Information processing apparatus, information processing method, and program

Abstract

To provide an information processing device capable of suppressing an error detection of a target object.SOLUTION: An information processing device according to an embodiment of the present disclosure comprises: an acquisition unit for acquiring first information indicating a first position of a target object calculated by a first calculation method based on a detection result of a distance sensor 101, and second information indicating a second position of the target object calculated by a simulation using a second calculation method different from the first calculation method; and a comparing unit for determining whether or not the first position is correct by comparing the first information and the second information.SELECTED DRAWING: Figure 2

Description

Technical Field

[0001] The present disclosure relates to an information processing apparatus, an information processing method, and a program for detecting the position of an object.

Background Art

[0002] For improving the safety of vehicles and drivers and preventing accidents, the development and introduction of an ADAS (Advanced Driving Assistant System) that acquires information around the vehicle and supports the driver's driving are accelerating.

[0003] Examples of means for acquiring the above information around the vehicle include distance measurement using a distance sensor such as an ultrasonic sensor, a radar, or a lidar. According to these distance sensors, a reflected wave from an object around the vehicle can be acquired, and the distance between the vehicle and the object can be calculated. In addition, by performing image processing on the image information of the scenery or object around the vehicle obtained by a camera or the like, it is possible to identify the position and shape of the object. By mounting such a distance sensor on a vehicle, it is possible to perform multi-directional monitoring. For example, the detection result of a distance sensor arranged at the front part of the vehicle is used for preventing a collision. Further, for example, the detection result of a distance sensor arranged at the rear part of the vehicle is used for preventing contact with a wall or another vehicle during parking.

[0004] Patent Document 1 discloses an object detection device that receives a reflected wave of a transmitted exploration wave as object detection information and detects an object existing around a moving body based on the detection information.

Prior Art Documents

Patent Documents

[0005]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0006] Here, for example, when the distance is calculated based on the reflected wave from the object based on the detection result of the distance sensor, due to interference by the reflected wave from the ground or a step, and disturbances due to the external environment, etc., there is a possibility of false detection in which the object is detected at a position different from the actual position. When false detection occurs, it may lead to accidents such as the brake being operated on the judgment that the object exists although it does not, or colliding with the object on the judgment that the object does not exist although it does.

[0007] In order to suppress such false detection, Patent Document 1 discloses a method of calculating the coordinate position from the received wave information, determining that the reliability of the position (coordinate) continuously detected at the same position is high, and excluding the position detected at other scattered positions as false detection.

[0008] However, the method disclosed in Patent Document 1 has a problem that it can only deal with false detection of scattered positions and cannot deal with false detection that repeatedly appears at the same position.

[0009] The present disclosure provides an information processing apparatus capable of suppressing false detection of an object.

Means for Solving the Problems

[0010] An information processing apparatus according to an aspect of the present disclosure includes an acquisition unit that acquires first information indicating a first position of an object calculated by a first calculation method based on a detection result of a distance sensor, and second information indicating a second position of the object calculated by simulation by a second calculation method different from the first calculation method, and a comparison unit that determines the correctness of the first position by comparing the first information and the second information.

[0011] An information processing method according to an aspect of the present disclosure is an information processing method executed by a computer, the method including: obtaining first information indicating a first position of an object calculated by a first calculation method based on a detection result of a distance sensor, and second information indicating a second position of the object calculated by simulation using a second calculation method different from the first calculation method; and determining the correctness of the first position by comparing the first information and the second information.

[0012] A program according to an aspect of the present disclosure is a program for executing the information processing method.

Advantages of the Invention

[0013] According to the present disclosure, it is possible to provide an information processing apparatus that can suppress misdetection of an object.

Brief Description of the Drawings

[0014]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Figure 11

Figure 12

Figure 13

Figure 14

Figure 15

Figure 16

Figure 17

Figure 18

Figure 19

Figure 20

Figure 21

Figure 22

[0015] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings. Note that the embodiments described below illustrate specific examples of the present disclosure. Therefore, the numerical values, shapes, materials, components, component placement positions, and connection configurations shown in the following embodiments are merely examples and are not intended to limit the present disclosure. Therefore, among the components in the following embodiments, components that are not recited in independent claims will be described as optional components.

[0016] It should be noted that the drawings are schematic diagrams and are not necessarily strict illustrations. In addition, in the drawings, substantially the same components are denoted by the same reference numerals, and redundant explanations are omitted or simplified.

[0017] (Embodiment 1) [composition] Fig. 1 is a diagram for explaining a specific example of detecting the position of an object, and Fig. 2 is a block diagram showing the configuration of an obstacle detection device 100 according to the first embodiment.

[0018] The obstacle detection device 100 is a device that detects the position of an object. The obstacle detection device 100 is an example of an information processing device. The obstacle detection device 100 is mounted on, for example, a vehicle 700, and detects objects 500 and 510 located around the vehicle 700 based on the detection results of a distance sensor 101 (e.g., wave receiving sensors 600, 610, 620, and 630).

[0019] The objects 500 and 510 are objects such as walls, poles, pedestrians, or other vehicles that are positioned around the vehicle 700 and that may hinder the vehicle 700 from traveling.

[0020] The obstacle detection device 100 includes a distance sensor 101 and an information processing unit 10.

[0021] The distance sensor 101 is a sensor that detects information for calculating the position of an object (specifically, the distance and orientation to the object). The distance sensor 101 emits, for example, radio waves or sound waves and detects the reflected wave of the radio waves or the sound waves at the object. The distance sensor 101 is, for example, an ultrasonic sensor, a radar, or a lidar. In the present embodiment, the distance sensor 101 is an ultrasonic sensor, which emits ultrasonic waves and receives the reflected wave reflected by an object, and outputs, as a detection result, information for calculating the distance to the object from the time from when the ultrasonic waves are emitted until the reflected wave is received to the information processing unit 10.

[0022] The distance sensor 101 includes, for example, receiving sensors 600, 610, 620, and 630 disposed on the vehicle 700. The receiving sensors 600, 610, 620, and 630 are respectively disposed at different positions on the vehicle 700.

[0023] The receiving sensors 600, 610, 620, and 630 are respectively sensors that detect reflected waves. In the present embodiment, only the receiving sensor 610 is an active type sensor having a function of outputting radio waves or sound waves (ultrasonic waves in the present embodiment), and the receiving sensors 600, 620, and 630 are passive type sensors that do not have a function of outputting ultrasonic waves. The receiving sensors 600, 610, 620, and 630 respectively detect the reflected wave of the ultrasonic waves emitted by the receiving sensor 610 at the object and output the detection result to the information processing unit 10.

[0024] Note that, for example, among the plurality of distance sensors 101 included in the obstacle detection device 100, the number of active type sensors may be one or more and may be arbitrary.

[0025] Also, the type of the distance sensor 101 is not limited to an ultrasonic sensor, and any sensor capable of calculating the distance and orientation to an object may be used and may be arbitrary.

[0026] The information processing unit 10 is a processing device that performs various processes executed by the obstacle detection device 100. The information processing unit 10 is realized by, for example, a non-volatile memory storing a program, a volatile memory which is a temporary storage area for executing the program, a processor for executing the program, and the like. The information processing unit 10 may be provided with a communication interface for communicating with an ECU (Electronic Control Unit) and a server provided in the vehicle 700, and the like.

[0027] The information processing unit 10 includes a coordinate calculation unit 102, a simulation unit 103, a parameter setting unit 104, and a coordinate comparison unit 105.

[0028] The coordinate calculation unit 102 is a processing unit that generates position information by calculating the position (first position) of an object by a first calculation method using the detection result of the distance sensor 101.

[0029] The position information is information indicating the first position of the object calculated by the first calculation method based on the detection result of the distance sensor 101. The position information is an example of the first information. The position (coordinates) of the object calculated by the coordinate calculation unit 102 is also referred to as the first position.

[0030] For example, the coordinate calculation unit 102 acquires, as input information, reception wave information such as the transmission and reception time and the received wave power obtained from the distance sensor 101 as the detection result of the distance sensor 101, and uses the distance that can be calculated from the reflected wave to the own sensor and the reflected wave to another sensor with respect to a transmission wave sensor (in this embodiment, the reception wave sensor 610) that emits waves such as radio waves or sound waves, and performs triangulation to calculate the position of the object. The coordinate calculation unit 102 outputs the calculation result to the coordinate comparison unit 105. Triangulation is an example of the first calculation method.

[0031] The simulation unit 103 is a processing unit that generates false detection information by calculating the position (second position) of the object through simulation using a second calculation method different from the first calculation method. Specifically, the simulation unit 103 performs a simulation using the second calculation method by using object information indicating the third position and shape of the object and vehicle information regarding the vehicle 700 on which the distance sensor 101 is mounted, thereby calculating the second position to generate second information. The third position is, for example, an arbitrarily set position of the object. The third position may be the position (coordinates) of the object calculated by the object estimation unit 206 (see FIG. 4) described later.

