Obstacle Detection System

Abstract

To more surely detect presence of an obstacle on a road.SOLUTION: An obstacle detection system for detecting an obstacle on a road comprises: a behavior determination unit for determining whether or not each automobile shows avoidance behavior for avoiding the obstacle for each automobile on the road based on behavior data as time series data regarding behavior of each automobile that traveled on the road; and an obstacle determination unit for determining that there is an obstacle on the road when a plurality of automobiles show avoidance behavior within a predetermined time. Thus, it is possible to more surely detect that there is an obstacle on the road.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present invention relates to an obstacle detection system, and more particularly to an obstacle detection system that detects obstacles on a road. [Background technology]

[0002] Conventionally, one such obstacle detection system proposed is one that detects obstacles on the road (see, for example, Patent Document 1). This obstacle detection system determines whether the vehicle is exhibiting the behavior that would occur if it had encountered an obstacle, based on the vehicle's behavior data (behavior information). If the vehicle is exhibiting the behavior that would occur if it had encountered an obstacle, the system detects the presence of an obstacle on the road and transmits this information to other vehicles in the vicinity. This is said to reduce accidents and congestion caused by obstacles. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2008-234044 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned obstacle detection system detects the presence of an obstacle on the road when a vehicle is exhibiting the behavior it would have if it had encountered an obstacle, so there is room for improvement in terms of reliability.

[0005] The main object of the obstacle detection system of the present invention is to more reliably detect the presence of an obstacle on the road. [Means for solving the problem]

[0006] The obstacle detection system of the present invention employs the following means to achieve the above-mentioned main object.

[0007] The obstacle detection system of the present invention comprises: An obstacle detection system that detects obstacles on a road, a behavior determination unit that determines, for each vehicle, whether or not the vehicle has exhibited an avoidance behavior for avoiding the obstacle on the road, based on behavior data that is time-series data regarding the behavior of each vehicle that has traveled on the road; an obstacle determination unit that determines that the obstacle is present on the road when a plurality of the vehicles exhibit the avoidance behavior within a predetermined time; The gist of the project is to provide the following:

[0008] The obstacle detection system of the present invention determines whether each vehicle exhibits avoidance behavior to avoid an obstacle on the road based on behavior data, which is time-series data on the behavior of each vehicle traveling on the road. If multiple vehicles exhibit avoidance behavior within a predetermined time, it determines that an obstacle is present on the road. As a result, the presence of an obstacle on the road can be detected more reliably.

[0009] In the obstacle detection system of the present invention, the behavior data includes the yaw rate of the vehicle and the lighting status of the left and right turn signals or information on the acceleration and deceleration of the vehicle, and the behavior determination unit determines whether the vehicle has made an abrupt turn based on the yaw rate, and when the vehicle has made an abrupt turn, determines that the vehicle has exhibited the avoidance behavior when the left and right turn signals are not lit, or when the left and right turn signals are lit alternately in succession, or when the vehicle accelerates after decelerating. This makes it possible to more reliably determine whether the vehicle has exhibited the avoidance behavior.

[0010] In this case, the behavior determination unit may determine that the vehicle has made an abrupt turn when the absolute value of the difference between adjacent maximum and minimum values ​​of the yaw rate is equal to or greater than a first threshold, the time difference between the adjacent maximum and minimum values ​​is equal to or greater than a second threshold, and the maximum value of the slope between the adjacent maximum and minimum values ​​is equal to or greater than a third threshold. This makes it possible to more reliably determine whether the vehicle has made an abrupt turn.

[0011] In the obstacle detection system of the present invention, the behavior determination unit may determine, for each road section, whether the vehicle has exhibited the avoidance behavior based on the behavior data of each vehicle that has traveled on the road section, and the obstacle determination unit may determine, for each road section, that an obstacle is present on the road section when a plurality of the vehicles have exhibited the avoidance behavior within the predetermined time. In this way, it is possible to properly determine, for each road section, whether an obstacle is present.

