JP2019079242A - Traveling assist system - Google Patents

Abstract

To make it possible to further diminish a load to be imposed for traveling assist.SOLUTION: Included are a behavior acquisition unit 201 that sequentially acquires behavior related information containing a numerical feature quantity concerning a behavior of an own vehicle, a symbol conversion unit 204 that sequentially converts the behavior related information, which is acquired by the behavior acquisition unit 201, into a behavior symbol containing a symbolic feature quantity through discretization, a symbol prediction unit 208 that predicts a future behavior symbol on the basis of behavior symbols obtained previously by the symbol conversion unit 204, a trajectory prediction unit 211 that predicts a future traveling trajectory on the basis of the future behavior symbol predicted by the symbol prediction unit 208, an object-of-avoidance identification unit 212 that identifies an obstacle, which is an object of avoidance of the own vehicle, using the future traveling trajectory predicted by the trajectory prediction unit 211, and a traveling assist unit 213 that performs traveling assist for avoiding the obstacle which is identified by the object-of-avoidance identification unit 212 as the obstacle that is the object of avoidance of the own vehicle.SELECTED DRAWING: Figure 3

Description

  The present disclosure relates to a travel support device that supports the travel of a vehicle.

  In Patent Document 1, information such as GPS data of adjacent vehicles, vehicle dynamic characteristics, vehicle speed, longitudinal acceleration, lateral acceleration, yaw rate, and steering angle is acquired by communication, and information of the own vehicle and other vehicles is obtained. There is disclosed a technique of giving a warning or the like based on the intersection of the travel paths predicted from the above.

Japanese Patent Application Publication No. 2009-537367

  However, in the technology disclosed in Patent Document 1, information on vehicle behavior having numerical feature quantities such as GPS data, vehicle dynamic characteristics, vehicle speed, longitudinal acceleration, lateral acceleration, lateral acceleration, yaw rate, and steering angle is predicted as it is. In order to use it, it is necessary to individually calculate the influence of the numerical feature quantities on the behavior of the vehicle to predict the traveling locus. Therefore, there is a problem that the processing load for prediction becomes large. In addition, when information on vehicle behavior of another vehicle is to be used, such information on a plurality of types of vehicle behavior is transmitted / received to / from other vehicles by communication, so the amount of communication increases and communication load becomes large. It also causes problems.

  One object of the present disclosure is to provide a driving support apparatus that can further reduce the load for driving support.

  The above object is achieved by a combination of the features of the independent claims, and the subclaims define further advantageous embodiments of the disclosure. The reference numerals in parentheses described in the claims indicate the correspondence with specific means described in the embodiments described later as one aspect, and do not limit the technical scope of the present disclosure. .

  In order to achieve the above object, a driving support apparatus of the present disclosure is a driving support apparatus including a driving support unit (213) that is used in a vehicle and performs driving support for avoiding an obstacle around the host vehicle. The behavior acquisition unit (201) sequentially acquires behavior-related information having numerical feature quantities relating to the behavior of the vehicle, and the behavior-related information acquired by the behavior acquisition section into symbolic information having symbolic feature quantities by discretization. A symbol conversion unit (204) for sequential conversion, a symbol prediction unit (208) for predicting future symbol information from symbol information obtained in the past by the symbol conversion unit, and a future symbol information predicted by the symbol prediction unit A trajectory prediction unit (211) that predicts the travel trajectory of the vehicle, and an avoidance target identification unit (212) that identifies an obstacle to be avoided by the vehicle using the future travel trajectory predicted by the trajectory prediction unit; The driving support unit is In target identification unit performs driving support for avoiding an obstacle for identifying an obstacle the vehicle is to avoid the subject.

  According to this, future symbol information is predicted from past symbol information obtained by converting behavior related information having a numerical feature amount relating to the behavior of the vehicle into symbol information having a symbolic feature amount by discretization, The future travel locus is predicted from future symbol information. Therefore, as compared with predicting the future traveling locus by using the behavior related information having the numerical feature value as it is, only by an amount to predict the future traveling locus using symbol information simplified than the behavior related information. It becomes possible to reduce the processing load concerning prediction. Therefore, it is possible to further reduce the load for driving assistance when specifying the obstacle to be avoided using the future traveling locus and performing driving assistance for avoiding the obstacle. .

1 shows an example of a schematic configuration of a support system 100. FIG. FIG. 2 is a view showing an example of a schematic configuration of a vehicle side unit 1; It is a figure showing an example of rough composition of run supporting ECU2. It is a figure which shows an example of the future travel locus | trajectory of an own vehicle and another vehicle. It is a figure for demonstrating an example of specification of the obstacle which self-vehicles make the avoidance object. It is a flow chart which shows an example of a flow of sign prediction DB update related processing in driving support ECU2. It is a flowchart which shows an example of the flow of the symbol prediction related process in driving assistance ECU2. It is a flowchart which shows an example of a flow of traveling locus DB update related processing in driving assistance ECU2. It is a flowchart which shows an example of a flow of locus | trajectory prediction related processing in driving assistance ECU2. It is a flow chart which shows an example of a flow of avoidance object specific related processing in driving support ECU2.

  DETAILED DESCRIPTION Embodiments of the disclosure will be described with reference to the drawings. Note that, for convenience of explanation, among the plurality of embodiments, portions having the same functions as the portions shown in the figures used in the description so far are given the same reference numerals and may not be described. is there. The description in the other embodiments can be referred to for parts denoted by the same reference numerals.

(Embodiment 1)
<Schematic Configuration of Support System 100>
Hereinafter, the present embodiment will be described using the drawings. The support system 100 shown in FIG. 1 includes a vehicle-side unit 1 used in each of a plurality of vehicles. The vehicle side unit 1 used by each vehicle shall be able to communicate by wireless communication. Although the vehicle referred to here will be described as a car, for example, it may be applied to a vehicle other than a car.