[0032] The false detection information is information indicating the second position of the object calculated by simulation using a second calculation method different from the first calculation method. The false detection information is an example of the second information. The position (coordinates) of the object calculated by the simulation unit 103 is also referred to as the second position.

[0033] The object information is information indicating the third position and shape of the object.

[0034] The vehicle information is information regarding the vehicle 700 on which the distance sensor 101 is mounted. The vehicle information includes, for example, information indicating the position of the vehicle 700, information indicating the speed of the vehicle 700, and information indicating the traveling direction of the vehicle 700. The vehicle information is acquired, for example, from an ECU and GPS (Global Positioning System) provided in the vehicle 700.

[0035] For example, the simulation unit 103 uses information indicating the position of the object, the shape of the object, the speed of the vehicle 700, and the position of the vehicle 700 as input information, and calculates the position of the object by calculating the reflection point of the wave output from the distance sensor 101 on the object by means of a mathematical model for the object. The simulation unit 103 outputs the calculation result to the coordinate comparison unit 105.

[0036] As described above, the coordinate calculation unit 102 calculates the position of the object by, for example, performing triangulation using the detection results of the distance sensor 101. On the other hand, the simulation unit 103 performs a simulation to calculate reflection points using, for example, a mathematical model, and calculates the reflection points, which are the simulation results, as the position of the object. Calculation using a mathematical model is an example of a second calculation method. For example, in the second calculation method, the shape of the object is used to calculate the reflection points, whereas in the first calculation method, the shape of the object is not used.

[0037] The parameter setting unit 104 is a processing unit that sets parameters used by the coordinate comparison unit 105. For example, the parameters are information indicating a predetermined distance. The parameters are stored in advance in, for example, the storage unit 11. For example, the storage unit 11 stores a plurality of parameters indicating different distances. The parameter setting unit 104 sets the parameters based on instructions from a driver or the like obtained via a user interface such as a touch panel display (not shown). The parameter setting unit 104 outputs the set parameters to the coordinate comparison unit 105.

[0038] The coordinate comparison unit 105 is a processing unit that acquires position information and false detection information and compares the position information with the false detection information to determine whether the position information is accurate. Specifically, the coordinate comparison unit 105 compares a first position indicated by the position information with a second position indicated by the false detection information to determine whether the first information indicated by the position information is accurate. The coordinate comparison unit 105 is an example of an acquisition unit and a comparison unit. For example, the coordinate comparison unit 105 receives output information from the coordinate calculation unit 102, the simulation unit 103, and the parameter setting unit 104, determines whether the detected coordinates (position of the object) of the coordinate calculation unit 102 and the simulation unit 103 are the same based on information (parameters) from the parameter setting unit 104, and filters out the incorrect calculation result of the object position (false detection coordinates) by the coordinate calculation unit 102.

[0039] For example, the coordinate comparison unit 105 determines whether the first position indicated by the position information and the second position indicated by the false detection information are located within a predetermined distance indicated by the parameters set by the parameter setting unit 104, thereby determining the correctness of the first position. For example, when the first position and the second position are located within a predetermined distance, the coordinate comparison unit 105 determines that the first position is correct, that is, the object is located at the first position. On the other hand, when the first position and the second position are not located within a predetermined distance, the coordinate comparison unit 105 determines that the first position is incorrect, that is, the object is not located at the first position.

[0040] In the calculation method by the coordinate calculation unit 102, although the calculation speed is fast, in principle, for example, when objects 500 and 510 exist as shown in FIG. 1, as shown by the dashed arrow, the ultrasonic wave emitted by the receiving sensor 610 is reflected by the object 500 and detected by the receiving sensor 610, and as shown by the dash-dotted arrow, the ultrasonic wave emitted by the receiving sensor 610 is reflected by the object 510 and detected by the receiving sensor 620. From these detection results, not only the reflection positions R1 and R2 but also the object may be calculated to exist at the intersection point C as the positions of the objects 500 and 510. Therefore, the obstacle detection device 100 calculates the position of the object by the simulation unit 103 using a mathematical model so that such an incorrect position of the object generated in principle is not calculated. For example, when a new position of an object is calculated by the coordinate calculation unit 102, the simulation unit 103 performs a simulation as described above to determine whether the object actually exists.

[0041] Each processing unit of the coordinate calculation unit 102, the simulation unit 103, the parameter setting unit 104, and the coordinate comparison unit 105 is realized by, for example, a processor and a memory storing a control program executed by the processor.

[0042] The storage unit 11 is a storage device that stores information used by each processing unit such as parameters and object information. The storage unit 11 is realized by, for example, an HDD (Hard Disk Drive) or a semiconductor memory.

[0043] [Operation] Next, the processing procedure of the obstacle detection device 100 will be described.

[0044] FIG. 3 is a flowchart showing the processing procedure of the obstacle detection device 100 according to the first embodiment.

[0045] First, the coordinate calculation unit 102 acquires the detection result from the distance sensor 101 (S110).

[0046] Next, the coordinate calculation unit 102 generates position information indicating the first position of the object by triangulation based on the acquired detection result (S120). Specifically, the coordinate calculation unit 102 calculates the coordinates of the object using triangulation based on the detection result, which is information such as the transmission / reception time and the received wave power obtained from the distance sensor 101 mounted on the vehicle 700.

[0047] Also, the simulation unit 103 generates false detection information indicating the second position of the object by a mathematical model based on the object information and the vehicle information (S130). Specifically, the simulation unit 103 constructs a mathematical model based on the object information and the vehicle information, and calculates the coordinates of the object derived by the mathematical model. In the present embodiment, the object information is, for example, prestored in the storage unit 11 as known information.

[0048] Note that step S120 and step S130 may be performed first from step S120, may be performed first from step S130, or may be performed simultaneously.

[0049] Next, the parameter setting unit 104 sets the determination criterion of the coordinate comparison unit 105 (S140). The parameter setting unit 104 sets, for example, information indicating a predetermined distance as the determination criterion.

[0050] Next, the coordinate comparison unit 105 compares the position information and the false detection information (S150). Specifically, the coordinate comparison unit 105 determines whether the first position and the second position are at the same position according to the criteria of the parameters obtained from the parameter setting unit 104.

[0051] Next, based on the comparison result, the coordinate comparison unit 105 outputs information indicating the position of the object to the ECU of the vehicle 700 or the like (S160). For example, when it is determined in step S105 that they are at the same position, the coordinate comparison unit 105 outputs the position information to, for example, the ECU of the vehicle 700 or the like. On the other hand, when it is determined in step S150 that they are not at the same position, the coordinate comparison unit 105 generates and outputs correction information obtained by correcting the first position indicated by the position information. For example, when the position information indicates the intersection point C of the reflection positions R1 and R2 shown in FIG. 1 as the first position, and the false detection information indicates the reflection positions R1 and R2 as the second position, the coordinate comparison unit 105 filters (deletes) the position (coordinates) of the intersection point C as a false detection, and outputs the result after filtering as correction information.

[0052] [Effects, etc.] As described above, according to the obstacle detection device 100 according to the present embodiment, by comparing the position of the object calculated based on the detection result of the distance sensor 101 with the position of the object calculated from the mathematical model, it can be determined whether the position of the object calculated based on the detection result of the distance sensor 101 is a false detection. Therefore, according to the obstacle detection device 100, for example, it is possible to filter even false detections that appear at a predetermined position in terms of calculation, which could not be solved in the above Patent Document 1. Therefore, it is usefully effective against non-varying false detections that occur due to the principle of the distance sensor 101. For example, when the vehicle 700 controls the brake or the like based on the detection result, the occurrence of incorrect control of the brake due to false detection can be suppressed.

[0053] (Embodiment 2) Next, Embodiment 2 will be described. In the description of this embodiment, the differences from the above embodiment will be mainly described.

[0054] [Configuration] FIG. 4 is a block diagram showing the configuration of the obstacle detection device 200 according to Embodiment 2.

[0055] In addition to the configuration provided in the obstacle detection device 100 according to Embodiment 1, the obstacle detection device 200 further includes an object estimation unit 206.

[0056] The object estimation unit 206 is a processing unit that generates object information by estimating a third position based on received wave information indicating the intensity of the reflected wave detected by the distance sensor 101, which is included in the detection result of the distance sensor 101. Specifically, similar to the coordinate calculation unit 102, the object estimation unit 206 acquires detection results such as the transmission / reception time and received wave power from the distance sensor 101 as input information, and calculates the position (third position) and shape of the object based on the detection results. The position (coordinates) of the object calculated by the object estimation unit 206 is also referred to as the third position. The object estimation unit 206 outputs the calculation result to the simulation unit 103 as object information.