[0012] In this case, the behavior determination unit may determine whether the vehicle has exhibited the avoidance behavior when there is no interchange or service area in the road section, or when there is no center of an S-curve in the road section. Vehicles may swerve suddenly near interchanges, service areas, or the centers of S-curves, regardless of the presence or absence of obstacles. Therefore, when there is no interchange or service area in the road section, or when there is no center of an S-curve in the road section, determining whether the vehicle has exhibited the avoidance behavior can more accurately determine whether there is an obstacle. [Brief explanation of the drawings]

[0013] [Figure 1] 1 is a diagram showing an outline of the configuration of an obstacle detection system 10 according to an embodiment of the present invention. [Figure 2] 10 is a flowchart showing an example of an obstacle detection routine executed by the automobile information server 40. [Figure 3]FIG. 2 is an explanatory diagram for explaining an example of a state in which an automobile 20 is avoiding an obstacle in a road section. [Figure 4] FIG. 2 is an explanatory diagram for explaining an example of a state in which an automobile 20 is avoiding an obstacle in a road section. [Figure 5] FIG. 2 is an explanatory diagram for explaining an example of a state in which an automobile 20 is avoiding an obstacle in a road section. DETAILED DESCRIPTION OF THE INVENTION

[0014] Next, a mode for carrying out the present invention will be described using examples. [Example]

[0015] 1 is a diagram showing the outline of the configuration of an obstacle detection system 10 according to one embodiment of the present invention. The obstacle detection system 10 includes a plurality of automobiles 20, an automobile information server 40, and an information terminal device 50.

[0016] Each automobile 20 is configured to run using power from a power source for running such as an engine or a motor, and in addition to the power source for running (not shown), it is equipped with a navigation device (navigation device) 22, a turn signal (directional indicator) 24, and an electronic control unit (hereinafter referred to as "ECU") 26.

[0017] The navigation device 22 sets a planned driving route from the current location of the automobile 20 to the destination based on stored map information, the current location of the automobile 20 from the GPS antenna, and the destination set by the user, and displays the set planned driving route on a display (not shown) to provide route guidance.

[0018] The blinkers 24 are attached to the front, rear, left and right sides of the automobile 20, and are turned on by the driver to indicate the direction to turn right or left or change course.

[0019] The ECU 26 is configured as a well-known microcomputer and includes a CPU, ROM, RAM, flash memory, input / output ports, etc. Signals from various sensors are input to the ECU 26 via input ports. Examples of signals input to the ECU 26 include a vehicle speed V from a vehicle speed sensor 28 that detects the vehicle speed, and a yaw rate Ry from a yaw rate sensor 30 that detects the yaw rate of the automobile 20. Various control signals are output from the ECU 26 via output ports. The ECU 26 exchanges various data with an automobile information server 40 via a DCM (on-board communication device) via wireless communication.

[0020] The automobile information server 40 is installed, for example, in a data center. The automobile information server 40 is configured as a well-known computer and includes a CPU, ROM, RAM, a storage device 42 (e.g., HDD or SSD), input / output ports, and communication ports. The automobile information server 40 exchanges various information with each automobile 20 via wireless communication, and exchanges various information with the information terminal device 50 via wired or wireless communication. The automobile information server 40 stores coordinate information (latitude and longitude information) for each distance post (kilometer post) in the storage device 42. The automobile information server 40 sets road sections as sections obtained by dividing the road into predetermined distances Lref (e.g., 50 m, 100 m, 150 m, etc.) based on the stored coordinate information, and inputs, for each road section, the yaw rate Ry, turn signal 24 illumination information Iwl, and vehicle speed V from each automobile 20 traveling on the road section via wireless communication at predetermined time intervals tref1 (e.g., several hundred msec), and stores them in the memory device 42 as time-series behavior data D.

[0021] The information terminal device 50 is installed, for example, in a facility of a road operator. The information terminal device 50 is configured as a well-known computer and includes a CPU, ROM, RAM, a storage device (for example, an HDD or SSD), an input / output port, a communication port, etc. The information terminal device 50 receives various information from each vehicle 20 and the vehicle information server 40 via wired or wireless communication.