<Schematic Configuration of Vehicle Side Unit 1>
As shown in FIG. 2, the vehicle side unit 1 includes a driving support ECU 2, a communication device 3, a locator 4, a map database (hereinafter, DB) 5, a vehicle condition sensor 6, a vehicle control ECU 7, and an HMI (Human Machine Interface) system 8. , And a peripheral monitoring sensor 9 are included. The driving support ECU 2, the communication device 3, the locator 4, the map DB 5, the vehicle state sensor 6, the vehicle control ECU 7, and an HMI (Human Machine Interface) system 8 are connected to, for example, an in-vehicle LAN.

  The communication device 3 performs communication for transmitting and receiving information with the communication device 3 of the vehicle unit 1 used by another vehicle, a roadside device installed on the roadside, or a center outside the vehicle. The communication device 3 includes a transmitting unit 30 and a receiving unit 31. The transmitting unit 30 transmits information, and the receiving unit 31 receives the information.

  Hereinafter, wireless communication with the communication device 3 of the vehicle unit 1 used in another vehicle will be referred to as inter-vehicle communication, wireless communication with the roadside device as road-vehicle communication, and communication with the center as wide area communication. Inter-vehicle communication and road-to-vehicle communication may be performed using radio waves such as 700 MHz band, 760 MHz band, 2.4 GHz band, 5.9 GHz band, and the like. Further, wide area communication may be performed via a public communication network such as a cellular phone network or the Internet. When communication devices 3 of different vehicles transmit / receive information via the center by wide area communication, by transmitting / receiving information including the position of the vehicle, the center can be within a certain range based on the position of the vehicle. It is preferable to adjust so that the information may be transmitted and received between the communication devices 3 of the vehicle.

  The locator 4 includes, for example, a Global Navigation Satellite System (GNSS) receiver and an inertial sensor. The GNSS receiver receives positioning signals from multiple satellites. As an inertial sensor, for example, a gyro sensor that detects a yaw rate and an acceleration sensor that detects an acceleration may be used. The locator 4 sequentially measures the position of the vehicle equipped with the locator 4 by combining the positioning signal received by the GNSS receiver and the measurement result of the inertial sensor. In addition, it is good also as a structure using the travel distance calculated | required from the signal sequentially output from the vehicle speed sensor mounted in the own vehicle for positioning of a vehicle position.

  The map DB 5 is, for example, a non-volatile memory, and stores map data such as link data, node data, road shapes, structures and the like. The link data includes link ID for specifying link, link length indicating link length, link direction, link travel time, link shape information, node coordinates (latitude / longitude) of start and end of link, road type, etc. It consists of each data of. The map data may be configured to include a three-dimensional map including a road shape and a point group of feature points of a structure. The map data may be acquired from the outside of the vehicle via the communication device 3.

  In addition, when using the three-dimensional map which consists of a point shape of the road shape and the feature point of a structure as map data, the locator 4 does not use a GNSS receiver, but this three-dimensional map, a road shape, The position of the vehicle of the vehicle may be specified using detection results of the surrounding area monitoring sensor 9 such as LIDAR (Light Detection and Ranging / Laser Imaging Detection and Ranging) that detects a point cloud of feature points.

  The vehicle state sensor 6 is a sensor group for detecting various states such as the traveling state and the operation state of the own vehicle. The vehicle state sensor 6 includes a vehicle speed sensor that detects the vehicle speed of the vehicle, a steering angle sensor that detects the steering angle of the vehicle's steering, and an accelerator that detects the opening degree of the accelerator pedal of the vehicle (hereinafter referred to as the accelerator opening degree). There are a position sensor, a brake depression force sensor that detects the depression amount of the brake pedal of the own vehicle, and the like. The vehicle state sensor 6 outputs the detection result to the in-vehicle LAN. The detection result of the vehicle state sensor 6 may be output to the in-vehicle LAN via the ECU mounted on the own vehicle.

  The vehicle control ECU 7 is an electronic control unit that performs acceleration / deceleration control and / or steering control of the own vehicle. The vehicle control ECU 7 includes a steering ECU that performs steering control, a power unit control ECU that performs acceleration and deceleration control, and a brake ECU.

  The HMI system 8 includes an HCU (Human Machine Interface Control Unit) 80, a display device 81, and an audio output device 82. The HMI system 8 presents information to the driver of the vehicle.

  Examples of the display device 81 include a combination meter, a CID (Center Information Display), a HUD (Head-Up Display), and an LED. The combination meter is disposed in front of the driver's seat. The CID is disposed above the center cluster in the vehicle cabin. The HUD projects light of an image based on image data acquired from the HCU 80 onto a projection area defined by a windshield, a combiner or the like. The light of the image reflected to the vehicle interior by this projection area is perceived by the driver sitting on the driver's seat, and the driver can visually recognize the virtual image of the image projected by the HUD superimposed on the external scenery in front of the vehicle. It becomes. The LEDs are arranged at noticeable positions of a driver such as an instrument panel, and the light emission is controlled by the HCU 80. The audio output device 82 includes, for example, an audio speaker that outputs a sound, a buzzer that outputs a sound, and the like. The HCU 80 is an electronic control unit that causes the display unit 81 to perform display and causes the audio output unit 82 to output audio.

  The surrounding area monitoring sensor 9 is an obstacle such as a pedestrian, a non-human animal, a moving object such as a bicycle, a motorcycle or another vehicle, a falling object on the road, a guardrail, a curb or a stationary object such as a tree. To detect. In addition, road markings such as travel division lines and stop lines around the vehicle are detected. As the surrounding area monitoring sensor 9, a surrounding area monitoring camera 90 having a predetermined range around the own vehicle as an imaging range may be used. The peripheral monitoring sensor 9 may be configured to use millimeter wave radar, sonar, light detection and ranging (LIDAR), or the like. The periphery surveillance camera 90 sequentially outputs the captured images to be sequentially captured to the driving support ECU 2 as sensing information. A sensor that transmits a search wave such as a sonar, millimeter wave radar, LIDAR or the like sequentially outputs a scan result based on a reception signal obtained when a reflection wave reflected by an obstacle is received to the travel support ECU 2 as sensing information.