[0057] The object estimation unit 206 is realized by, for example, a processor and a memory in which a control program executed by the processor is stored.

[0058] FIGS. 5 and 6 are diagrams for explaining the process in which the object estimation unit 206 according to Embodiment 2 determines the shape of the object.

[0059] As shown in FIGS. 5(a) and 5(c), for example, it is assumed that the vehicle 700 is equipped with a wave receiving sensor 640. The wave receiving sensor 640 is, for example, an active sensor that emits ultrasonic waves and detects the reflected waves thereof, and is a sensor included in the distance sensor 101. FIGS. 5(a) and 5(c) show different shapes of the object. FIG. 5(b) is a graph showing the detection result of the reflected wave from the object 520 such as the wall shown in FIG. 5(a). FIG. 5(d) is a graph showing the detection result of the reflected wave from the object 530 such as the pole shown in FIG. 5(c). The horizontal axis of these graphs is time, and the vertical axis is the intensity of the reflected wave (received power).

[0060] For example, as shown in FIG. 5(a), when the object 520 is an object (strong reflector) that returns a strong reflected wave such as a wall, as shown in FIG. 5(b), the wave receiving sensor 640 detects a reflected wave with a strong received power.

[0061] On the other hand, for example, as shown in FIG. 5(c), when the object 530 is an object (weak reflector) that is slender like a pole and returns a relatively weak reflected wave compared to a wall, as shown in FIG. 5(d), the wave receiving sensor 640 detects a reflected wave with a weak received power.

[0062] Also, if the object is the same, the closer the distance between the wave receiving sensor 640 and the object, the stronger the received power and the more the reflected wave is detected by the wave receiving sensor 640.

[0063] From these facts, the type of the object (for example, the shape such as a pole and a wall) can be determined based on the position of the object (specifically, the distance between the wave receiving sensor 640 and the object) and the received power.

[0064] Fig. 6 is a table showing, for example, the relationship between received wave power, distance, and the shape of an object. For example, if the distance between the wave receiving sensor 640 and the object is i and the received wave power is j, it corresponds to the square Eij (row i, column j shown in Fig. 6) in the table of Fig. 6, and the shape of the object is pole-like (i.e., the type of object is a pole). Information (correspondence information) of such a table is stored in advance in, for example, the storage unit 11.

[0065] The object estimation unit 206 estimates the position (third position) of the object by, for example, triangulation based on the detection result of the distance sensor 101, and estimates the shape of the object based on the calculated position and correspondence information. The object estimation unit 206 outputs the estimation result to the simulation unit 103.

[0066] 7 is a diagram illustrating the positional relationship between the vehicle 700 and the objects 500 and 510. In the example shown in Fig. 7, an ultrasonic wave emitted by the wave receiving sensor 610 is reflected by the object 500 and detected by the wave receiving sensors 610 and 620, and is also reflected by the object 510 and detected by the wave receiving sensors 610 and 620. Furthermore, the object 500 is located closer to the vehicle 700 than the object 510.

[0067] FIG. 8 is a diagram illustrating the relationship between the detection result of the distance sensor 101 and the positions of the objects 500 and 510. The first sensor is, for example, the wave receiving sensor 610, and the second sensor is, for example, the wave receiving sensor 620. For example, the first wave is the ultrasonic wave detected first, and the second wave is the ultrasonic wave detected after the first wave. In the example shown in FIG. 7, the wave receiving sensors 610 and 620 detect the wave reflected from the object 500 as the first wave and the wave reflected from the object 510 as the second wave, respectively. Therefore, coordinate a calculated based on the first wave detected by each of the wave receiving sensors 610 and 620 indicates reflection position R1 (i.e., the position of the object 500). Furthermore, coordinate b calculated based on the second wave detected by each of the wave receiving sensors 610 and 620 indicates reflection position R2 (i.e., the position of the object 510).

[0068] Therefore, when the vehicle 700 and the objects 500 and 510 are in the positional relationship as shown in FIG. 7, for example, the object estimation unit 206 estimates the positions of the objects (in this example, two third positions) using the correspondence relationship as shown in FIG. 8.

[0069] [Operation] Next, the processing procedure of the obstacle detection device 200 according to the second embodiment will be described.

[0070] FIG. 9 is a flowchart showing the processing procedure of the object estimation unit 206 according to the second embodiment.

[0071] First, the object estimation unit 206 calculates coordinates based on the combination of the order in which the reflected waves return (S201). Specifically, the object estimation unit 206 determines the combination of each wave using the order of the waves received by the plurality of wave receiving sensors based on the detection results of the plurality of wave receiving sensors (for example, wave receiving sensors 610 and 620) provided in the distance sensor 101, and calculates the position of the object using the determined combination. More specifically, the object estimation unit 206 receives, as input information, the information on the reflected waves observed from the distance sensor 101. Thereafter, the object estimation unit 206 considers the combination according to the order in which the reflected waves return, and calculates the coordinate position of the reflecting object by performing triangulation. For example, in the example shown in FIG. 8, the object estimation unit 206 acquires, as detection results, information on two waves received by each of the wave receiving sensor 610 and the wave receiving sensor 620. Further, the object estimation unit 206 determines, as a wave combination, the first wave detected by each of the wave receiving sensor 610 and the wave receiving sensor 620 and the second wave detected by each of the wave receiving sensor 610 and the wave receiving sensor 620. Further, the object estimation unit 206 calculates coordinate a based on the first wave detected by each of the wave receiving sensor 610 and the wave receiving sensor 620. Further, the object estimation unit 206 calculates coordinate b based on the second wave detected by each of the wave receiving sensor 610 and the wave receiving sensor 620. Coordinate a and coordinate b are each an example of the third position.

[0072] Next, the object estimation unit 206 estimates the shape (type) of the object based on the distance from the wave receiving sensor to the object, which is derived from the transmission and reception time included in the detection result of the distance sensor 101, and the wave reception power, which is the intensity when the wave is received by the wave receiving sensor, included in the detection result of the distance sensor 101 (S202). For example, the object estimation unit 206 estimates the shape of the object based on the detection result of the distance sensor 101 and the correspondence information shown in FIG.

[0073] [Effects, etc.] As described above, according to the obstacle detection device 200 of this embodiment, the object estimation unit 206 eliminates the need to store object information in advance in the storage unit 11 or the like, which was necessary as known information in the obstacle detection device 100, and enables real-time derivation. Therefore, even for objects whose position and shape are unknown, it is possible to estimate these and perform a simulation using a mathematical model.

[0074] (Embodiment 3) Next, a description will be given of embodiment 3. In the description of this embodiment, differences from the above embodiments will be mainly explained.

[0075] The obstacle detection device according to the third embodiment has the same configuration as the obstacle detection device 200 according to the second embodiment. The obstacle detection device according to the third embodiment differs from the obstacle detection device 200 in the processing of the object estimation unit 206. Specifically, like the second embodiment, the object estimation unit 206 in this embodiment estimates the position and shape of the object based on the detection result obtained from the distance sensor 101, but if there are three or more estimated positions, it considers possible combinations of those positions and performs estimation of the shape of the object for all of the combinations.

[0076] FIG. 10 is a diagram for explaining the positional relationship between the vehicle 700 and the objects 500 and 510. As shown in FIG.

[0077] In the example shown in FIG. 10, the ultrasonic waves emitted by the receiving sensor 610 are reflected by the object 500 and detected by the receiving sensors 610 and 620, and are reflected by the object 510 and detected by the receiving sensors 610 and 620. Also, in this example, the distances to the vehicle 700 are similar for the object 500 and the object 510.

[0078] FIG. 11 is a diagram for explaining the relationship between the detection result of the distance sensor 101 and the positions of the objects 500 and 510. The first sensor is, for example, the receiving sensor 610, and the second sensor is, for example, the receiving sensor 620. In the example shown in FIG. 10, it is unclear whether the reflected waves from which of the objects 500 and 510 are detected as the first wave or the second wave in the receiving sensors 610 and 620, respectively.

[0079] In such a case, for example, the object estimation unit 206 calculates coordinates for possible wave combinations. In this example, the object estimation unit 206 calculates the coordinate a calculated based on the first wave detected by each of the receiving sensor 610 and the receiving sensor 620, the coordinate b calculated based on the second wave detected by each of the receiving sensor 610 and the receiving sensor 620, the coordinate c calculated based on the second wave detected by the receiving sensor 610 and the first wave detected by the receiving sensor 620, and the coordinate d calculated based on the first wave detected by the receiving sensor 610 and the second wave detected by the receiving sensor 620, and estimates them as the third positions, respectively. Thereby, for example, the reflection positions R1 and R2, and the calculation points C1 and C2 are calculated as the third positions. For example, the reflection position R1 corresponds to the coordinate a, the reflection position R2 corresponds to the coordinate b, the calculation point C1 corresponds to the coordinate c, and the calculation point C2 corresponds to the coordinate d.