[0022] Next, a description will be given of the operation of the obstacle detection system 10 of the embodiment configured as described above. Figure 2 is a flowchart showing an example of an obstacle detection routine executed by the automobile information server 40. This routine is repeatedly executed for each road section at predetermined intervals tref2 (e.g., every few seconds).

[0023] When this routine is executed, the CPU of the automobile information server 40 determines whether the road section is a similar behavior occurrence section, which is a section where behavior similar to the obstacle avoidance behavior occurs (step S100). A similar behavior occurrence section is a section where the automobile 20 may make a sudden turn of the steering wheel, regardless of the presence or absence of an obstacle, and examples of such a section include a road section where an interchange or a service area is located, and a road section where the center of an S-curve is located.

[0024] If the road section is determined to be a similar behavior occurrence section in step S100, the routine is terminated. If the road section is not a similar behavior occurrence section, behavior data D of the automobile 20 in the road section is input (step S110), and based on the input behavior data D, it is determined whether or not the automobile 20 traveling on the road section made an abrupt turn (step S120). Step S120 makes the determination based on the waveform of the time change of the yaw rate Ry in the road section, which is included in the behavior data D. In step S120, it is determined that the automobile 20 made an abrupt turn of the steering wheel when, in the waveform of the time change of the yaw rate Ry, the absolute value of the difference between adjacent maximum and minimum values ​​is equal to or greater than a first threshold, the time difference between adjacent maximum and minimum values ​​is equal to or greater than a second threshold, and the maximum value of the slope between adjacent maximum and minimum values ​​is equal to or greater than a third threshold. FIGS. 3 to 5 are explanatory diagrams illustrating an example of how the automobile 20 avoids an obstacle on a road section. When the automobile 20 avoids an obstacle on the road, as shown in the figure, it is steered both during the avoidance and when steering back afterwards. Therefore, experiments and analyses have revealed that the waveform of the time change of the yaw rate Ry shows a peak during the avoidance, and then a convex peak in the opposite direction to that during the avoidance when steering back. In step S120, these two peaks are identified using the absolute value of the difference between adjacent maximum and minimum values ​​of the yaw rate Ry, the time difference between adjacent maximum and minimum values, and the maximum value of the slope between adjacent maximum and minimum values. Therefore, the first to third thresholds are set based on the waveform of the time change of the yaw rate Ry when avoiding an obstacle, which is obtained in advance through experiments, analysis, and machine learning.

[0025] If the steering wheel is not turned suddenly in step S120, the routine ends. If the steering wheel is turned suddenly, the routine then determines whether the turn signals 24 were turned on in the road section in question (step S130), whether the turn signals 24 were turned on alternately left and right consecutively (step S140), and whether the vehicle temporarily decelerated and then accelerated relatively quickly (step S150). Steps S130 and S140 are determined based on the turn signal 24 illumination information Iwl included in the behavior data D for the road section in question. Step S150 is determined based on the vehicle speed V included in the behavior data D for the road section in question. When the vehicle 20 avoids an obstacle in the road section, the vehicle 20 may change lanes without turning on the turn signals 24, as shown in FIG. 3; or, as shown in FIG. 4, turn on the right turn signal 24 to move to the right lane and then turn on the left turn signal 24 to return to the left lane, i.e., turn on the turn signals 24 alternately left and right consecutively; or, as shown in FIG. 5, temporarily decelerate and then accelerate. Therefore, steps S130 to S150 are processes for determining whether the behavior of the turn signals 24 and the vehicle speed V indicates the behavior of the automobile 20 when avoiding an obstacle in a road section.

[0026] If the blinkers 24 are turned on in the road section in steps S130 and S140 but are not turned on alternately on the left and right consecutively, and if the vehicle does not accelerate relatively quickly after decelerating in step S150, this routine is terminated.

[0027] If the turn signal 24 is not on in the road section in step S130, if the turn signal 24 is continuously turned on alternately left and right in step S140, or if the vehicle accelerates relatively quickly after decelerating in step S150, it is determined that the vehicle 20 has exhibited an avoidance behavior (step S160).