  The driving support ECU 2 includes a processor, a memory, an I / O, and a bus connecting these, and executes a control program stored in the memory to execute various processing related to the driving support of the vehicle. Execution of the control program by the processor corresponds to execution of a method corresponding to the control program. As used herein, memory is a non-transitory tangible storage medium that stores non-transitory computer readable programs and data. In addition, the non-transitional tangible storage medium is realized by a semiconductor memory or a magnetic disk. The travel support ECU 2 corresponds to a travel support device. Details of the processing in the driving support ECU 2 will be described later.

<Schematic Configuration of Driving Support ECU 2>
Subsequently, a schematic configuration of the driving support ECU 2 will be described with reference to FIG. The travel support ECU 2 includes a behavior acquisition unit 201, a reference information acquisition unit 202, a behavior symbol DB 203, a symbol conversion unit 204, another vehicle information acquisition unit 205, a symbol prediction DB 206, a first update unit 207, a symbol prediction unit 208, and a travel locus DB 209. The second update unit 210, the trajectory prediction unit 211, the avoidance target identification unit 212, and the travel support unit 213 are provided as functional blocks. The behavior symbol DB 203, the symbol prediction DB 206, and the traveling locus DB 209 may be realized by an electrically rewritable non-volatile memory.

  Note that part or all of the functions executed by the travel support ECU 2 may be configured as hardware by one or more ICs or the like. In addition, some or all of the functional blocks included in the driving support ECU 2 may be realized by a combination of software execution by a processor and hardware members. The behavior symbol DB 203, the symbol prediction DB 206, and the travel locus DB 209 are not limited to the configuration realized by the memory provided in the travel support ECU 2, and may be implemented by a storage device connected to the outside of the travel support ECU 2.

  The behavior acquisition unit 201 sequentially acquires behavior related information having numerical feature quantities related to the behavior of the vehicle detected by the inertial sensor of the locator 4 and the vehicle state sensor 6. Behavior related information includes yaw rate detected by gyro sensor, acceleration detected by acceleration sensor, vehicle speed detected by vehicle speed sensor, steering angle detected by steering angle sensor, accelerator opening detected by accelerator position sensor, and brake depression force sensor There is the amount of depression of the brake to be detected, etc. The acceleration detected by the acceleration sensor includes longitudinal acceleration, lateral acceleration, and the like.

  The reference information acquisition unit 202 acquires various types of information from the locator 4, the map DB 5, the surrounding area monitoring sensor 9, and the like. For example, the vehicle position of the own vehicle is acquired from the locator 4, and map data is acquired from the map DB 5. In addition, from the surroundings monitoring sensor 9, a captured image of the surroundings of the vehicle and information of an object around the vehicle are acquired. As information of an object around the own vehicle, for example, peripheral object attributes such as the type of the object, the distance between the own vehicle and the object, and the relative velocity of the object relative to the own vehicle are estimated from sensing information obtained by the surroundings monitoring sensor 9 It may be configured to acquire. The type of object may be estimated by performing pattern matching or the like based on a captured image of the sensing information. Besides, an identifier (hereinafter referred to as a driver ID) for identifying a driver driving the own vehicle may be acquired. As an example, the driver ID may be configured to acquire, as the driver ID, a code of an electronic key of which collation has been established, for example, in the passenger compartment of the own vehicle.

  The behavior symbol DB 203 stores pattern information of symbols necessary to convert behavior related information into behavior symbols that are symbol information having symbolic feature quantities. The symbol conversion unit 204 performs discretization on the behavior related information as time series data sequentially acquired by the behavior acquisition unit 201. For discretization, for example, a hierarchical Dirichlet process Hidden Markov Model, a general Hidden Markov Model, an N-order Markov Model, a hierarchical Markov Model, a switching AR model, a switching Kalman filter model, etc. may be used. Then, the symbol conversion unit 204 converts the behavior related information classified by the discretization into a symbol based on the pattern information stored in the behavior symbol DB 203. This makes it possible to simplify behavior-related information having numerical feature quantities into symbols grouped by driving scene of the vehicle.

  It is preferable that the symbol conversion unit 204 collectively convert a plurality of types of behavior related information into one behavior symbol corresponding to a set of the plurality of types of behavior related information. Further, the symbol conversion unit 204 may segment the symbol string obtained by the discretization into each symbol string representing the driving scene, integrate the behavior symbols in the same segment, and convert it into a new behavior symbol. preferable. When this configuration is adopted, behavior-related information having numerical feature quantities can be simplified into symbols summarized according to changes in the driving scene of the vehicle. Further, in the case of adopting this configuration, the behavior symbol DB 203 may be configured to store pattern information for integrating the symbols in the segment and converting them into new symbols.

  The behavior symbol of the vehicle which is sequentially converted by the symbol converter 204 may be transmitted from the transmitter 30. When transmitting the behavior symbol of the own vehicle from the transmission unit 30, the vehicle position of the own vehicle, an identification for identifying the own vehicle (hereinafter, vehicle ID) and the like may be transmitted. The information such as the behavior symbol of the own vehicle transmitted from the transmission unit 30 is received by the reception unit 31 of the communication device 3 of another vehicle located within the communication range of the transmission unit 30.

  The other vehicle information acquisition unit 205 acquires the information about the other vehicle transmitted from the communication device 3 of the vehicle unit 1 used by the other vehicle, which is received by the reception unit 31. Other vehicle information acquired by the other vehicle information acquisition unit 205 includes the behavior symbol of the other vehicle converted by the symbol conversion unit 204 of the other vehicle, the vehicle position of the other vehicle positioned by the locator 4 of the other vehicle, and the other vehicle Vehicle ID etc. are mentioned.

  The symbol prediction DB 206 stores information necessary to predict future behavior symbols. The symbol prediction DB 206 corresponds to a symbol prediction storage unit. As an example, the symbol prediction DB 206 is obtained by the symbol conversion unit 204 in the past following the symbol string of the pattern for each pattern of the symbol string of the behavior symbol as time series data sequentially converted by the symbol conversion unit 204. A correspondence (hereinafter, symbol prediction correspondence) in which a behavior symbol and its frequency are defined is stored. Details of the symbol prediction correspondence relationship will be described later.