[0080] Furthermore, when there are three or more of the calculated plurality of third positions (in this example, four), the object estimation unit 206 determines a combination in which the object is considered to be located among the calculated plurality of third positions. For example, even if there are multiple objects, one wave detected by the wave receiving sensor corresponds to one object. That is, the information of one detected wave is used to calculate one coordinate and not used to calculate other coordinates. Therefore, for example, in this example, it is considered that the object is located at the position of either the combination of coordinate a and coordinate b or the combination of coordinate c and coordinate d. In other words, in this example, it is considered that either the object is located at each of coordinate a and coordinate b or the object is located at each of coordinate c and coordinate d. The object estimation unit 206 performs a simulation using a mathematical model for each determined combination to derive a reflected wave, and determines an appropriate third position from among the three or more third positions based on the derived reflected wave.

[0081] Thus, for example, when the number of the estimated third positions is 3 or more, the object estimation unit 206 determines a plurality of sets of 3 or more third positions (for example, coordinate a and coordinate b, and coordinate c and coordinate d), and for each of the plurality of sets, assumes that an object exists at two or more third positions of the set and estimates the shape of the object. Further, the object estimation unit 206 determines one or more third positions from among the three or more estimated third positions based on the detection result of the distance sensor 101, and outputs object information including the determined one or more third positions and the shape of the object corresponding to each of the one or more third positions to the simulation unit 103. The simulation unit 103 performs a simulation by the second calculation method using the one or more third positions and the shape of the object indicated by the object information acquired from the object estimation unit 206, thereby calculating one or more second positions corresponding to the one or more third positions and the shape, and generating second information. Thus, the object estimation unit 206 derives a reflected wave from the information of the distance sensor 101 using a mathematical model, and calculates the position (third position) of the object based on the derived reflected wave. The simulation unit 103 calculates, as the position (second position) of the object, the position where the wave emitted from the distance sensor is reflected by the object by performing a simulation by a mathematical model using the third position of the object calculated by the object estimation unit 206 and the shape of the object estimated by the object estimation unit 206.

[0082] [Operation] FIG. 12 is a flowchart showing the processing procedure of the obstacle detection device according to the third embodiment. Specifically, FIG. 12 is a flowchart showing the processing procedure of the object estimation unit 206 according to the third embodiment.

[0083] First, the object estimation unit 206 executes the above steps S201 and S202.

[0084] Next, the object estimation unit 206 determines whether or not there are three or more candidates for the position (coordinates) of the object (S303).

[0085] When the object estimation unit 206 determines that there are not three or more, that is, when it determines that there are two or less (No in S303), it outputs the position and shape of the estimated object to the simulation unit 103 (S308) and ends the process.

[0086] On the other hand, when the object estimation unit 206 determines that there are three or more (Yes in S303), it derives combinations of the estimated multiple positions (step S304).

[0087] Next, the object estimation unit 206 selects one combination from the multiple combinations, installs an object at each position of the selected combination, and calculates the reflected wave (for example, the intensity and spreading manner of the reflected wave, etc.) by performing a simulation using a mathematical model (S305).

[0088] Next, the object estimation unit 206 determines whether the information of the calculated reflected wave matches the information of the reflected wave included in the detection result of the distance sensor 101 (S306).

[0089] When the object estimation unit 206 determines that they match (Yes in S306), it outputs the position and shape of the selected object to the simulation unit 103 (S308).

[0090] On the other hand, when the object estimation unit 206 determines that they do not match (No in S306), it determines whether it has calculated the reflected wave for all the calculated combinations (S307).

[0091] When the object estimation unit 206 determines that it has not calculated the reflected wave for all the combinations (No in S307), it returns the process to step S305, selects a combination for which the reflected wave has not been calculated, installs an object at each position of the selected combination, and calculates the reflected wave by performing a simulation using a mathematical model.

[0092] On the other hand, when the object estimation unit 206 determines that the reflected waves have been calculated for all combinations (Yes in S307), there may be an error in the shape of the object used in the simulation. Therefore, the process returns to step S202 to re-estimate the shape of the object. In this case, for example, the object estimation unit 206 re-estimates the object so that a shape different from the originally estimated shape of the object is determined. For example, when the object estimation unit 206 selects the shape of an object corresponding to a distance of i and a received wave power of j based on the correspondence information shown in FIG. 6, it selects the shape of an object corresponding to a grid around Eij, for example, a grid with a distance of i±1 and a received wave power of j±1.

[0093] [Effects, etc.] As described above, according to the obstacle detection device according to the present embodiment, it is possible to perform estimation for all positions of the object that can be considered by the reflected waves. Therefore, it is possible to estimate the position of the object more accurately than the obstacle detection device 200 according to the second embodiment.

[0094] (Embodiment 4) Subsequently, Embodiment 4 will be described. In the description of the present embodiment, the description will focus on the differences from the above-described embodiments.

[0095] The obstacle detection device according to Embodiment 4 has the same configuration as the obstacle detection device 200 according to Embodiment 2. The obstacle detection device according to Embodiment 4 differs from the obstacle detection device 200 in the processing of the object estimation unit 206. Specifically, the object estimation unit 206 in the present embodiment estimates the position and shape of the object based on the detection result obtained from the distance sensor 101 in the same manner as in Embodiment 2. However, when there are three or more estimated positions, possible combinations of those positions are considered. The object estimation unit 206 in the present embodiment selects a combination that is farthest from the vehicle 700's traveling direction among the possible combinations, and assumes that an object exists at the position of the selected combination, and then estimates the shape of the object. Specifically, when the number of the estimated third positions is three or more, the object estimation unit 206 determines a plurality of sets of three or more third positions. Here, the object estimation unit 206 selects a set including a third position that extends in the front-rear direction of the vehicle 700 and is located at the farthest position from the virtual axis (for example, the axle shown in FIG. 10) passing through the center of the vehicle 700, and assumes that there is an object at two or more of the third positions in the set, and then estimates the shape of the object.

[0096] [Operation] FIG. 13 is a flowchart showing the processing procedure of the obstacle detection device according to Embodiment 4. Specifically, FIG. 13 is a flowchart showing the processing procedure of the object estimation unit 206 according to Embodiment 4.

[0097] First, the object estimation unit 206 executes the above steps S201, S202, and S303.

[0098] When the object estimation unit 206 determines that there are not three or more, that is, two or less (No in S303), it outputs the estimated position and shape of the object to the simulation unit 103 (S308) and ends the processing.

[0099] On the other hand, when the object estimation unit 206 determines that there are three or more (Yes in S303), it selects a combination including a third position located outside the vehicle 700 during its travel (S404). The outside during the travel of the vehicle 700 is, for example, a location other than the path of the vehicle 700 when the vehicle 700 moves on the axle shown in FIG. 10. In the example shown in FIG. 10, the objects 500 and 510, and the reflection positions R1 and R2 are located outside the vehicle 700 during its travel. On the other hand, in the example shown in FIG. 10, the calculation points C1 and C2 are not located outside the vehicle 700 during its travel. In other words, in the example shown in FIG. 10, the calculation points C1 and C2 are located on the travel path of the vehicle 700.

[0100] Next, the object estimation unit 206 installs an object at each position of the selected combination and performs a simulation using a mathematical model to calculate reflected waves (for example, the intensity and spread of the reflected waves, etc.) (S405).

[0101] Next, the object estimation unit 206 determines whether the information of the calculated reflected waves matches the information of the reflected waves included in the detection result of the distance sensor 101 (S306).

[0102] When the object estimation unit 206 determines that they match (Yes in S306), it outputs the selected third position and shape to the simulation unit 103 (S308) and ends the process.

[0103] On the other hand, when the object estimation unit 206 determines that they do not match (No in S306), it determines whether the positions (coordinates) of the unselected combinations exist on the travel path of the vehicle 700 (S407).

[0104] For example, when the object estimation unit 206 determines that it exists on the travel path of the vehicle 700 (Yes in S407), in step S308, it outputs the position of the unselected combination and the shape estimated by the object estimation unit 206 in step S202 to the simulation unit 103.

[0105] On the other hand, for example, when the object estimation unit 206 determines that the object does not exist on the path of the vehicle 700 (No in S407), the process proceeds to step S305 shown in FIG. 12. An object is placed at each position of the unselected combination, and by performing a simulation using a mathematical model, the reflected wave (for example, the intensity and spreading manner of the reflected wave) is calculated.

