JP2014043156A - Vehicle travel control device and method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide a vehicle travel control device and a vehicle travel control method which perform vehicle control in accordance with attributes without requiring image processing when attributing an object.SOLUTION: A vehicle travel control device 1 includes: a relative position sensor 12 which detects a position of an object around a vehicle; a road situation detection part 21 which detects a road situation; an attribute selection part 23 which adds an attribute to the object detected by the relative position sensor 12 in accordance with the road situation in a position of the object which is detected by the road situation detection part 21; and a travel control part 24 which executes travel control in accordance with the attribute added by the attribute selection part 23.

Description

  The present invention relates to a vehicle travel control apparatus and method.

  Conventionally, it is determined whether an object detected from an image is a predetermined animal other than a pedestrian (for example, a quadruped animal such as a dog or a cat), and the object is a pedestrian or an animal other than a pedestrian. There has been proposed a vehicular travel control device that determines whether or not, and performs, for example, brake control or steering wheel control in accordance with the determination result. In this device, for example, attention is paid to a characteristic part such as a tail of a dog or a cat, and when the characteristic part is detected, the animal is determined to be an animal other than a pedestrian (see Patent Document 1).

JP 2008-21035 A

  As described above, in the apparatus described in Patent Document 1, it is possible to attach attributes such as pedestrians and animals other than pedestrians to moving objects. However, if the moving object is not within the angle of view of the camera, or if the camera is not functioning due to a malfunction, it cannot be determined whether it is a pedestrian or an animal other than a pedestrian.

  The problem of the present invention is not limited to a vehicle equipped with a camera, and whether a moving object is a pedestrian or an animal other than a pedestrian in a vehicle equipped with only a position sensor such as a radar without a camera in the first place. Or the like, and vehicle control according to the attribute cannot be performed.

  The present invention has been made to solve such a conventional problem, and an object of the present invention is to perform vehicle control in accordance with attributes without requiring image processing for attribute assignment of objects. The object is to provide a vehicle travel control apparatus and method.

  The vehicular travel control device of the present invention adds an attribute to the object according to the road condition at the position where the object exists, and executes the travel control according to the added attribute.

  According to the present invention, it is possible to perform attribute assignment according to the possibility of existing depending on road conditions, such as the vicinity of a pedestrian crossing, the vicinity of a road shoulder, and the inside of a roadway. And since the running control according to the attribute added in this way is performed, the vehicle control according to the attribute can be performed without requiring image processing for attribute assignment of the object.

1 is a schematic configuration diagram illustrating a vehicular travel control apparatus according to an embodiment, and illustrates a state in which the vehicle is viewed from above. FIG. 2 is a block diagram showing details of the microprocessor shown in FIG. 1. It is a flowchart which shows the vehicle travel control method which concerns on this embodiment. It is a graph which shows the content of the road condition, the movement of an surrounding object, an attribute, and traveling control. It is a block diagram which shows the detail of the microprocessor which concerns on 2nd Embodiment. It is a flowchart which shows the vehicle travel control method which concerns on 2nd Embodiment. It is a table | surface which shows the content of the road condition of 2nd Embodiment, the motion of a surrounding object, an attribute, and traveling control.

  DESCRIPTION OF EXEMPLARY EMBODIMENTS Hereinafter, preferred embodiments of the invention will be described with reference to the drawings. FIG. 1 is a schematic configuration diagram showing a vehicle travel control apparatus according to the present embodiment, and shows a state in which the vehicle is viewed from above. In this embodiment, when there is no imaging means such as a camera, or even if an imaging means is provided, it is used to acquire information such as signal colors and lanes, and can be used until object attribute determination. It assumes no case. That is, in this embodiment, a technique for adding an attribute to an object from position information by a radar or the like and a road condition without depending on an image will be described.

  As shown in FIG. 1, the vehicle travel control apparatus 1 according to this embodiment includes a camera 11, a relative position sensor (position detection means) 12, a steering angle sensor 13, a car navigation unit 14, and a vehicle speed sensor 15. And a microprocessor 20, a power train controller 31, a brake controller 32, a steering motor controller 33, an engine / drive system 41, a brake unit 42, and a steering assist motor 43.

  The camera 11 captures the front of the host vehicle. The camera 11 is attached to, for example, the upper part of the front window in the passenger compartment. The camera 11 captures surrounding obstacles including traffic lights and road environments such as lanes and captures image information. It is transmitted to the processor 20. Note that, as described above, in the present embodiment, the captured image of the camera 11 is not used for object attribute assignment.

  The relative position sensor 12 is, for example, a laser radar, a raider, or a sonar, and detects the relative position of the surrounding object with respect to the host vehicle and transmits the detected position information to the microprocessor 20. The steering angle sensor 13 is attached to the steering shaft of the vehicle and outputs a signal corresponding to the steering angle of the steering shaft.