  The symbol prediction DB 206 preferably also stores information for improving the prediction accuracy of future behavior symbols. As an example, it may be configured to store information (hereinafter, trend information) in which the tendency of the behavior of the vehicle is defined according to information related to the traveling environment of the vehicle and for each driver. Examples of information related to the traveling environment of a vehicle include the type of an object around the vehicle, the distance between the vehicle and an object around the vehicle, the relative velocity of the object relative to the vehicle, and the behavior of other vehicles relative to the vehicle There is information on surrounding objects that affect driving. There are other information on the travel point of the vehicle.

  The following is an example of the tendency of behavior according to information about the traveling environment of the vehicle and driver. For example, on the side where an obstacle such as a wall exists among the left and right of the vehicle, there is a tendency not to change lanes. There is also a tendency that it is easy to change the lane to the right when approaching the intersection where the right turn lane is present. In addition, there is a tendency that it is difficult to change the lane to the right when another vehicle to the rear is approaching. Furthermore, there is also a tendency to frequently use sudden braking of a specific driver.

  The first update unit 207 sequentially updates the symbol prediction correspondence stored in the symbol prediction DB 206 based on the behavior symbol sequentially converted by the symbol conversion unit 204. Details of the update of the symbol prediction correspondence in the first update unit 207 will be described later.

  The symbol prediction unit 208 predicts future behavior symbols of the vehicle from the past behavior symbols of the vehicle which are sequentially converted by the symbol conversion unit 204. As an example, in the symbol prediction correspondence relationship stored in the symbol prediction DB 206 based on the symbol string (that is, n-gram) of n behavior symbols obtained by the symbol conversion unit 204 in the most recent past, A behavior symbol of the type most frequently obtained by the symbol conversion unit 204 after this symbol string may be predicted as a future behavior symbol. That is, the future behavior symbol is predicted from the tendency of the behavior symbol transition in the past behavior symbol string. The symbol prediction unit 208 also predicts future behavior symbols of other vehicles from the past behavior symbols of other vehicles acquired by the other vehicle information acquisition unit 205 in the same manner. The symbol prediction unit 208 may be configured to predict future behavior symbols by a method other than that described above, as long as it is a method that can predict future behavior symbols from past behavior symbols.

  In addition to the past behavior symbols sequentially converted by the symbol conversion unit 204, the symbol prediction unit 208 also reinforces the information acquired by the reference information acquisition unit 202 or the information of other vehicles acquired by the other vehicle information acquisition unit 205. It may be used to improve the prediction accuracy of future behavior symbols of the vehicle. In this case, the tendency corresponding to the information acquired by the reference information acquisition unit 202 or the information of another vehicle acquired by the other vehicle information acquisition unit 205 is specified with reference to the tendency information stored in the symbol prediction DB 206. Good. Then, for example, by weighting the frequency of the behavior symbol matched with the identified tendency, the behavior symbol matched with the identified tendency may be easily predicted as the future behavior symbol.

  For example, based on the captured image of the surroundings of the vehicle taken by the surrounding surveillance camera 90 acquired by the reference information acquisition unit 202, the tendency information stored in the symbol prediction DB 206 is referred to, and the captured image indicates The tendency of the behavior of the vehicle corresponding to the traveling environment of the vehicle may be specified. In addition, peripheral object attributes such as the type of the object estimated from the sensing information acquired by the surrounding area monitoring sensor 9 acquired by the reference information acquisition unit 202, the distance between the vehicle and the object, and the relative velocity of the object relative to the vehicle Based on the tendency information stored in the symbol prediction DB 206, the tendency of the behavior of the vehicle corresponding to the traveling environment of the vehicle indicated by the surrounding object attribute may be specified. Furthermore, based on the behavior symbol of the other vehicle and the vehicle position of the other vehicle acquired by the other vehicle information acquisition unit 205, referring to the tendency information stored in the symbol prediction DB 206, the behavior symbol of the other vehicle and The tendency of the behavior of the vehicle corresponding to the behavior of the other vehicle relative to the vehicle identified from the vehicle position of the other vehicle may be identified. According to these, it is possible to improve the prediction accuracy of future behavior symbols in consideration of surrounding information that affects the behavior of the vehicle.

  Also, based on the map data and the vehicle position of the vehicle determined by the locator 4 acquired by the reference information acquisition unit 202, the vehicle on the map is referenced with reference to the tendency information stored in the symbol prediction DB 206. The tendency of the behavior of the vehicle corresponding to the traveling environment of the vehicle indicated by the position of the vehicle may be identified. According to this, it becomes possible to improve the prediction accuracy of future behavior symbols in consideration of the deviation of the behavior of the vehicle due to the traveling point of the vehicle. In addition, referring to the tendency information stored in the symbol prediction DB 206 based on the driver ID acquired by the other vehicle information acquisition unit 205, the behavior of the own vehicle corresponding to the driver indicated by the driver ID The trend may be identified. According to this, it becomes possible to improve the prediction accuracy of future behavior symbols in consideration of the bias of the behavior of the vehicle by the driver.

  The traveling locus DB 209 stores information (hereinafter, correspondence relationship for locus prediction) associated with representative traveling loci for each behavior symbol, which is referred to when predicting the traveling locus from the behavior symbol. The travel locus DB 209 corresponds to a locus prediction storage unit. As an example, in the correspondence relationship for trajectory prediction, a vehicle that can pass most separately by behavior symbol from the past behavior symbol converted by the symbol conversion unit 204 and the traveling trajectory of the own vehicle in the traveling section corresponding to the behavior symbol The surrounding area may be defined as a typical travel locus for the behavior symbol. Details of the trajectory prediction correspondence relationship will be described later.