[0028] Next, it is determined whether or not another vehicle 20 has exhibited avoidance behavior within a predetermined time tref2 (for example, 10 minutes, 15 minutes, 20 minutes, etc.) (step S170). When there is no obstacle on the road, the vehicle 20 may exhibit the behaviors exemplified in FIGS. 3 to 5 even when changing lanes to overtake another vehicle 20 that is traveling. When there is an obstacle on the road, it is considered that multiple vehicles 20 traveling within a certain period of time will exhibit avoidance behavior. Therefore, step S170 is a process for determining whether or not there is an obstacle on the road.

[0029] If the other vehicle 20 does not exhibit evasive behavior within the predetermined time tref2 in step S170, it is determined that there is no obstacle on the road, and this routine is terminated. If the other vehicle 20 exhibits evasive behavior within the predetermined time tref2 in step S170, it is determined that there is an obstacle on the road section (step S180), and this routine is terminated. In this way, by determining that there is an obstacle on the road when multiple vehicles 20 exhibit evasive behavior within the predetermined time tref2, it is possible to more reliably detect the presence of an obstacle on the road.

[0030] If the automobile information server 40 determines in step S180 that an obstacle exists on the road section, it notifies the information terminal device 50 via wired or wireless communication of the location information of the road section and the fact that an obstacle exists. The information terminal device 50 then notifies the received location information of the road section and the fact that an obstacle exists on a display (not shown) or the like. Upon recognizing this notification, an employee of the road operator can proceed to the road section in question and remove the obstacle.

[0031] According to the obstacle detection system 10 of the embodiment described above, it is determined whether or not each vehicle 20 has exhibited avoidance behavior to avoid an obstacle on the road, based on the behavior data D, which is time-series data relating to the behavior of each vehicle 20 traveling on the road. If multiple vehicles 20 have exhibited avoidance behavior within a predetermined time tref2, it is determined that there is an obstacle on the road, thereby making it possible to more reliably detect the presence of an obstacle on the road.

[0032] The behavior data D also includes the yaw rate Ry of the automobile 20 and the lighting status of the left and right turn signals 24 or information on the acceleration and deceleration of the automobile 20, and determines whether or not the automobile 20 has made an abrupt turn in the steering wheel based on the yaw rate Ry of the automobile 20. When an abrupt turn has occurred, it is determined that the automobile 20 has exhibited evasive behavior when the left and right turn signals 24 are not lit, or when the left and right turn signals 24 are lit alternately in succession, or when the automobile 20 accelerates after decelerating, thereby making it possible to more reliably determine whether or not the automobile 20 has exhibited evasive behavior.

[0033] Furthermore, by determining that the automobile 20 has made a sudden turn of the steering wheel when the absolute value of the difference between adjacent maximum and minimum values ​​of the yaw rate Ry is equal to or greater than a first threshold value, the time difference between adjacent maximum and minimum values ​​is equal to or greater than a second threshold value, and the maximum value of the slope between adjacent maximum and minimum values ​​is equal to or greater than a third threshold value, it is possible to more reliably determine whether the automobile 20 has made a sudden turn of the steering wheel.

[0034] Then, for each road section, it is determined whether or not the vehicle 20 has exhibited avoidance behavior based on the behavior data D for each vehicle 20 that has traveled in the road section, and if multiple vehicles 20 have exhibited the avoidance behavior for each road section within a predetermined time tref2, it is determined that the obstacle is present in the road section, thereby making it possible to properly determine whether or not an obstacle is present for each road section.

[0035] In this case, when there is no interchange or service area in the road section, or when there is no center of an S-curve in the road section, it is possible to more accurately determine whether an obstacle is present by determining whether the automobile 20 has exhibited evasive behavior.

[0036] In the obstacle detection system 10 of the embodiment, it is determined in step S100 whether the road section is a similar behavior occurrence section, and if it is not a similar behavior occurrence section, the processing from step S110 onwards is executed. However, if a slight decrease in the accuracy of determining whether an obstacle is present is acceptable, step S100 does not have to be executed.