  The car navigation unit 14 includes a GPS receiving unit, a road information database, an information processing device, and the like, and mainly performs processing for creating various types of information for route guidance of automobiles. In the present embodiment, the car navigation unit 14 transmits the position information and direction information of the host vehicle to the microprocessor 20.

  The vehicle speed sensor 15 is a rotary encoder attached to the wheel, for example, and measures the vehicle speed by detecting a pulse signal generated in proportion to the rotation of the wheel, and transmits it to the microprocessor 20.

  The microprocessor 20 is an integrated circuit composed of an A / D conversion circuit, a D / A conversion circuit, a central processing unit, a memory, and the like, and assigns attributes to surrounding objects according to a program stored in the memory. The vehicle control according to is performed. In order to realize the vehicle control, the microprocessor 20 transmits the driving force operation amount to the power train controller 31, transmits the braking force operation amount to the brake controller 32, and transmits the steering angle operation amount to the steering motor controller 33. Send.

  The power train controller 31 controls the engine / drive system 41 so as to realize a drive force operation amount. The brake controller 32 controls the brake unit 42 so as to realize the braking force operation amount, and the steering motor controller 33 controls the steering assist motor 43 so as to realize the steering angle operation amount.

FIG. 2 is a block diagram showing details of the microprocessor 20 shown in FIG. As shown in FIG. 2, the microprocessor 20 includes a road condition detection unit (road condition detection unit) 21, an automatic driving unit 22, an attribute selection unit (attribute selection unit) 23, and a travel control unit (travel control unit). 24.

  The road condition detection unit 21 is based on the position information, the direction information of the own vehicle from the car navigation unit 14 and the map information from the map database stored in the memory. It detects surrounding road conditions. The road condition is not limited to the above, and is a concept including road types, road signs, road traffic rules such as one-way traffic, and includes, for example, the vicinity of a temporary stop line. The road condition detection unit 21 may detect the road condition using not only the information of the car navigation unit 14 but also image information acquired by the camera 11.

  In addition to the position, orientation, and speed information of the host vehicle that is obtained based on information from the car navigation unit 14 and the vehicle speed sensor 15, the automatic driving unit 22 reads from the map database stored in the memory of the car navigation unit 14. The route to the set destination is calculated based on the map information. Furthermore, the automatic driving unit 22 determines traffic rules from the color information of the signal obtained by analyzing the image captured by the camera 11, the obstacle position information from the relative position sensor 12, the road condition, and the state of the host vehicle. The target value of the route and speed that realizes the target route without protruding the road is calculated while avoiding the collision with the obstacle.

  The attribute selection unit 23 adds an attribute to the object detected by the relative position sensor 12 according to the road condition. In this embodiment, the attributes are “low-speed human movement” such as pedestrians and bicycles, “high-speed human movement” such as motorcycles and cars, “animals” such as dogs and cats, and “emergency vehicles” such as police cars and ambulances. It is. The attribute is not limited to this.

  The travel control unit 24 executes control related to automatic driving, and in particular in the present embodiment, executes travel control according to the attribute added by the attribute selection unit 23. The travel control unit 24 includes a correction unit 24a and a track correction unit 24b. The correction unit 24a calculates the correction amount of the target route and the speed so that the traveling control according to the added attribute and the road condition is realized. The trajectory correcting unit 24b corrects the target value of the route and speed from the automatic driving unit 22 with the correction amount from the travel control unit 24, and adjusts the steering angle and braking / driving force so as to realize the corrected route and speed. Calculate the target value. For example, the route may be calculated from the target route and the position and orientation of the host vehicle using a forward gaze driver model. Further, the braking / driving force target value may be obtained by, for example, PI control so as to compensate for the difference between the target speed and the actual vehicle speed.

  In such a vehicle travel control device 1, for example, the following operations are realized. First, it is assumed that an object is detected by the relative position sensor 12. Furthermore, it is assumed that the position of the object is near the pedestrian crossing by the road condition detection unit 21. Since the pedestrian crossing is a passage for pedestrians and bicycles, the attribute selection unit 23 adds an attribute of “low-speed person movement” such as pedestrians and bicycles to the object. Then, the traveling control unit 24 temporarily stops in front of the pedestrian crossing in order to comply with the traffic rule that a person who is about to cross the pedestrian crossing should not enter the pedestrian crossing. Thereafter, the traveling control unit 24 stops until the object detected by the relative position sensor 12 and added with the attribute “moving at low speed” passes the pedestrian crossing and starts traveling after the object passes the pedestrian crossing. Or when the object does not pass the pedestrian crossing for a certain period of time.

  Moreover, in the above operation, attribute addition by image processing is not performed, and it is not necessary to perform image processing to determine a person. For this reason, the vehicle control according to the attribute can be performed without requiring a camera.