  The second updating unit 210 sequentially updates the trajectory prediction correspondence relationship stored in the traveling trajectory DB 209 based on the behavior symbol sequentially converted by the symbol conversion unit 204. Details of the update of the correspondence relationship for trajectory prediction in the second update unit 210 will be described later.

  The trajectory prediction unit 211 refers to the correspondence relationship for trajectory prediction stored in the traveling trajectory DB 209 based on the future behavior symbol of the vehicle predicted by the symbol prediction unit 208, and the future behavior symbol of the vehicle. The traveling locus corresponding to is predicted as the future traveling locus of the vehicle. Further, the trajectory prediction unit 211 refers to the correspondence relationship for trajectory prediction stored in the traveling trajectory DB 209 based on the future behavior symbol of the other vehicle predicted by the symbol prediction unit 208, and the future of the other vehicle A traveling locus corresponding to the behavior sign is predicted as a future traveling locus of another vehicle. As an example, as shown in A and B of FIG. 4, the future travel locus is defined as a grid overlapping the future travel locus among grids divided at predetermined intervals around the reference vehicle. Just do it. A of FIG. 4 shows an example of a future travel locus of the own vehicle, and B shows an example of a future travel locus of another vehicle.

  The avoidance target specifying unit 212 specifies an obstacle to be the avoidance target of the own vehicle using the future travel locus predicted by the locus prediction unit 211. The avoidance target specifying unit 212 may specify the other vehicle to be the avoidance target of the own vehicle using the future traveling trajectory of the own vehicle predicted by the trajectory prediction unit 211 and the future traveling trajectory of the other vehicle. According to this, it becomes possible to specify the avoidance target with higher accuracy by considering the future travel locus of another vehicle.

  In addition, the avoidance target identification unit 212 uses the future travel locus of the vehicle predicted by the trajectory prediction unit 211 and the information such as the position of the object around the vehicle acquired by the reference information acquisition unit 202, etc. May specify an object to be avoided. According to this, it is possible to specify an avoidance target other than the other vehicle, and also to specify another vehicle as the avoidance target even when the behavior symbol of the other vehicle can not be received from the other vehicle Become.

  For example, the avoidance target identification unit 212 sets an obstacle for which the host vehicle avoids an object that is within a predetermined distance starting from the future travel locus of the host vehicle predicted by the locus prediction unit 211. It should just be composition specified as. The predetermined distance referred to here may be any distance as long as avoidance is preferable, and can be set arbitrarily. For example, the predetermined distance may be "0". In addition, when using the travel locus which defined the future travel locus of the own vehicle and the future travel locus of other vehicles by the grid which divided at predetermined intervals, such as several meters, it was defined by the grid as shown in FIG. It is good also as composition specified as the avoidance object of the other car with which a running track overlaps.

  In addition, the future travel locus of one's own vehicle is given time information based on the information of speed such as the average velocity of one's other vehicle, and the future's future locus of one's vehicle and the future of the other vehicle at the same timing. In the case where the traveling track of the vehicle is overlapped, the other vehicle may be specified as an avoidance object. On the other hand, when the future traveling locus of the own vehicle and the future traveling locus of the other vehicle do not overlap at the same timing, the other vehicle may not be specified as the avoidance target.

  The driving support unit 213 performs driving support for avoiding an obstacle around the own vehicle, which the avoidance target specifying unit 212 has identified as an obstacle to be avoided by the own vehicle. One example of driving support is to instruct the HCU 80 to cause the HUD of the display device 81 to perform a display for prompting attention on an obstacle to be avoided on the external scenery in front of the host vehicle. . Note that the HCU 80 may be instructed to perform voice output for calling attention from the voice output device 82, or display for calling attention from the display device 81 other than the HUD. In addition, the vehicle control ECU 7 may be instructed to perform acceleration / deceleration control and / or steering control of the vehicle so as to avoid the obstacle to be avoided.

<Symbol Predictive DB Update Related Processing in Driving Support ECU 2>
Subsequently, an example of a flow of processing (hereinafter, symbol prediction DB update related processing) related to the update of the symbol prediction DB 206 in the driving support ECU 2 will be described using the flowchart of FIG. The flowchart in FIG. 6 may be configured to start, for example, when the ignition power supply of the vehicle is turned on. The flowchart of FIG. 6 may be configured to be performed at predetermined timings such as every fixed time or every fixed traveling distance in a situation where the ignition power supply of the own vehicle is turned on.

  First, in step S1, the symbol conversion unit 204 sequentially converts behavior-related information acquired by the behavior acquisition unit 201 into behavior symbols, and obtains a symbol string S of a predetermined number or more of behavior symbols greater than n. In step S2, from the symbol string S obtained in S1, the first updating unit 207 obtains a symbol string Sn as a subsequence for n pieces, and a behavior symbol obtained by the symbol converter 204 next to the symbol string Sn. Extract pairs with s (Sn, s).

  In step S3, the first updating unit 207 calculates the frequency fnew (s | Sn) of s for each symbol string Sn. Specifically, when there is a plurality of symbol strings Sn having the same pattern in the symbol string S, the frequency fnew (s | Sn) of s is calculated for each of the plurality of symbol strings Sn. In step S4, if the frequency f (s | Sn) of s calculated in S3 is already defined in the symbol prediction DB 206 for the symbol string Sn (YES in S4), the process proceeds to step S5. On the other hand, when the frequency f (s | Sn) of s calculated in S3 is not defined in the symbol prediction DB 206 for the symbol string Sn (NO in S4), the process proceeds to step S6.

  In step S5, the first updating unit 207 sets symbol string Sn in the symbol prediction DB 206 as new f (s | Sn) with (1-αf) · f (s | Sn) + αf · fnew (s | Sn) as a new f (s | Sn). Update the frequency f (s | Sn) of s defined for and terminate the symbol prediction DB update related processing. Here, α f is a learning rate of f, and a value of 0 or more and 1 or less is set in advance. Note that α f may be a value set in advance for each behavior symbol s, or may be a common value. On the other hand, in step S6, the first updating unit 207 sets the frequency f (s | Sn) of s for the symbol string Sn in the symbol prediction DB 206, with fnew (s | Sn) as the new f (s | Sn). Define and complete the symbol prediction DB update related processing.