[0106] [Effects, etc.] As described above, according to the obstacle detection device according to the present embodiment, the process proceeds on the assumption that there is an object at an outer position on the path of the vehicle 700 with respect to the combination of positions of the object that can be considered by the reflected wave. Thereby, the calculation time can be reduced and the position of the object can be estimated. Further, since the estimation is performed on the premise that it is outside the path of the vehicle 700, if the detection result of the distance sensor 101 matches the simulation result by the simulation unit 103, the vehicle 700 can proceed. If they do not match and the remaining third position is located on the path of the vehicle 700, for example, by instructing a braking operation to the ECU of the vehicle 700 or the like on the assumption that there is a risk of collision with the object, the occurrence of an accident can be suppressed. For example, when the answer is Yes in step S407, the obstacle detection device according to the present embodiment outputs information indicating the determination result in step S407 (for example, the positions of the combinations not selected by the object estimation unit 206) to the ECU provided in the vehicle 700. When the answer is Yes in step S407, since the vehicle 700 is highly likely to collide with the object, the obstacle detection device according to the present embodiment outputs the determination result to the ECU provided in the vehicle 700 to cause the vehicle 700 to apply the brakes. As a result, the vehicle 700 is stopped urgently.

[0107] (Embodiment 5) Subsequently, Embodiment 5 will be described. In the description of the present embodiment, the description will be centered on the differences from the above-described embodiments.

[0108] The obstacle detection device according to Embodiment 5 has the same configuration as the obstacle detection device 200 according to Embodiment 2. The obstacle detection device according to Embodiment 5 differs from the obstacle detection device 200 in the processing of the target object estimation unit 206. Specifically, the target object estimation unit 206 in the present embodiment estimates the position and shape of the target object based on the detection result obtained from the distance sensor 101 in the same manner as in Embodiment 2. However, when there are three or more estimated positions, possible combinations of those positions are considered. In the present embodiment, when all positions in a considered combination are outside the vehicle 700's traveling path, the target object estimation unit 206 determines that the position of the target object is at a point far from the vehicle 700's traveling path and that the target object is an object that returns a strong reflection, such as a wall or another vehicle, and determines the type (shape) of the target object. Specifically, when the number of the estimated third positions is three or more, the target object estimation unit 206 determines a plurality of sets of three or more third positions and determines whether the three or more third positions are located on the vehicle 700's traveling path when the vehicle 700 moves forward or backward. Further, the target object estimation unit 206 assumes that the target object exists at two or more third positions of a set in which all of the two or more third positions of the set are not located on the vehicle 700's traveling path among the plurality of sets. Also, for example, the target object estimation unit 206 estimates that the shape of the target object is a shape having a reflectance higher than a predetermined reflectance.

[0109] Note that the predetermined reflectance and the shape having a reflectance higher than the predetermined reflectance may be arbitrarily determined. For example, an object having a relatively large area that reflects waves, such as a wall, is an object having a shape with a reflectance higher than the predetermined reflectance. On the other hand, for example, an object that is slender and has a relatively small area that reflects waves compared to a wall or the like, such as a pole, is an object having a shape with a reflectance equal to or lower than the predetermined reflectance.

[0110] [Operation] FIG. 14 is a flowchart showing the processing procedure of the obstacle detection device according to Embodiment 5. Specifically, FIG. 14 is a flowchart showing the processing procedure of the target object estimation unit 206 according to Embodiment 5.

[0111] First, the object estimation unit 206 executes the above steps S201 and S303.

[0112] When the object estimation unit 206 determines that there are not 3 or more, that is, 2 or less (No in S303), it outputs the position and shape of the estimated object to the simulation unit 103 (S308) and ends the process.

[0113] On the other hand, when the object estimation unit 206 determines that there are 3 or more (Yes in S303), it determines whether there is any combination in which all the positions (coordinates) are outside the traveling direction of the vehicle 700 (S509).

[0114] When the object estimation unit 206 determines that there is no combination in which all the positions (coordinates) are outside the traveling direction of the vehicle 700 (No in S509), after performing the process of step S202, it performs the processes after step S404.

[0115] On the other hand, when the object estimation unit 206 determines that there is a combination in which all the positions (coordinates) are outside the traveling direction of the vehicle 700 (Yes in S509), it selects the combination and determines that a strong reflector (an object having a shape with a reflectivity higher than a predetermined reflectivity) exists as an object at each position of the combination (S510). Thereafter, the object estimation unit 206 performs the processes after step S405.

[0116] [Effects, etc.] As described above, according to the obstacle detection device according to the present embodiment, in a limited situation where all of the combinations of the positions of the objects considered by the reflected waves are located outside the vehicle 700 during travel, it can be assumed that the vehicle 700 can pass through between the objects, and it can be assumed that a strong reflection is returned from the objects. Therefore, the calculation time for specifying the shape of the object can be significantly reduced. Further, since the estimation is performed on the premise that it is outside the vehicle 700 during travel, if the detection result of the distance sensor 101 and the simulation result by the simulation unit 103 match, the vehicle 700 can travel. If they do not match and the remaining third position is located on the vehicle 700's travel path, for example, by instructing the ECU of the vehicle 700 to perform a braking operation assuming there is a risk of collision with the object, the occurrence of an accident can be suppressed.

[0117] (Embodiment 6) Subsequently, Embodiment 6 will be described. In the description of the present embodiment, the description will focus on the differences from the above-described embodiments.

[0118] [Configuration] FIG. 15 is a block diagram showing the configuration of an obstacle detection device 300 according to Embodiment 6.

[0119] The obstacle detection device 300 further includes a camera unit 307 in addition to the configuration of the obstacle detection device 200.

[0120] The camera unit 307 is a device that acquires an image (image information) by imaging the surroundings of the vehicle 700 with a camera, and estimates the presence or absence of an object, the shape of the object, and the position of the object by performing image analysis on the acquired image. For example, the camera unit 307 estimates the position of the object by performing triangulation using the generated image. The camera unit 307 outputs the estimation result to the object estimation unit 206.

[0121] The camera unit 307 is realized by, for example, a camera, a processor, a memory that stores a control program executed by the processor, and a communication interface for communicating with the information processing unit 10.

[0122] In addition, the object estimation unit 206 according to the present embodiment generates object information based on, for example, the detection result of the distance sensor 101 (specifically, received wave information) and the image captured by the camera of the camera unit 307. Specifically, the object estimation unit 206 generates object information based on the position of the object (for example, the estimation result by the camera unit 307) calculated by performing triangulation using the received wave information and the image captured by the camera.

[0123] Note that the object estimation unit 206 according to the present embodiment may generate object information using the detection result of an arbitrary sensor of a type different from the distance sensor 101 instead of, for example, the image information from the camera unit 307. For example, the object estimation unit 206 generates object information based on the received wave information and sensor information obtained from a predetermined sensor of a type different from the distance sensor 101. As described above, for example, the predetermined sensor is a camera, and the object estimation unit 206 generates object information based on the received wave information and the shape of the object obtained by processing the image captured by the camera. Also, the predetermined sensor may be, for example, the camera included in the camera unit 307, but may be other than a camera and is not particularly limited. For example, the predetermined sensor may be a sensor different from the distance sensor and may be any one of an ultrasonic sensor, a radar, and a lidar.

[0124] [Operation] Subsequently, the processing procedure of the obstacle detection device 300 according to Embodiment 6 will be described. Specifically, the processing procedures of the camera unit 307 and the object estimation unit 206 included in the obstacle detection device 300 according to Embodiment 6 will be described.

[0125] FIG. 16 is a flowchart showing the processing procedure of the camera unit 307 according to Embodiment 6.

[0126] First, the camera unit 307 generates an image by performing imaging with the camera, and estimates the presence or absence of an object by performing image analysis on the generated image. When the object exists, the type (shape) of the object is estimated (S601). For example, the camera unit 307 determines whether the object shown in the image is another vehicle, a person, or something else. Also, for example, when the object shown in the image is longer and thinner than a predetermined size, the camera unit 307 determines it as a pole, and when it is larger than the predetermined size, it determines it as a wall, etc., to estimate the shape of the object.

[0127] Next, the camera unit 307 calculates the position of the object by performing, for example, triangulation based on the image (S602).

[0128] The camera unit 307 outputs the information about the object calculated as described above to the object estimation unit 206.

[0129] FIG. 17 is a flowchart showing the processing procedure of the object estimation unit 206 according to Embodiment 6.