  Next, the vehicle travel control method of the vehicle travel control apparatus 1 according to the present embodiment will be described. FIG. 3 is a flowchart showing the vehicle travel control method according to the present embodiment. As shown in FIG. 3, the road condition detection unit 21 first detects a road condition (S1). At this time, the road condition detection unit 21 obtains the road condition of the area where the object detected by the relative position sensor 12 exists from the direction of the host vehicle and the relative position to the object. The road conditions are classified into the following four, for example. a) Near a pedestrian crossing, b) A roadway, c) A sidewalk or roadside of a general road, d) A sidewalk or roadside of a motorway.

  Next, the relative position sensor 12 detects the movement of surrounding objects from the relative position of the past object and the relative position of the current object (S2). At this time, the relative position sensor 12 removes the surrounding object from 1) the forward moving object, 2) the forward moving object + the subsequent moving object, 3) the forward stopping object, and 4) the surrounding object slowly approaches the road shoulder. Or at least judge to stop and avoid moving objects.

  Next, the attribute selection unit 23 adds an attribute according to the table shown in FIG. 4 from the road condition of the object position obtained in step S1 and the movement of surrounding objects in step S2 (S3). Then, the process shown in FIG. 3 ends. After the process shown in FIG. 3 is completed, the traveling control unit 24 executes the traveling control according to the attribute added in step S3.

  FIG. 4 is a chart showing road conditions, movements of surrounding objects, attributes, and the content of travel control. As shown in FIG. 4, first, when the position of an object whose attribute is unknown is in the vicinity of a pedestrian crossing, there is a high possibility that the object is a pedestrian or a bicycle who is about to cross the pedestrian crossing. For this reason, the attribute selection unit 23 adds the attribute “low-speed person movement” to an object near the pedestrian crossing. And the traveling control part 24 performs control which stops once before a pedestrian crossing. Thereby, the own vehicle can observe the traffic rule that the person who is going to cross the pedestrian crossing should not enter the pedestrian crossing.

  In addition, when an object with unknown attributes is located on the same roadway as the host vehicle (that is, a road that is not an oncoming lane or a crossing road) and the object is moving forward, the object is a motorcycle or automobile traveling on the same roadway. Is likely. For this reason, the attribute selection unit 23 adds an attribute of “high-speed person movement” to an object moving forward on the same roadway. Then, the travel control unit 24 executes control to travel following the object. Thereby, the own vehicle can implement | achieve following driving | running | working, without performing the attribute addition by image processing.

  Further, when an object with unknown attributes is located on the same roadway as the host vehicle and the host vehicle is overtaken by an object approaching from behind the host vehicle, the object may be an animal moving on the roadway. For this reason, the attribute selection unit 23 adds an “animal” attribute to an object whose attribute is unknown. Here, the animal is uncertain about movement. That is, even if the animal moves forward, the animal may suddenly move laterally or move backward. Therefore, the traveling control unit 24 has overtaken the host vehicle while securing the distance from the object in consideration of the uncertainty of the movement of the animal (that is, securing a larger distance than when overtaking an object other than an animal). Executes the control to follow the legal speed and follow the object. As a result, it is possible to reduce the risk of collision and the like for an object that is difficult to predict the movement of an animal, and to avoid an object without complying with the legal speed and committing a violation.

Further, when an object with unknown attributes is located on the same roadway as the own vehicle and the object is stopped, the object may be an animal that has stopped on the roadway. For this reason, the attribute selection unit 23 adds an “animal” attribute to an object located on the same roadway and stopped. Then, the traveling control unit 24 takes into account the uncertainty of the movement of the animal while ensuring the distance from the object,
Control overtaking the object is executed. As a result, it is possible to reduce the risk of a collision and avoid an object even for an object that is difficult to predict the movement of an animal.

  In addition, when a surrounding vehicle (exactly, an object to which an attribute of high-speed human movement is added) approaches the shoulder of the road and stops or slows down, and an object of unknown attribute is approaching from the rear of the own vehicle, the object is There is a high possibility that it is an emergency vehicle such as a police car or an ambulance. For this reason, the attribute selection unit 23 adds the attribute of “emergency vehicle” to an object approaching from behind in a state where the surrounding vehicle is stopped or slowing down toward the road shoulder. Then, the traveling control unit 24 performs control to bring the host vehicle closer to the road shoulder so that the object can pass the host vehicle. As a result, it is possible to comply with a traffic rule that the progress of an emergency vehicle such as an ambulance must not be hindered.