<Signal prediction related processing in driving support ECU 2>
Subsequently, an example of the flow of processing (hereinafter, symbol prediction related processing) related to prediction of future behavior symbols in the driving support ECU 2 will be described using the flowchart of FIG. 7. The flowchart in FIG. 7 may be configured to start, for example, when the ignition power supply of the vehicle is turned on.

  First, in step S21, the symbol prediction unit 208 obtains the symbol string Sn of n behavior symbols obtained by the symbol conversion unit 204 in the most recent past. In step S22, based on the symbol string Sn acquired in step S21, the symbol prediction unit 208 follows the symbol string Sn, and the frequency f (s | Sn) of the behavior symbol s obtained in the past by the symbol conversion unit 204. Are acquired from the symbol prediction DB 206.

  In step S23, the symbol prediction unit 208 selects, from the frequency f (s | Sn) of the behavior symbol s obtained in S22, the behavior symbol s having the maximum frequency as the future behavior symbol following the symbol string Sn. Predict. In step S24, when it is the end timing of the symbol prediction related processing (YES in S24), the symbol prediction related processing is ended. On the other hand, if it is not the end timing of the symbol prediction related processing (NO in S24), the processing returns to S21 and is repeated. The end timing of the symbol prediction related processing may be, for example, when the ignition power supply of the vehicle is turned off.

  Here, an example in the case of predicting the future behavior sign of the own vehicle has been described, but in the case of predicting the future behavior sign of the other vehicle, in S21, the symbol prediction unit 208 For example, the symbol string Sn of n behavior symbols obtained by the other vehicle information acquisition unit 205 in the past may be acquired separately for each vehicle based on the vehicle ID, for example.

<Travel Path DB Update Related Processing in Driving Support ECU 2>
Subsequently, an example of the flow of processing (hereinafter, travel locus DB update related processing) related to updating of the travel locus DB 209 in the travel support ECU 2 will be described using the flowchart of FIG. 8. For example, the flowchart in FIG. 8 may be configured to start each time a new behavior symbol is obtained by the symbol conversion unit 204.

  First, in step S41, the second update unit 210 acquires a new behavior symbol s obtained by the symbol conversion unit 204. In addition, the actual traveling locus t in the traveling section in which the behavior related information converted to the behavior symbol s is acquired is obtained by the reference information acquiring unit 202 of the own vehicle in the traveling section (hereinafter, symbol section). It acquires by specifying from the time series data of the vehicle position.

  In step S42, the second updating unit 210 travels corresponding to the behavior symbol s in the array Gnew (s) having elements corresponding one-to-one to the grid obtained by dividing the periphery of the vehicle at predetermined intervals such as several meters. While "1" is given to the element corresponding to the grid overlapping the locus t, "0" is given to the element corresponding to the grid not overlapping the traveling locus t. As a result, the traveling locus t is simply represented by an array Gnew (s) having elements corresponding to a grid obtained by dividing the vehicle periphery serving as a reference at predetermined intervals. Hereinafter, the array Gnew (s) is referred to as a traveling locus Gnew (s).

  In step S43, when a traveling locus G (s) representing a traveling locus is already defined in the traveling locus DB 209 for the behavior symbol s (YES in S43), the process proceeds to step S44. On the other hand, when the traveling locus G (s) is not defined in the traveling locus DB 209 for the behavior symbol s (NO in S43), the process proceeds to step S45.

  In step S44, the second updating unit 210 runs with the behavior symbol s in the travel locus DB 209 defined as (1−αG) · G (s) + αG · Gnew (s) as a new G (s). The locus G (s) is updated, and the traveling locus DB update related process is ended. Here, αG is a learning rate of G, and a value of 0 or more and 1 or less is set in advance. Note that αG may be a value preset for each behavior symbol s, or may be a common value. In the process of S44, numerical values are added to the elements corresponding to the frequently-fed grid that has actually passed for the behavior symbol s. On the other hand, in step S45, the second updating unit 210 defines G (s) for the behavior symbol s in the traveling locus DB 209 as Gnew (s) as a new G (s), and performs traveling locus DB update related processing Finish.

<Treatment prediction related processing in driving support ECU 2>
Subsequently, an example of a flow of processing (hereinafter, trajectory prediction related processing) related to prediction of a future travel trajectory in the travel support ECU 2 will be described using the flowchart of FIG. 9. The flowchart of FIG. 9 may be configured to start, for example, when the ignition power supply of the vehicle is turned on.

  First, in step S61, the trajectory prediction unit 211 acquires the future behavior symbol s predicted by the symbol prediction unit 208 and the vehicle position. For the future behavior symbol s of the vehicle predicted by the symbol prediction unit 208, the trajectory prediction unit 211 acquires the vehicle position of the latest vehicle acquired by the reference information acquisition unit 202. Further, for the future behavior symbol s of the other vehicle predicted by the symbol prediction unit 208, the trajectory prediction unit 211 acquires the vehicle position of the latest other vehicle acquired by the other vehicle information acquisition unit 205.

  In step S62, based on the behavior symbol s acquired in S61, the trajectory prediction unit 211 defines, from the travel trajectory DB 209, an array G (s) representing a travel trajectory, which is defined in association with the behavior symbol s. get. In step S63, the trajectory prediction unit 211 superimposes the array G (s) acquired in S62 on the map coordinate system from the vehicle position acquired in S61 as a starting point, and the array G (superimposed on the map coordinate system) Among the elements of s), one or more of the elements are predicted to be a future travel locus.

  In step S64, when it is the completion | finish timing of a locus | trajectory prediction related process (it is YES at S64), a locus | trajectory prediction related process is complete | finished. On the other hand, if it is not the end timing of the trajectory prediction related process (NO in S64), the process returns to S61 and the process is repeated. The end timing of the trajectory prediction related process may be, for example, when the ignition power supply of the vehicle is turned off.

