
2. The vehicle is equipped with a collision prevention function control unit that controls the operation of a collision prevention function that avoids collision with the moving target or reduces damage caused by a collision, The vehicle control device according to claim 1, wherein the collision prevention function control unit changes the reference operating timing of the collision prevention function based on the prediction result corrected by the prediction correction unit.
3. The vehicle control device according to claim 1 or 2, wherein the trajectory prediction unit uses high-precision map data to acquire the location and content of real-world objects present on the actual road and predicts the trajectory including the time change of the moving target.
4. The trajectory prediction unit is, Using the image data including the captured intersection, the location and content of road markings, including at least one of a stop line, a right-turn marking on the right-turn lane, and a left-turn marking on the left-turn lane, which are real objects present on the actual road, are obtained. Using the acquired location and content of the road markings, the trajectory of the moving object, including its time change, is predicted. Vehicle control device according to claim 1 or 2.