  In addition, when an object whose attribute is unknown is located on a roadside or a sidewalk on a general road, the object may be an animal. Therefore, the attribute selection unit 23 adds an “animal” attribute to an object located on the roadside or on the sidewalk on the roadside. Then, the traveling control unit 24 executes control for overtaking the object while securing the distance from the object in consideration of the uncertainty of the movement of the animal. Here, if the attribute of “moving at low speed” such as a person is added to an object located on the roadside or sidewalk, if the object is actually an animal, Animals can jump out of contact and touch. However, by adding the “animal” attribute as described above, it is possible to perform traveling control in consideration of the jumping out of the animal, and to further reduce the risk of collision and avoid an object.

  In addition, when an object with unknown attributes is located on the side of a road dedicated to automobiles, it is highly likely that the object is a motorcycle. For this reason, the attribute selection unit 23 adds an attribute of “high-speed movement” to an object located on the side of the road dedicated to the automobile. Then, the travel control unit 24 executes control to travel following the object. Thereby, the own vehicle can implement | achieve following driving | running | working, without performing the attribute addition by image processing.

  Thus, according to the vehicle travel control apparatus 1 and the method according to the present embodiment, an attribute is added to the object according to the road situation at the position where the object exists, for example, near a pedestrian crossing. Attribute assignment according to the possibility of existing depending on the road condition, such as near the shoulder of a road or in a roadway, can be performed. And since the running control according to the attribute added in this way is performed, the vehicle control according to the attribute can be performed without requiring image processing for attribute assignment of the object.

  In addition, if it is determined that an object with unknown attributes is located near the pedestrian crossing, an attribute of low-speed movement indicating that the object is a self-propelled person including pedestrians and bicycles is added to the object, and the object before the pedestrian crossing is added. To stop the vehicle. For this reason, it is possible to observe the traffic rule that a person who is going to cross a pedestrian crossing should not enter the pedestrian crossing.

  In addition, when it is determined that an object with unknown attributes is located on the same roadway ahead of the host vehicle and the object is moving forward, an object that self-runs at high speed, including a motorcycle and a car, with respect to the object. An attribute of high-speed human movement indicating that the vehicle is moving is added, and control for traveling following the object is executed. Therefore, when the vehicle ahead is traveling as usual, the vehicle can automatically travel following the vehicle.

If it is determined that an object with unknown attributes is located on the same roadway ahead of the host vehicle and the host vehicle is overtaken by an object approaching from behind the host vehicle, an animal attribute is added to the object. Then, while keeping the distance from the object to which the animal attribute is added, the vehicle follows the object while following the legal speed to execute the control for overtaking the object. For this reason, it is possible to reduce the risk of a collision or the like even for an object whose movement is difficult to predict, and to avoid an object without complying with the legal speed and committing a violation.

  If an object with unknown attributes is located on the same roadway ahead of the host vehicle and the object is determined to be stopped, an animal attribute is added to the object, and the movement of the animal is uncertain. In consideration of the above, the control for overtaking the object is executed while securing the distance from the object to which the animal attribute is added. For this reason, if it is estimated that there is a high possibility that the vehicle is stopped on the road, such as a cat, an attribute of the animal is assigned, and in such a case, a distance considering the uncertainty of the movement of the animal is secured. Overtaking the object. Therefore, it is possible to reduce the risk of collision and avoid an object even for an object whose movement is difficult to predict.

  In addition, when it is determined that an object of unknown attribute is approaching from the rear of the host vehicle when the surrounding vehicle stops near the road shoulder or slows down, an attribute of an emergency vehicle including a police car and an ambulance is added to the object, Control to bring the vehicle close to the road shoulder is executed. For this reason, it is possible to observe the traffic rule that the progress of an emergency vehicle such as an ambulance must not be hindered.

  If it is determined that an object with unknown attributes is located on the roadside or on the sidewalk, add the animal attribute to the object and consider the animal's movement uncertainty. The control for overtaking the object is executed while securing the distance from the added object. In this way, it is possible not only to attribute pedestrians with a low possibility of sudden jumping out, but by assigning animals that can also jump suddenly, the risk of collision can be further reduced, Objects can be avoided.

  If it is determined that an object with unknown attributes is located on the road for exclusive use of an automobile, an attribute of high-speed human movement is added to the object, and control for traveling following the object is executed. For this reason, in a road situation where there is a very low possibility that a pedestrian or the like called an automobile-only road is present, it is possible to automatically follow the vehicle by assigning an attribute such as a vehicle.

  Next, a second embodiment according to the present invention will be described. The vehicular travel control device and method according to the second embodiment are the same as those of the first embodiment, but the configuration and processing contents are partially different. Hereinafter, differences from the first embodiment will be described.

  In the vehicular travel control apparatus 1 and method according to the first embodiment, the captured image is not used for attribute addition. However, in the vehicular travel control apparatus 2 and method according to the second embodiment, an image is captured by the camera 11. A function of adding an attribute based on the generated image.