<Avoidance Target Identification Related Processing in Driving Support ECU 2>
Subsequently, an example of the flow of processing (hereinafter, avoidance target identification related processing) related to the specification of the avoidance target in the driving support ECU 2 will be described using the flowchart in FIG. 10. The flowchart of FIG. 10 may be configured to start, for example, when the ignition power supply of the vehicle is turned on and the future travel trajectory of the vehicle is predicted in the trajectory prediction related processing.

  First, in step S81, the avoidance target identification unit 212 uses the future travel locus G (s) of the vehicle predicted by the trajectory prediction unit 211 and the position of the object around the vehicle acquired by the reference information acquisition unit 202. When an object in the vicinity of the vehicle is located in an area corresponding to an element whose value is equal to or more than the threshold among elements of the traveling locus G (s), the object is specified as an avoidance target. Since the elements of the traveling locus G (s) correspond to the grids divided at predetermined intervals, specifying an object located in a region corresponding to the elements as an avoidance target is based on the future traveling locus of the vehicle as a starting point This corresponds to specifying an object that is to be present within a predetermined distance as an avoidance target.

  In addition, the threshold value said here should just be a value larger than 1, and can be set arbitrarily. In the traveling locus G (s) stored in the traveling locus DB 209, since values are added to elements corresponding to the grid with which the vehicle has frequently passed, numerical values are added, so in the region where the vehicle is likely to pass. The corresponding elements have larger values. Therefore, when an object around the vehicle is located in a region corresponding to an element whose value is equal to or more than the threshold value, specifying this object as an avoidance target makes it possible to specify the avoidance target more accurately.

  In step S82, the avoidance target specifying unit 212 sets the future traveling locus G (s) of the vehicle predicted by the locus predicting unit 211 and the future traveling locus G (s) of the other vehicle predicted by the locus predicting unit 211. From the above, the value of the elements of the traveling locus G (s) of the own vehicle corresponds to the element above the threshold and the value of the elements of the traveling locus G (s) of the other vehicle is above the above threshold If the area corresponding to the element of (1) overlaps with the other element, the other vehicle is specified as an avoidance target. Since the elements of the traveling locus G (s) correspond to the grids divided at predetermined intervals, specifying the other vehicle where the areas corresponding to the elements overlap as the avoidance target is based on the future traveling locus of the own vehicle as the starting point It corresponds to specifying the other vehicle which will be in the range within the predetermined distance as an avoidance object.

  In step S83, when it is the end timing of the avoidance object identification related process (YES in S83), the avoidance object identification related process is ended. On the other hand, if it is not the end timing of the avoidance target identification related process (NO in S64), the process returns to S61 to repeat the process. As the end timing of the avoidance target specifying process, for example, the time when the ignition power supply of the own vehicle is turned off can be mentioned.

<Summary of Embodiment 1>
In the first embodiment, behavior-related information having numerical feature quantities relating to the behavior of the vehicle is converted into behavior symbols having symbolic feature quantities by discretization processing, and future behavior symbols are predicted from past behavior symbols. Predict future travel trajectory from future behavior symbols. Also, in order to predict the traveling locus of another vehicle around the own vehicle, the behavior symbol of the other vehicle around the own vehicle is received, and the traveling locus of the other vehicle is predicted from the received behavior symbol.

  According to the configuration of the first embodiment, the process of directly predicting the traveling locus from the behavior related information is replaced with the prediction of the discrete behavior symbol and the reference of the traveling locus corresponding to the behavior symbol. It is possible to reduce the processing load. Also, since prediction of future behavior symbols can be performed by referring to the frequency of behavior symbols obtained subsequently following the sequence of behavior symbols obtained in the past, the processing load for prediction also in this respect It becomes possible to reduce the Since it is sufficient to transmit and receive only the index of discrete behavior symbols when sharing the traveling locus with other vehicles around the own vehicle, the amount of communication can be reduced and the communication load can also be reduced.

Second Embodiment
The first embodiment shows a configuration in which the transmitting unit 30 transmits the behavior symbol of the vehicle which is sequentially converted by the symbol conversion unit 204 of the vehicle, but the present invention is not necessarily limited thereto. For example, instead of transmitting the behavior symbol of the vehicle which is sequentially converted by the symbol converter 204 of the vehicle from the transmitting unit 30, the future behavior symbol of the vehicle which is sequentially predicted by the symbol predicting unit 208 of the vehicle is transmitted It may be

  In this case, the other vehicle information acquisition unit 205 receives the other vehicle predicted by the symbol prediction unit 208 of the other vehicle transmitted from the communication device 3 of the vehicle unit 1 used by the other vehicle received by the reception unit 31. It may be configured to obtain future behavior symbols of. Further, the trajectory prediction unit 211 refers to the correspondence relationship for trajectory prediction stored in the traveling trajectory DB 209 based on the future behavior sign of the other vehicle acquired by the other vehicle information acquisition unit 205, and A traveling locus corresponding to a future behavior sign may be predicted as a future traveling locus of another vehicle.

  Even in the configuration of the second embodiment, the process of directly predicting the traveling locus from the behavior related information is replaced with the prediction of the discrete behavior symbol and the reference of the traveling locus corresponding to the behavior symbol, the prediction is taken. It is possible to reduce the processing load. In addition, since it is sufficient to transmit and receive only the index of discrete behavior symbols when sharing the traveling locus with other vehicles around the own vehicle, the amount of communication can be reduced and the communication load can also be reduced.

(Embodiment 3)
In the above embodiment, the transmitting unit 30 transmits the behavior symbol of the vehicle, the future behavior symbol of the vehicle, etc., and the receiving unit 31 receives the behavior symbols of other vehicles, the future behavior symbols of other vehicles, etc. But it is not necessarily limited to this. For example, the transmitting unit 30 may not transmit the behavior symbol of the vehicle or the future behavior symbol of the vehicle, and the receiving unit 31 may not receive the behavior symbol of another vehicle, the future behavior symbol of the other vehicle, etc. The communication device 3 itself may not be included in the vehicle unit 1.