[0130] First, the object estimation unit 206 acquires the estimation result from the camera unit 307 and the detection result from the distance sensor 101. The object estimation unit 206 estimates the position (third position) of the object based on the estimation result acquired from the camera unit 307, that is, the position of the object estimated from the imaging result of the camera (the image generated by the camera), and the position of the object calculated from the detection result from the distance sensor 101 (S603). For example, the object estimation unit 206 compares the position of the object estimated from the imaging result of the camera with the position of the object calculated from the detection result of the distance sensor 101, and selects the position where the object is likely to exist as the third position. Which of the position of the object estimated from the imaging result of the camera and the position of the object calculated from the detection result from the distance sensor 101 is determined to be highly likely to have the object may be arbitrarily determined. For example, if the positions of these objects are less than a predetermined distance from the vehicle 700, the position of the object estimated from the imaging result of the camera may be preferentially estimated as the third position, or if it is more than the predetermined distance, the position of the object calculated from the detection result from the distance sensor 101 may be preferentially estimated as the third position. The predetermined distance may be arbitrarily determined.

[0131] Next, based on the correspondence information indicating the relationship between the distance of the object from the distance sensor 101 and the received wave power, and the shape (type) of the object estimated from the imaging result of the camera unit 307, the shape (type) of the object is estimated (step S604). For example, the object estimation unit 206 compares the shape of the object estimated from the correspondence information with the shape of the object estimated from the imaging result of the camera, and selects the highly likely shape as the shape of the object. Which of the shape of the object based on the correspondence information and the shape of the object estimated from the imaging result of the camera is estimated as the shape of the object may be arbitrarily determined. For example, if the positions of these objects are less than a predetermined distance from the vehicle 700, the shape of the object estimated from the imaging result of the camera may be prioritized, or if it is more than the predetermined distance, the shape of the object determined from the correspondence information may be prioritized. The predetermined distance may be arbitrarily determined.

[0132] [Effects, etc.] As described above, according to the obstacle detection device according to the present embodiment, in addition to the detection result obtained from the distance sensor 101, the position and shape of the object are estimated using the information on the position and shape of the object obtained by image analysis by the camera unit 307. Therefore, the position and shape of the object can be estimated more accurately.

[0133] (Embodiment 7) Subsequently, Embodiment 7 will be described. In the description of this embodiment, the description will focus on the differences from the above-described embodiments.

[0134] [Configuration] FIG. 18 is a block diagram showing the configuration of an obstacle detection device 400 according to Embodiment 7. The obstacle detection device 400 includes an information processing unit 40 different from the obstacle detection device 200. The information processing unit 40 further includes an object confirmation unit 408 in addition to the configuration of the information processing unit 20. That is, the obstacle detection device 400 further includes an object confirmation unit 408 in addition to the configuration included in the obstacle detection device 200.

[0135] The object confirmation unit 408 determines whether or not a second position calculated by performing a simulation by a second calculation method using a first position indicated by first information generated using a first detection result of the distance sensor 101 at a first time and a third position generated using a second detection result of the distance sensor 101 at a second time before the first time matches.

[0136] The distance sensor 101 repeatedly detects the object. The coordinate calculation unit 102, for example, repeatedly obtains the detection result from the distance sensor 101 and calculates the first position repeatedly based on the obtained detection result. The object estimation unit 206, for example, repeatedly obtains the detection result from the distance sensor 101 and generates object information indicating the third position and the shape of the object repeatedly based on the obtained detection result. The simulation unit 103, for example, repeatedly obtains the object information from the object estimation unit 206 and calculates the second position repeatedly based on the obtained object information. Therefore, the object confirmation unit 408 determines whether the position of the object calculated by the coordinate calculation unit 102 in the past is appropriate for the position of the object calculated by the simulation unit 103 this time. The object confirmation unit 408, for example, uses the object information such as the position and shape of the object estimated by the object estimation unit 206 based on the detection result of the distance sensor 101 at a time before the current time to determine whether the second position of the object calculated by the simulation unit 103 matches the first position calculated by the coordinate calculation unit 102 based on the detection result of the distance sensor 101 at the current time. For example, when they match, the object confirmation unit 408 outputs the calculation result of the simulation unit 103 to the coordinate comparison unit 105. On the other hand, when they do not match, the object confirmation unit 408 outputs an instruction to the object estimation unit 206 to estimate the position and / or shape of the object again.

[0137] For example, when the object estimation unit 206 obtains such an instruction, it estimates again the shape of the object as a shape different from the shape of the object it has been estimating. The simulation unit 103 performs simulation using the shape of the object estimated again and calculates the second position.

[0138] [Operation] Subsequently, the processing procedure of the obstacle detection device 400 according to Embodiment 7 will be described. Specifically, the processing procedures of the object confirmation unit 408 and the object estimation unit 206 included in the obstacle detection device 400 will be described.

[0139] FIG. 19 is a flowchart showing the processing procedure of the object confirmation unit 408 according to Embodiment 7.

[0140] First, the object confirmation unit 408 acquires, from the coordinate calculation unit 102, position information indicating a first position calculated based on the detection result of the distance sensor 101 at time t+1 (S701). Time t+1 is an example of a first time.

[0141] Also, the object confirmation unit 408 acquires, from the simulation unit 103, false detection information indicating a second position calculated based on a third position calculated based on the detection result of the distance sensor 101 at time t (S702). Time t is an example of a second time.

[0142] The order in which steps S701 and S702 are executed may be arbitrary. Step S702 may be executed before step S701, or steps S701 and S702 may be executed simultaneously.

[0143] Next, the object confirmation unit 408 determines whether or not the positions (coordinates) of the first position indicated by the acquired position information and the second position indicated by the acquired false detection information match (S703).

[0144] If the object confirmation unit 408 determines that they match (Yes in S703), it outputs, to the coordinate comparison unit 105, false detection information indicating a second position calculated based on a third position calculated based on the detection result of the distance sensor 101 at time t+1 (S704).

[0145] On the other hand, if the object confirmation unit 408 determines that they do not match (No in S703), it outputs an instruction (re-estimation instruction) to the object estimation unit 206 to perform estimation again based on the detection result of the distance sensor 101 at time t+1 (step S705). The re-estimation instruction includes, for example, a flag for causing the object estimation unit 206 to perform re-estimation and an estimation result of the shape of the object in the object estimation unit 206 based on the detection result of the distance sensor 101 at time t.

[0146] As a result, the object estimation unit 206 performs processing for estimating the shape of the object based on the detection result of the distance sensor 101 at time t + 1.

[0147] FIG. 20 is a flowchart showing the processing procedure of the object estimation unit 206 according to Embodiment 7.

[0148] First, the object estimation unit 206 executes the above steps S201 and S202. As a result, the object estimation unit 206 estimates the third position and shape of the object based on, for example, the detection result of the distance sensor 101 at time t + 1.

[0149] Next, the object estimation unit 206 determines whether or not a re-estimation instruction has been acquired from the object confirmation unit 408 (S706). For example, the object estimation unit 206 determines whether or not a flag is included in the information acquired from the object confirmation unit 408.

[0150] If the object estimation unit 206 determines that it has not acquired a re-estimation instruction from the object confirmation unit 408 (No in S706), it outputs the object information generated by executing the above steps S201 and S202 to the simulation unit 103. As a result, the simulation unit 103 calculates the second position based on the object information generated based on the detection result of the distance sensor 101 at time t + 1, and outputs error detection information indicating the calculation result to the object confirmation unit 408. The object confirmation unit 408 transfers the acquired error detection information to the coordinate comparison unit 105.

[0151] On the other hand, if the object estimation unit 206 determines that it has acquired a re-estimation instruction from the object confirmation unit 408 (Yes in S706), it determines whether or not the shape of the object estimated by executing the above step S202 is the same as the shape of the object included in the information acquired from the object confirmation unit 408 (S707).

[0152] When the object estimation unit 206 determines that they are different (No in S707), it outputs the object information generated by executing steps S201 and S202 described above to the simulation unit 103.

[0153] On the other hand, when the object estimation unit 206 determines that they are the same (Yes in S707), it determines the shape of the object (S708) so that the shape is different from the shape of the object included in the information acquired from the object confirmation unit 408 at the periphery (the cells around the cell) of the corresponding location (for example, any cell of the correspondence information shown in FIG. 21) in the correspondence information used when estimating the shape of the object.

[0154] FIG. 21 is a diagram for explaining the process in which the object estimation unit 206 according to the seventh embodiment determines the shape of the object.

[0155] As shown in FIG. 21, for example, it is assumed that the object estimation unit 206 selects the shape of the object corresponding to the cell Eij in step S202. In this case, for example, when the shape of the selected object is the same as the shape of the object included in the information acquired from the object confirmation unit 408, the object estimation unit 206 selects the shape of the object corresponding to the cell within the broken line frame A shown in FIG. 21 and other than the cell Eij.