  More specifically, in the vehicle travel control apparatus 2 and method according to the second embodiment, the relative position detection sensor 12 is configured by a laser range finder or the like, and the relative position is larger than the viewing angle of the camera (imaging means) 11. The detection range of the sensor 12 is widened. Furthermore, in the second embodiment, the attribute of the object is detected by image processing, and the object moves within the detection range of the relative position sensor 12 but out of the viewing angle of the camera 11 and intersects with another object. Even in this case, it is possible to perform traveling control based on attributes. That is, for example, after a dog and a person cross each other, it is unclear whether each object is a dog or a person. In such a case, traveling control based on attributes can be performed.

  FIG. 5 is a block diagram showing details of the microprocessor 20 according to the second embodiment. As shown in FIG. 5, in the second embodiment, the microprocessor 20 includes an image processing unit (image processing unit) 25, an attribute association unit (attribute association unit) 26, and an attribute holding unit (attribute association unit). 27 is further provided.

The image processing unit 25 detects a position and an attribute of an object in a captured image obtained by the camera 11. For the detection of the position and the attribute, the method described in Japanese Patent Application Laid-Open No. 2008-21035 and other known methods are employed.

  When the attribute linking unit 26 determines that each object is the same object based on the position of the object detected by the image processing unit 25 and the position of the object detected by the relative position sensor 12, The attribute detected by the image processing unit 25 is given to the object detected by the relative position sensor 12.

  The attribute holding unit 27 is provided by the attribute linking unit 26 as long as the object to which the attribute is assigned by the attribute linking unit 26 is detected by the relative position sensor 12 even if the object moves outside the field of view of the camera 11. Holds attributes. As the attribute holding unit 27 holds the attribute in this way, the attribute does not become unknown as long as it is detected by the relative position sensor 12 even if it moves out of the field of view, and according to the attribute as in the first embodiment. Traveling control can be performed.

  However, if the object intersects with a plurality of objects within the detection range of the relative position sensor 12 but outside the viewing angle of the camera 11, the attributes of each object become unclear. Therefore, in the vehicle travel control apparatus 2 and method according to the present embodiment, attributes are added as follows, and travel control according to the attributes is realized.

  In other words, the attribute of the crossed objects as described above is unknown, but the position is revealed by the relative position sensor 12. For this reason, the road situation detection unit 21 detects the road situation at the crossed object position, and the attribute selection unit 23 adds an attribute to each of the crossed objects.

  In addition, when adding attributes, for example, when the attributes of the crossed objects are “low-speed human movement” and “animal”, one attribute of the crossed objects is “low-speed human movement” or “animal”. Yes, it can be said that the other attribute of the crossed object is also “low-speed movement” or “animal”. Therefore, in the second embodiment, it is not necessary to narrow down one attribute from four attributes. In the above example, one attribute can be narrowed down from two attributes, and the accuracy of attribute addition can be increased.

  Next, a vehicle travel control method of the vehicle travel control apparatus 2 according to the second embodiment will be described. First, the image processing unit 25 detects an object in the captured image and adds an ID number to each object. Furthermore, the image processing unit 25 detects an object in the captured image at the next time, and adds the same ID number as the ID number added at the previous time to an object that can be determined to be the same object as the previous time. The same applies to the relative position sensor 12, and an object is detected and an ID number is added to each object, and an object that can be determined to be the same object at the next time is the same as the ID number added at the previous time. Add an ID number.

  In addition to the ID number, the image processing unit 25 and the relative position sensor 12 provide object position information (vertical and horizontal position information) and size information (at least width information). , And camera viewing angle out-of-view flag information. Furthermore, the image processing unit 25 and the relative position sensor 12 associate attribute flag information or attribute information with each object.

  Here, the attribute flag information is information indicating an attribute as an option when adding the attribute. For example, when an object to which the attribute of “low-speed human movement” is added and an object to which the attribute of “animal” is added, the attribute flags of “low-speed human movement” and “animal” are set for each object. Information is added. The attribute information is information indicating the added attribute.

  FIG. 6 is a flowchart showing a vehicle travel control method according to the second embodiment. First, the microprocessor 20 extracts an object that cannot be recognized by the camera 11 but can be recognized by the relative position sensor 12 (S11). In more detail, the microprocessor 20 lowers the camera out-of-view angle flag for an object that can be recognized by the camera 11. Therefore, the camera viewing angle outside flag information of the object that can be recognized by the camera 11 is “flag reduction”.

  On the other hand, for an object that cannot be recognized by the camera 11 but can be recognized by the relative position sensor 12, the camera viewing angle outside flag is raised. Therefore, the camera viewing angle out-of-view flag information of the object that cannot be recognized by the camera 11 is “flag up”.