  In this case, the avoidance target identification unit 212 does not use the future travel locus of another vehicle, and the future travel locus of the vehicle predicted by the trajectory prediction unit 211 and the area around the vehicle acquired by the reference information acquisition unit 202 The configuration may be such that an object to be avoided by the vehicle is specified using information such as the position of the object.

  The present disclosure is not limited to the above-described embodiment, and various modifications can be made within the scope of the claims, and the present disclosure can be obtained by appropriately combining the technical means disclosed in different embodiments. Embodiments are also included in the technical scope of the present disclosure.

Reference Signs List 1 vehicle-side unit, 2 travel support ECU (travel support device), 3 communication device, 4 locator, 5 map DB, 6 vehicle state sensor, 7 vehicle control ECU, 8 HMI system, 9 periphery monitoring sensor, 30 transmitter, 31 Reception unit, 80 HCU, 81 display device, 82 sound output device, 90 perimeter surveillance camera, 100 support system, 201 behavior acquisition unit, 202 reference information acquisition unit, 203 behavior symbol DB, 204 symbol converter, 205 other vehicle information acquisition Part 206 206 symbol prediction DB (storage unit for symbol prediction) 207 first update unit 208 symbol prediction unit 209 travel locus DB (storage unit for trajectory prediction) 210 second update unit 211 trajectory prediction unit 212 avoidance Target identification unit, 213 driving support unit

Claims (10)

A driving support apparatus including a driving support unit (213) that is used in a vehicle and performs driving support for avoiding an obstacle around the vehicle,
A behavior acquisition unit (201) for sequentially acquiring behavior related information having numerical feature quantities related to the behavior of the vehicle;
A symbol conversion unit (204) for sequentially converting the behavior related information acquired by the behavior acquisition unit into symbol information having symbolic feature amounts by discretization;
A symbol prediction unit (208) for predicting future symbol information from symbol information obtained in the past by the symbol conversion unit;
A trajectory prediction unit (211) for predicting a future travel trajectory from future symbol information predicted by the symbol prediction unit;
And an avoidance target identification unit (212) for identifying an obstacle to be avoided by the vehicle using the future travel locus predicted by the locus prediction unit.
The travel support device performs travel support for avoiding an obstacle identified by the host vehicle and an obstacle identified by the avoidance target identification unit.   The travel support device according to claim 1, wherein the symbol prediction unit predicts future symbol information from a tendency of transition of symbol information in a symbol information sequence which is a sequence of symbol information obtained in the past by the symbol conversion unit. . A storage for symbol prediction storing a symbol prediction correspondence relationship in which the symbol information string is obtained in the past by the symbol conversion unit and the frequency of each type of symbol information is associated with each symbol information string. Part (206),
The symbol prediction unit is configured to receive the symbol information sequence obtained by the symbol conversion unit most recently by the symbol conversion unit based on the symbol prediction correspondence relationship stored in the symbol prediction storage unit. 3. The driving support apparatus according to claim 2, wherein the symbol information of the frequently obtained type is predicted as future symbol information. A locus prediction storage unit (209) storing a locus prediction correspondence relationship in which a traveling locus is associated with each symbol information;
The trajectory prediction unit is configured to, based on the correspondence relationship for trajectory prediction stored in the storage unit for trajectory prediction, the travel trajectory corresponding to future symbol information of the vehicle predicted by the symbol prediction unit. The driving assistance apparatus according to any one of claims 1 to 3, wherein the driving assistance apparatus is predicted as a future traveling locus of a car.   5. The locus prediction storage unit according to claim 4, wherein the locus prediction storage unit stores, for each of the symbol information, the locus prediction correspondence in which a representative traveling locus when the symbol information is obtained in the past is associated. Driving support device.   The avoidance target identification unit is an obstacle whose target object is an object that is within a predetermined distance from the future travel locus of the vehicle predicted by the trajectory prediction unit. The driving support device according to any one of claims 1 to 5, which specifies. A receiver (31) for receiving, from the other vehicle, the future symbol information of the other vehicle predicted by the symbol prediction unit of the other vehicle;
The trajectory prediction unit predicts a future travel trajectory of the vehicle from future symbol information predicted by the symbol prediction unit of the vehicle, and the future symbol predicted by the other vehicle received by the reception unit From the information, predict the future travel path of the other vehicle,
The avoidance object identification unit identifies an obstacle to be avoided by the vehicle using the future travel trajectory of the vehicle predicted by the trajectory prediction unit and the future travel trajectory of the other vehicle. The travel support device according to any one of 6. A receiver (31) for receiving the symbol information transmitted from another vehicle and converted from the behavior related information of the other vehicle by the symbol converter of the other vehicle;
The symbol prediction unit predicts future symbol information of the vehicle from the symbol information obtained in the past by the symbol conversion unit of the vehicle, while the behavior related information of the other vehicle received by the reception unit is converted Predict future symbol information of the other vehicle from the symbol information
The trajectory prediction unit predicts the future travel trajectory of the vehicle from the future symbol information of the vehicle predicted by the symbol prediction unit, and the future symbol information of the other vehicle predicted by the symbol prediction unit Predict the future travel path of other vehicles,
The avoidance object identification unit identifies an obstacle to be avoided by the vehicle using the future travel trajectory of the vehicle predicted by the trajectory prediction unit and the future travel trajectory of the other vehicle. The travel support device according to any one of 6.   The avoidance object identification unit is an area defined based on a future traveling locus of the vehicle predicted by the locus prediction unit, and an area defined based on a future traveling locus of the other vehicle predicted by the locus prediction unit 9. The driving support apparatus according to claim 7, wherein the other vehicle is specified as an obstacle to be avoided by the own vehicle, when the two vehicles overlap.   Transmitter for transmitting symbol information of the vehicle obtained by converting the behavior related information of the vehicle by the symbol conversion unit, or future symbol information of the vehicle predicted from the symbol information of the vehicle by the symbol prediction unit (30 The driving support apparatus according to any one of claims 1 to 9, further comprising

Images