[0156] Note that the broken line frame A may be arbitrarily determined. For example, when the shapes of the objects corresponding to the cells within the broken line frame A are all the same, the object estimation unit 206 may increase the options for the shape of the object by enlarging the broken line frame A or the like.

[0157] [Effects, etc.] As described above, according to the obstacle detection device 400 according to the present embodiment, for example, in the target object estimation unit 206, it is confirmed whether the first position calculated by the coordinate calculation unit 102 from the detection result of the distance sensor 101 at the same time matches the third position calculated by the target object estimation unit 206. In the target object confirmation unit 408, it is confirmed whether the second position calculated using the third position estimated based on the detection result of the distance sensor 101 at a certain time matches the first position calculated based on the detection result of the distance sensor 101 at a later time. Thereby, for example, when the third position is incorrect, it is possible to reduce the possibility that filtering of the first position is performed based on the erroneously calculated second position. Therefore, according to the obstacle detection device 400, it is possible to further suppress an incorrect calculation of the position of the target object.

[0158] (Summary) FIG. 22 is a flowchart showing a processing procedure of an information processing apparatus according to an aspect of the present disclosure.

[0159] First, the information processing apparatus acquires first information indicating a first position of a target object calculated by a first calculation method based on a detection result of a distance sensor 101, and second information indicating a second position of the target object calculated by simulation using a second calculation method different from the first calculation method (S10).

[0160] Next, the information processing apparatus determines the correctness of the first position by comparing the first information and the second information (S20).

[0161] The first information is, for example, position information. The second information is, for example, false detection information. The acquisition unit and the comparison unit are, for example, the coordinate comparison unit 105. The information processing apparatus is, for example, the obstacle detection device 100, 200, 300, or 400. The information processing apparatus may be realized by, for example, the information processing unit 10, 20, or 40.

[0162] Next, the information processing device outputs the determination result to the vehicle 700 or the like. As a result, the vehicle 700 can perform appropriate control based on the determination result. Also, for example, by displaying the determination result on a display device such as a display, the driver can know the position of an appropriate object.

[0163] Hereinafter, the technology obtained from the disclosure of this specification will be exemplified, and the effects and the like obtained from the exemplified technology will be described.

[0164] The technology 1 includes an acquisition unit that acquires first information indicating a first position of an object calculated by a first calculation method based on a detection result of a distance sensor 101, and second information indicating a second position of the object calculated by simulation using a second calculation method different from the first calculation method, and a comparison unit that determines the correctness of the first position by comparing the first information and the second information.

[0165] Conventionally, when calculating the position of an object using triangulation from the detection results of a distance sensor such as a lidar using a principle such as TOF (Time Of Flight), if two distance sensors detect reflected waves from different objects, the position (coordinates) of the object calculated from the detection results may include incorrect coordinates. For example, it may be calculated that an object exists at the intersection C shown in FIG. 1. Therefore, in order to filter out incorrect coordinates that occur in principle, such as the positional relationship calculated from the detection result of the distance sensor 101, like in the simulation using the above mathematical model, the position of the object is calculated by multiple calculation methods and the calculation results are compared. Thereby, even if the position (first position) of the object calculated by the first calculation method such as triangulation includes incorrect coordinates, for example, using the position (second position) of the object calculated by the second calculation method different from the first calculation method, such as a mathematical model, it is possible to determine whether the position of the object calculated by the first calculation method is appropriate. Therefore, according to the information processing device, false detection of the object can be suppressed. Thus, for example, it is usefully effective against non-varying false detections that occur in principle in the distance sensor 101, and for example, it can cope with false braking of the vehicle 700 due to false detection.

[0166] The technique 2 is further the information processing device according to the technique 1, comprising a coordinate calculation unit 102 that generates first information by calculating a first position by a first calculation method using the detection result.

[0167] According to this, the first information can be generated by the coordinate calculation unit 102.

[0168] The technique 3 is further the information processing device according to the technique 1 or 2, comprising a simulation unit 103 that generates second information by calculating a second position by performing a simulation by a second calculation method using object information indicating a third position and shape of the object and vehicle information regarding the vehicle 700 on which the distance sensor 101 is mounted.

[0169] According to this, the second information can be generated by the simulation unit 103.

[0170] The technique 4 is the information processing apparatus described in technique 3, wherein the comparison unit determines whether the first position and the second position are located within a predetermined distance, and determines the correctness of the first position.

[0171] The predetermined distance is, for example, a parameter set by the parameter setting unit 104.

[0172] According to this, when the predetermined distance is appropriately set, even when the first position and the second position do not completely match but are almost the same and the driver or the like wants to handle them in the same way as when they match, the determination result desired by the driver or the like can be obtained.

[0173] The technique 5 is the information processing apparatus described in technique 3 or 4, wherein the distance sensor 101 emits radio waves or sound waves and detects the reflected waves of the radio waves or the sound waves on the object, and the information processing apparatus further includes an object estimation unit 206 that generates object information by estimating a third position based on reception information indicating the intensity of the reflected waves detected by the distance sensor 101 included in the detection result.

[0174] According to this, the object information can be generated by the object estimation unit 206.

[0175] The technique 6 is the information processing apparatus described in technique 5, wherein when the number of the estimated third positions is 3 or more, the object estimation unit 206 determines a plurality of sets of 3 or more third positions, and for each of the plurality of sets, assumes that an object exists at two or more of the third positions in the set and estimates the shape of the object.

[0176] The object estimation unit 206 calculates the third position by performing the same calculations as the coordinate calculation unit 102 based on the detection result of the distance sensor 101, for example. For example, when a plurality of positions (specifically, three or more positions) are estimated as the third position, there may be a possibility that incorrect coordinates are calculated by the coordinate calculation unit 102. Also, when three or more positions are estimated, not all of them are correct, and in many cases, some of the three or more positions are correct. Therefore, the information processing apparatus determines, for example, pairs of two out of three or more, and performs simulations for each of the determined pairs. As a result, for example, when a correct pair is selected, it becomes unnecessary to calculate other pairs, and thus a reduction in the processing amount can be expected.

[0177] In Technique 7, when the number of estimated third positions is three or more, the object estimation unit 206 determines a plurality of pairs of the three or more third positions, and selects a pair including a third position that extends in the front-rear direction of the vehicle 700 and is located at the position farthest from the virtual axis passing through the center of the vehicle 700, and assumes that there is an object at two or more of the third positions in the pair to estimate the shape of the object. The information processing apparatus according to Technique 5.

[0178] The virtual axis is, for example, the above-described axle.

[0179] According to this, since the position of the object is narrowed down to some extent in advance at the beginning of the calculation, the position of the object can be estimated with less calculation time. Also, since the calculation is performed assuming that the object is far from the vehicle 700, for example, when the second position calculated from the third position is different from the first position, that is, when the first position includes incorrect coordinates, there is a possibility that the object is located at a position close to the vehicle 700. Therefore, for example, by suddenly stopping the vehicle 700, the occurrence of an accident can be suppressed.

[0180] In Technology 8, when the number of estimated third positions is 3 or more, the object estimation unit 206 determines a plurality of sets of three or more third positions, determines whether the three or more third positions are located on the travel path of the vehicle 700 when the vehicle 700 moves forward or backward, and assumes that an object exists at two or more third positions of a set among the plurality of sets where not all of the two or more third positions of the set are located on the travel path of the vehicle 700, and estimates the shape of the object to be a shape having a reflectance higher than a predetermined reflectance. It is the information processing apparatus according to Technology 5.

[0181] According to this, since the position of the object is narrowed down to a certain extent in advance at the beginning of the calculation, the position of the object can be estimated with less calculation time. Further, since it is estimated that the object does not exist on the travel path of the vehicle 700 and calculation is performed, for example, when the second position calculated from the third position is different from the first position, that is, when the first position includes incorrect coordinates, since there is a possibility that an object is located on the travel path of the vehicle 700, for example, by suddenly stopping the vehicle 700, the occurrence of an accident can be suppressed.

[0182] In Technology 9, the object estimation unit 206 generates object information based on reception wave information and sensor information obtained from a predetermined sensor of a type different from the distance sensor 101. It is the information processing apparatus according to any one of Technologies 5 to 8.

[0183] The predetermined sensor is, for example, a camera included in the camera unit.

[0184] According to this, the third position and shape of the object can be estimated with higher accuracy.

[0185] Note that the predetermined sensor may be other than a camera and is not particularly limited. For example, the predetermined sensor may be a sensor different from the distance sensor and may be any one of an ultrasonic sensor, a radar, and a lidar.

[0186] The technique 10 is the information processing apparatus described in technique 9, where a predetermined sensor is a camera, and the object estimation unit 206 generates object information based on received wave information and the shape of an object obtained by processing an image captured by the camera.