  Next, the microprocessor 20 extracts an object in which crossing has occurred among objects whose camera viewing angle out-of-view flag information is “flag up” (S12). In this process, the attribute flag information is updated. For example, for an object to which the attribute of “low-speed person movement” is added by image processing, the attribute of “low-speed person movement” is added by the attribute linking unit 26 and the attribute holding unit 27 even if the object is moved to the viewing angle of the camera 11. It is held as it is. For this reason, when an object having the attribute of “low-speed human movement” and an object having the attribute of “animal” are crossed, “low-speed human movement” and “animal” Attribute flag information is added.

  Furthermore, in the second embodiment, there is also an object detected for the first time by the relative position sensor 12. With respect to such an object, the second embodiment may perform the same processing as in the first embodiment to add an attribute, or may not add an attribute and perform “low-speed person movement” and “high-speed person movement”. Attribute flag information of “animal” and “emergency vehicle” may be added. When attributes are added by performing the same processing as in the first embodiment, attribute flag information such as “low-speed movement” and “animal” is added to each object in the same manner as described above. On the other hand, when the attribute flag information of “low-speed person movement”, “high-speed person movement”, “animal” and “emergency vehicle” is added without adding the attribute, this object is not only crossed with such an object. Also for the object, attribute flag information of “low-speed human movement”, “high-speed human movement”, “animal”, and “emergency vehicle” is added.

  Next, in step S13 and step S14, the road condition detection unit 21 detects the road condition of the crossed object (S13), and the relative position sensor 12 detects the movement of surrounding objects (S14). This process is the same as the process of steps S1 and S2 shown in FIG.

  Thereafter, the attribute selection unit 23 adds an attribute to the mixed object from the attribute flag information updated in step S12, the road condition of the object position obtained in step S13, and the movement of surrounding objects in step S14 ( S15). And the process shown in FIG. 6 is complete | finished, and the traveling control part 24 performs traveling control based on the added attribute.

  For example, if the attribute flag information of a crossed object is “low-speed person movement” and “animal” and the road condition of the object is near a pedestrian crossing, the attribute selection unit 23 sets “low-speed person” to the object. Add "move" attribute. This is because priorities are determined in advance, and the attribute selection unit 23 adds attributes based on the priorities.

  Further, in the second embodiment, since an attribute is captured by the camera 11 and an attribute is added, for example, an object to which an attribute of “emergency vehicle” is added based on a captured image of the camera 11 and an attribute of “high-speed human movement” are There is also a possibility that the added object crosses near the pedestrian crossing outside the viewing angle of the camera 11. In such a case, the attribute selection unit 23 adds an attribute of “high-speed movement” based on the priority order.

FIG. 7 is a chart showing the road conditions, the movements of surrounding objects, attributes, and the content of travel control according to the second embodiment. In the attribute column of FIG. ~ 4. The numbers indicate the above-mentioned priorities. Is the highest priority. Has the lowest priority. In other words, when priority level 1 and priority level 2 are included in the attribute flag information of a crossed object, the priority level 1 attribute is added to the object.

  As shown in FIG. 7, when the crossed object is located in the vicinity of the pedestrian crossing, the attribute selection unit 23 performs the crossing in the priority order of “low-speed person movement”, “high-speed person movement”, “animal”, and “emergency vehicle”. Attributes are added to the selected object. Then, when the attribute of “low-speed person movement” is added to the object, the traveling control unit 24 performs control to temporarily stop before the pedestrian crossing. In addition, when the attributes of “high-speed human movement”, “animal”, and “emergency vehicle” are added to the object, the traveling control unit 24 executes control as follows. For the attribute of “high-speed human movement”, control for following the object is executed. For the attribute of “animal”, for example, a collision risk range is estimated as a dog, and control for avoiding the range and overtaking is executed. For the “emergency vehicle” attribute, control is performed to stop the vehicle while approaching the shoulder.

  In addition, when the mixed object is moving forward on the same roadway as the host vehicle, the attribute selection unit 23 sets the priority in the order of “high-speed person movement”, “low-speed person movement”, “animal”, and “emergency vehicle”. Add attributes to the crossed objects. Then, when the attribute “high-speed human movement” is added to the object, the traveling control unit 24 executes control to follow the object, and the attributes “low-speed human movement”, “animal”, and “emergency vehicle” are added. If so, control is executed as follows. For the attribute of “low-speed human movement”, control to overtake the object is executed. For the attribute of “animal”, for example, a collision risk range is estimated as a dog, and control for avoiding the range and overtaking is executed. For the “emergency vehicle” attribute, control is performed to stop the vehicle while approaching the shoulder.

  Further, the attribute selection unit 23 is configured such that when the crossed object is located on the same roadway as the own vehicle and the own vehicle is overtaken by an object approaching from behind the own vehicle, the “animal”, “low-speed person movement”, and “high-speed person movement” ”And“ emergency vehicle ”, an attribute is added to the object that intersects with priority. Then, when the attributes of “animal” and “low-speed human movement” are added to the object, the traveling control unit 24 estimates the collision risk range, and executes control to avoid the range and overtake the object. When the attribute of “person movement” is added, control to follow the object is executed. When the attribute of “emergency vehicle” is added, control is performed to stop the vehicle while approaching the shoulder.