[0037] In the obstacle detection system 10 of the embodiment, the automobile information server 40 executes each step of the obstacle detection routine illustrated in Fig. 2. However, at least a part of the steps of the obstacle detection routine may be executed by the automobile information server 40 or the information terminal device 50.

[0038] The correspondence between the main elements of the embodiment and the main elements of the invention described in the "Means for Solving the Problem" section will be explained. In the embodiment, the CPU of the automobile information server 40 corresponds to the "behavior determination unit" and the "obstacle determination unit."

[0039] The correspondence between the main elements of the Examples and the main elements of the invention described in the "Means for Solving the Problem" section does not limit the elements of the invention described in the "Means for Solving the Problem" section, since the Examples are examples for specifically explaining the mode for implementing the invention described in the "Means for Solving the Problem" section. In other words, the interpretation of the invention described in the "Means for Solving the Problem" section should be based on the description in that section, and the Examples are merely specific examples of the invention described in the "Means for Solving the Problem" section.

[0040] The above describes the form for carrying out the present invention using examples, but the present invention is not limited to these examples in any way, and it goes without saying that the present invention can be carried out in various forms within the scope that does not deviate from the gist of the present invention. [Industrial Applicability]

[0041] The present invention can be used in the obstacle detection system manufacturing industry and the like. [Explanation of symbols]

[0042] 10 Obstacle detection system, 20 Automobile, 22 Navigation device (navigation device), 24 Turn signal, 26 Electronic control unit (ECU), 28 Vehicle speed sensor, 30 Yaw rate sensor, 40 Automobile information server, 42 Storage device, 50 Information terminal device.

Claims

1. An obstacle detection system that detects obstacles on a road, a behavior determination unit that determines, for each vehicle, whether or not the vehicle has exhibited an avoidance behavior for avoiding the obstacle on the road, based on behavior data that is time-series data regarding the behavior of each vehicle that has traveled on the road; an obstacle determination unit that determines that the obstacle is present on the road when a plurality of the vehicles exhibit the avoidance behavior within a predetermined time; Equipped with the behavior data includes a yaw rate of the vehicle, and information on the lighting status of left and right turn signals or acceleration / deceleration of the vehicle; the behavior determination unit determines whether or not the steering wheel has been turned suddenly in the vehicle based on the yaw rate, and when the steering wheel has been turned suddenly, determines that the vehicle has exhibited the avoidance behavior when the left and right direction indicators do not light up, or when the left and right direction indicators light up successively and alternately, or when the vehicle accelerates after decelerating, Furthermore, The behavior determination unit determines that the vehicle has made an abrupt turn in the steering wheel when an absolute value of a difference between adjacent maximum and minimum values ​​of the yaw rate is equal to or greater than a first threshold value, a time difference between the adjacent maximum and minimum values ​​is equal to or greater than a second threshold value, and a maximum value of a slope between the adjacent maximum and minimum values ​​is equal to or greater than a third threshold value. Obstacle detection system.

2. An obstacle detection system that detects obstacles on a road, a behavior determination unit that determines, for each vehicle, whether or not the vehicle has exhibited an avoidance behavior for avoiding the obstacle on the road, based on behavior data that is time-series data regarding the behavior of each vehicle that has traveled on the road; an obstacle determination unit that determines that the obstacle is present on the road when a plurality of the vehicles exhibit the avoidance behavior within a predetermined time; Equipped with the behavior determination unit determines, for each road section, whether or not the vehicle has exhibited the avoidance behavior based on the behavior data for each vehicle that has traveled on the road section; the obstacle determination unit determines that the obstacle is present in the road section when a plurality of the vehicles exhibit the avoidance behavior within the predetermined time for each road section; Furthermore, The behavior determination unit determines whether the vehicle has exhibited the avoidance behavior when there is no interchange or service area in the road section, or when there is no center of an S-curve in the road section. Obstacle detection system.

Images