[0187] According to this, the shape of the object can be estimated with higher accuracy.

[0188] The technique 11 is the information processing apparatus described in technique 10, where the object estimation unit 206 generates object information based on received wave information and the position of an object calculated by performing triangulation using an image captured by the camera.

[0189] According to this, the third position of the object can be estimated with higher accuracy.

[0190] The technique 12 is the information processing apparatus according to any one of techniques 5 to 11, further comprising an object confirmation unit 408 that determines whether or not a first position indicated by first information generated using a first detection result of the distance sensor 101 at a first time matches a second position calculated by performing simulation by a second calculation method using a third position generated using a second detection result of the distance sensor 101 at a second time before the first time.

[0191] For example, when the object is not moving and when the object is moving very slowly, it is assumed that there is no significant change in the position of the object. Therefore, for example, by determining the correctness of the currently calculated position of the object using the position of the object calculated in the past, false detection of the object can be further suppressed.

[0192] The technique 13 is the information processing apparatus according to any one of techniques 1 to 12, where the distance sensor 101 is an ultrasonic sensor, a radar, or a lidar.

[0193] Based on the detection result of such a distance sensor 101, the position of the object calculated may include the error coordinates theoretically calculated as described above. Therefore, the information processing device is particularly effective for filtering the position of the object calculated when the distance sensor 101 is such a sensor.

[0194] Technique 14 is an information processing method executed by a computer, which acquires first information indicating a first position of an object calculated by a first calculation method based on the detection result of a distance sensor 101, and second information indicating a second position of the object calculated by simulation using a second calculation method different from the first calculation method (S10), and determines the correctness of the first position by comparing the first information and the second information (S20), and is an information processing method.

[0195] According to this, the same effect as that of the information processing device according to one aspect of the present disclosure is achieved.

[0196] Technique 15 is a program for causing a computer to execute the information processing method described in Technique 14.

[0197] According to this, the same effect as that of the information processing device according to one aspect of the present disclosure is achieved.

[0198] (Other embodiments) As described above, the present disclosure has been described based on each embodiment, but the present disclosure is not limited to the above-described embodiments. Therefore, among the components described in the accompanying drawings and the detailed description, there may be included not only the components essential for solving the problems, but also the components not essential for solving the problems for exemplifying the above technology. Therefore, just because those non-essential components are described in the accompanying drawings and the detailed description, it should not be immediately determined that those non-essential components are essential.

[0199] For example, the information processing apparatus may be implemented by the coordinate comparison unit 105. Also, for example, the information processing apparatus may be implemented by the coordinate calculation unit 102 and the coordinate comparison unit 105. Also, for example, the information processing apparatus may be implemented by the simulation unit 103 and the coordinate comparison unit 105. Also, for example, the information processing apparatus may be implemented by the coordinate calculation unit 102, the simulation unit 103, and the coordinate comparison unit 105.

[0200] Also, for example, in the above embodiment, each component (each processing unit) may be implemented by executing a software program suitable for each component. Each component may be implemented by a program execution unit such as a CPU (Central Processing Unit) or a processor reading and executing a software program recorded on a recording medium such as a hard disk or a semiconductor memory.

[0201] Also, each component may be implemented by hardware. Each component may be a circuit (or an integrated circuit). These circuits may constitute one circuit as a whole, or may be separate circuits respectively. Also, these circuits may be general-purpose circuits or dedicated circuits respectively.

[0202] Also, the general or specific aspects of the present disclosure may be implemented by a system, an apparatus, a method, an integrated circuit, a computer program, or a non-transitory recording medium such as a computer-readable CD-ROM. Also, it may be implemented by any combination of a system, an apparatus, a method, an integrated circuit, a computer program, and a recording medium.

[0203] Also, the division of the functional blocks in the block diagram is an example, and a plurality of functional blocks may be implemented as one functional block, one functional block may be divided into a plurality, or some functions may be transferred to other functional blocks. Also, the functions of a plurality of functional blocks having similar functions may be processed by a single hardware or software in parallel or time-division.

[0204] Also, the order in which each step in the flowchart is executed is for illustrative purposes to specifically describe the present disclosure, and it may be in an order other than the above. Also, some of the above steps may be executed simultaneously (in parallel) with other steps.

[0205] In addition, forms obtained by applying various modifications that those skilled in the art can conceive to the above embodiments, and forms realized by arbitrarily combining the components and functions in the above embodiments without departing from the spirit of the present disclosure are also included in the present disclosure.

Industrial Applicability

[0206] The present disclosure can be used in a control device that controls a vehicle based on a detection result of an obstacle.

Explanation of Signs

[0207] 10, 20, 40 Information processing unit 11 Storage unit 100, 200, 300, 400 Obstacle detection device 101 Distance sensor 102 Coordinate calculation unit 103 Simulation unit 104 Parameter setting unit 105 Coordinate comparison unit 206 Object estimation unit 307 Camera unit 408 Object confirmation unit 500, 510, 520, 530 Object 600, 610, 620, 630, 640 Wave receiving sensor 700 Vehicle

Claims

1. An acquisition unit that acquires first information indicating a first position of an object calculated by a first calculation method based on a detection result of a distance sensor, and second information indicating a second position of the object calculated by a simulation using a second calculation method different from the first calculation method; A comparison unit that determines whether the object is located at the first position by determining the correctness of the first position by comparing the first information and the second information, and deletes the first information when it is determined that the object is not located at the first position; An information processing apparatus.

2. Further comprising a coordinate calculation unit that generates the first information by calculating the first position by the first calculation method using the detection result; The information processing apparatus according to claim 1.

3. Further comprising a simulation unit that generates the second information by calculating the second position by performing a simulation using the second calculation method using object information indicating a third position and shape of the object and vehicle information regarding a vehicle on which the distance sensor is mounted; The information processing apparatus according to claim 1.

4. The comparison unit determines the correctness of the first position by determining whether the first position and the second position are located within a predetermined distance; The information processing apparatus according to claim 3.

5. The distance sensor emits radio waves or sound waves and detects a reflected wave of the radio waves or the sound waves at the object; The information processing apparatus further comprises an object estimation unit that generates the object information by estimating the third position based on reception wave information indicating the intensity of the reflected wave detected by the distance sensor included in the detection result; The information processing apparatus according to claim 4.

6. The object estimation unit: When the number of the estimated third positions is 3 or more, determines a plurality of sets of 3 or more of the third positions; For each of the plurality of sets, assumes that the object exists at two or more of the third positions in the set and estimates the shape of the object; The information processing apparatus according to claim 5.

7. The object estimation unit: When the number of the estimated third positions is 3 or more, determines a plurality of sets of 3 or more of the third positions; Select a set including the third position that extends in the longitudinal direction of the vehicle and is located at the position farthest from the virtual axis passing through the center of the vehicle, and assume that the object exists at two or more of the third positions in the set, and estimate the shape of the object. The information processing apparatus according to claim 5.

8. The object estimation unit When the number of the estimated third positions is three or more, determine a plurality of sets of three or more of the third positions. Determine whether or not the three or more third positions are located on the travel of the vehicle when the vehicle moves forward or backward. Assume that the object exists at two or more of the third positions in a set among the plurality of sets where all of the two or more third positions in the set are not located on the travel of the vehicle, and estimate that the shape of the object is a shape having a reflectance higher than a predetermined reflectance. The information processing apparatus according to claim 5.

9. The object estimation unit generates the object information based on the received wave information and sensor information obtained from a predetermined sensor of a type different from the distance sensor. The information processing apparatus according to claim 5.

10. The predetermined sensor is a camera. The object estimation unit generates the object information based on the received wave information and the shape of the object obtained by processing an image captured by the camera. The information processing apparatus according to claim 9.

11. The object estimation unit generates the object information based on the received wave information and the position of the object calculated by performing triangulation using an image captured by the camera. The information processing apparatus according to claim 10.

12. Furthermore, an object confirmation unit is provided that determines whether or not the first position indicated by the first information generated using the first detection result of the distance sensor at the first time matches the second position calculated by performing simulation by the second calculation method using the third position generated using the second detection result of the distance sensor at the second time before the first time. The information processing apparatus according to claim 5.

13. The distance sensor is an ultrasonic sensor, a radar, or a lidar. The information processing apparatus according to any one of claims 1 to 12.

14. An information processing method executed by a computer, Obtain first information indicating a first position of an object calculated by a first calculation method based on a detection result of a distance sensor, and second information indicating a second position of the object calculated by simulation using a second calculation method different from the first calculation method. By comparing the first information and the second information, determine whether the first position is correct, and thereby determine whether the object is located at the first position. When it is determined that the object is not located at the first position, delete the first information. An information processing method.

15. For causing a computer to execute the information processing method according to claim 14. A program.

Images