  In addition, the attribute selection unit 23 selects “animal”, “low-speed person movement”, “high-speed person movement”, and “emergency vehicle” when the crossed object is located on the same roadway as the own vehicle and the object is stopped. Add attributes to objects that are interlaced in order of priority. Then, the traveling control unit 24 executes control to overtake the object regardless of which attribute is added.

  In addition, the attribute selection unit 23 stops or slows down the surrounding vehicle close to the road shoulder, and when the mixed object approaches from the rear of the own vehicle, “emergency vehicle” “high-speed person movement” “low-speed person movement” And an attribute is added to the object which has been interlaced in the order of priority of “animal”. And the traveling control part 24 performs control which brings the own vehicle close to the road shoulder, regardless of which attribute is added.

  In addition, when the crossed object is located on the side of the road or on the sidewalk on the road, the attribute selection unit 23 selects “animal”, “low-speed person movement”, “high-speed person movement”, and “emergency vehicle”. Add attributes to objects that are interlaced in priority order. Then, the traveling control unit 24 executes control to overtake the object regardless of which attribute is added.

Further, the attribute selection unit 23, in the case where the crossed object is located on the roadside or sidewalk of the road for exclusive use of the automobile, in the order of “high-speed person movement” “emergency vehicle” “animal” and “low-speed person movement” Attributes are added to objects that are interlaced in the priority order. Then, when the attributes “high-speed human movement” and “emergency vehicle” are added to the object, the traveling control unit 24 executes control to follow the object, and attributes “animal” and “low-speed human movement”. When is added, control to overtake the object is executed.

  Thus, according to the vehicle travel control device 2 and the method according to the second embodiment, the same effects as all the effects described in the first embodiment can be obtained. For example, it is possible to perform vehicle control in accordance with attributes without requiring image processing for attribute assignment of objects. In addition, it is possible to comply with a traffic rule that a person who is trying to cross a pedestrian crossing should not enter the pedestrian crossing. Further, when the vehicle ahead is traveling as usual, the vehicle can automatically travel following this. In addition, it is possible to reduce the risk of collision and the like for an object that is difficult to predict the movement of an animal, and to avoid an object without complying with the legal speed and committing a violation. Furthermore, it is possible to comply with a traffic rule that an emergency vehicle such as an ambulance must not be obstructed.

  Furthermore, according to the second embodiment, the position and attribute of an object in the captured image are detected, and when the object cannot be captured, the detected attribute is retained, and the object having the attribute is interlaced. In this case, an attribute is added to the object in accordance with the road condition at the position where the intersecting object exists. For this reason, when the attributed object crosses outside the imaging range, it is usually unclear to which attribute each of the crossed object can be assigned, but even in such a case, the road situation By performing the attribute assignment based on, the attribute is not unknown and vehicle control according to the attribute can be performed.

  As described above, the present invention has been described based on the embodiments, but the present invention is not limited to the above-described embodiments, and modifications may be made without departing from the spirit of the present invention. For example, in this embodiment, there are four attributes of “low-speed person movement”, “high-speed person movement”, “animal”, and “emergency vehicle”, but the number may be three or less, or may be five or more. Good.

  In addition, the attributes detected by the image processing unit 25 in the second embodiment are not limited to “low-speed human movement”, “high-speed human movement”, “animal”, and “emergency vehicle”, but “low-speed human movement” such as “child” and “adult”. ”May be subdivided, or“ high-speed human movement ”such as“ large truck ”and“ passenger car ”may be subdivided. Furthermore, “animal” and “emergency vehicle” may be subdivided. Note that for an object to which the attribute “child” is added by image processing, the attribute linking unit 26 may also assign the attribute “child” to the object, or the attribute “low-speed person movement”. It may be given. Furthermore, the attribute holding unit 27 may add the attribute “move low-speed person” to the object at the timing when the object to which the attribute “child” is added is moved outside the viewing angle of the camera 11 by image processing. .

DESCRIPTION OF SYMBOLS 1 ... Vehicle travel control apparatus 11 ... Camera (imaging means)
12 ... Relative position sensor (position detection means)
DESCRIPTION OF SYMBOLS 13 ... Steering angle sensor 14 ... Car navigation unit 15 ... Vehicle speed sensor 20 ... Microprocessor 21 ... Road condition detection part (road condition detection means)
22 ... Automatic driving unit 23 ... Attribute selection unit (attribute selection means)
24 ... Travel control unit (travel control means)
24a ... Correction unit 24b ... Trajectory correction unit 25 ... Image processing unit (image processing means)
26 ... attribute linking unit (attribute linking means)
27 ... Attribute holding unit (attribute linking means)
31 ... Powertrain controller 32 ... Brake controller 33 ... Steering motor controller 41 ... Engine / drive system 42 ... Brake unit 43 ... Steering assist motor

Claims (10)

Position detecting means for detecting the position of an object around the vehicle;
Road condition detection means for detecting the road condition;
Attribute selection means for adding an attribute to the object detected by the position detection means according to the road situation of the position where the object detected by the road situation detection means exists;
Travel control means for executing travel control according to the attribute added by the attribute selection means;
A vehicle travel control device comprising: The attribute selection means is a self-running person including a pedestrian and a bicycle with respect to the object when the position detection means and the road condition detection means determine that the object with unknown attribute is located near the pedestrian crossing. Add the attribute of slow movement to indicate that
2. The vehicle according to claim 1, wherein when the attribute of the low-speed person movement is added by the attribute selection unit, the travel control unit performs control to temporarily stop the host vehicle in front of a pedestrian crossing. Travel control device. The attribute selection means, when the position detection means and the road condition detection means determine that the object whose attribute is unknown is located on the same road ahead of the host vehicle and the object is moving forward, Add an attribute of high-speed human movement indicating that the object is a self-propelled object including a motorcycle and a car,
3. The vehicle according to claim 1, wherein the traveling control unit performs control of traveling following the object to which the attribute of the high-speed human movement is added by the attribute selecting unit. Travel control device. The attribute selecting means includes the position detecting means and the road condition detecting means in which an object whose attribute is unknown is located on the same road ahead of the host vehicle and the host vehicle is overtaken by an object approaching from the rear of the host vehicle. If it is determined that the animal has an animal attribute,
The travel control means observes the legal speed for an object that has passed the own vehicle while ensuring the distance from the object to which the animal attribute is added by the attribute selection means in consideration of the uncertainty of the movement of the animal. The vehicle travel control device according to any one of claims 1 to 3, wherein control for overtaking the object is performed by following the vehicle. If the attribute selecting means determines that the object with unknown attribute is located on the same road ahead of the host vehicle and the object is stopped by the position detecting means and the road condition detecting means, Add animal attributes to
The travel control means executes control for overtaking the object while ensuring the distance from the object to which the animal attribute is added by the attribute selection means in consideration of the uncertainty of the movement of the animal. The vehicle travel control apparatus according to any one of claims 1 to 4. The attribute selection means, when the position detection means and the road condition detection means determine that the surrounding vehicle stops or slows down on the shoulder of the road, and that an object with unknown attributes is approaching from behind the host vehicle, Add the attributes of emergency vehicles including police cars and ambulances to the object,
6. The control according to claim 1, wherein the travel control unit performs control in which the object to which the attribute of the emergency vehicle is added is overtaken by the attribute selection unit after the host vehicle is brought close to a road shoulder. The vehicle travel control device according to claim 1. The attribute selection means adds an animal attribute to the object when the position detection means and the road condition detection means determine that an object with unknown attributes is located on a roadside or a sidewalk on the roadside. And
The travel control means executes control for overtaking the object while ensuring the distance from the object to which the animal attribute is added by the attribute selection means in consideration of the uncertainty of the movement of the animal. The vehicle travel control apparatus according to any one of claims 1 to 6. The attribute selecting means, when the position detecting means and the road condition detecting means determine that an object with unknown attribute is located on a road for exclusive use of an automobile, adds an attribute of high-speed human movement to the object,
8. The control according to claim 1, wherein the traveling control unit performs control of traveling following the object to which the attribute of the high-speed human movement is added by the attribute selection unit. Vehicle travel control device. Imaging means for imaging the surroundings of the vehicle;
Image processing means for detecting a position and an attribute of an object in a captured image obtained by the imaging means;
Based on the position of the object detected by the image processing means and the position of the object detected by the position detection means, it is detected by the position detection means when it is determined that each object is the same object. Attribute association means for assigning an attribute detected by the image processing means to the object,
Attribute holding that holds the attribute given by the attribute linking means as long as the object having the attribute given by the attribute linking means is detected by the position detecting means even if it moves out of the field of view of the imaging means Means, and further,
The attribute selecting means, when an object whose attribute is held by the attribute holding means is crossed, depending on the road situation of the position where the crossed object detected by the road situation detecting means exists, The vehicle travel control apparatus according to any one of claims 1 to 8, wherein an attribute is added. A position detection step for detecting the position of an object around the vehicle;
A road condition detection process for detecting road conditions;
An attribute selection step of adding an attribute to the object according to the road situation of the position where the object detected in the road situation detection step is present in the object detected in the position detection step;
A travel control step for executing travel control according to the attribute added in the attribute selection step;
A vehicular travel control method comprising:

Images