WO2023149003A1 - 車両制御装置 - Google Patents
車両制御装置 Download PDFInfo
- Publication number
- WO2023149003A1 WO2023149003A1 PCT/JP2022/032103 JP2022032103W WO2023149003A1 WO 2023149003 A1 WO2023149003 A1 WO 2023149003A1 JP 2022032103 W JP2022032103 W JP 2022032103W WO 2023149003 A1 WO2023149003 A1 WO 2023149003A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- lane
- vehicle
- information
- grid
- risk
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Ceased
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/08—Active safety systems predicting or avoiding probable or impending collision or attempting to minimise its consequences
- B60W30/09—Taking automatic action to avoid collision, e.g. braking and steering
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/167—Driving aids for lane monitoring, lane changing, e.g. blind spot detection
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2552/00—Input parameters relating to infrastructure
- B60W2552/10—Number of lanes
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W2556/00—Input parameters relating to data
- B60W2556/40—High definition maps
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W60/00—Drive control systems specially adapted for autonomous road vehicles
- B60W60/001—Planning or execution of driving tasks
- B60W60/0027—Planning or execution of driving tasks using trajectory prediction for other traffic participants
Definitions
- FIG. 1 is a functional block diagram showing the configuration of a vehicle system including a vehicle control device according to an embodiment of the present invention
- FIG. FIG. 4 is a diagram showing the correlation of processes performed in the vehicle control device
- Explanatory diagram of lane grid map generation processing Diagram showing an example of lane grid map data group Flowchart for explaining processing executed by the lane risk map generator
- a diagram showing a specific example of collision risk calculation processing with latent obstacles Flowchart for explaining processing executed by the travel control planning unit Diagram showing specific examples of trajectory generation, evaluation, and correction
- the vehicle control device 3 is an ECU (Electronic Control Unit) that is mounted on the vehicle 2 and performs arithmetic processing for driving support and travel control of the vehicle 2 .
- the vehicle control device 3 controls driving for driving assistance or automatic driving of the vehicle 2 based on various input information provided from the external sensor group 4, the vehicle sensor group 5, the map information management device 6, the external communication device 9, and the like. It generates control information and outputs it to the actuator group 7 and the HMI device group 8 .
- the external sensor group 4 is a collection of devices that detect the surrounding conditions of the vehicle 2 .
- Various sensors such as a camera device, millimeter wave radar, LiDAR, and sonar correspond to the external sensor group 4, for example.
- the external sensor group 4 detects environmental elements such as obstacles, road markings, signs, and signals around the vehicle 2 and outputs these detection results to the vehicle control device 3 via the in-vehicle network N.
- the external sensor group 4 cannot necessarily detect all obstacles existing around the vehicle 2, and obstacles hidden in the blind spots of the vehicle 2 cannot be detected.
- an obstacle that can be detected by the external sensor group 4 and that can hinder the running of the vehicle 2 will be referred to as an "existing obstacle".
- a latent obstacle that cannot be detected by the external sensor group 4 and that is hidden in a blind spot and may come out toward the vehicle 2 is called a "latent obstacle”.
- Both actual obstacles and latent obstacles are sometimes simply referred to as "obstacles". These obstacles include, for example, other vehicles other than the vehicle 2, pedestrians, objects falling onto the road, roadsides, and the like.
- the "road markings" are, for example, white lines, pedestrian crossings, stop lines, etc. drawn on the road surface.
- the external sensor group 4 may also output information regarding the detection state of each environmental element to the vehicle control device 3 via the in-vehicle network N based on its own sensing range and its state.
- the vehicle sensor group 5 is a collection of devices that detect various states of the vehicle 2 . Each vehicle sensor detects, for example, the position information of the vehicle 2, the traveling speed, the steering angle, the accelerator operation amount, the brake operation amount, etc., and outputs them to the vehicle control device 3 via the in-vehicle network N.
- FIG. 1 the position information of the vehicle 2, the traveling speed, the steering angle, the accelerator operation amount, the brake operation amount, etc., and outputs them to the vehicle control device 3 via the in-vehicle network N.
- the map information management device 6 is a device that manages and provides digital map information around the vehicle 2 .
- the map information management device 6 is configured by, for example, a navigation device or the like.
- the map information management device 6 has, for example, digital road map data of a predetermined area including the surroundings of the vehicle 2, and based on the position information of the vehicle 2 output from the vehicle sensor group 5, etc., the vehicle 2 on the map. , that is, the road or lane on which the vehicle 2 is traveling.
- the current position of the identified vehicle 2 and map data of its surroundings are output to the vehicle control device 3 via the in-vehicle network N.
- the actuator group 7 is a device group that controls control elements such as steering, braking, and accelerator that determine the movement of the vehicle 2 .
- Actuator group 7 controls movements of control elements such as steering, brake, accelerator, etc., based on operation information of the steering wheel, brake pedal, accelerator pedal, etc. by the driver and control command values output from vehicle control device 3. Thus, the behavior of the vehicle 2 is controlled.
- the HMI device group 8 is a device group for inputting information from the driver and passengers to the vehicle system 1 and for notifying the driver and passengers of information from the vehicle system 1 .
- the HMI device group 8 includes a display, speaker, vibrator, switch, and the like.
- the existing obstacle prediction unit 12 predicts the future behavior of existing obstacles around the vehicle 2. For example, assuming that the actual obstacle is traveling along the current lane, the future position and speed of the actual obstacle are predicted using the lane information represented by the road environment data group 32 .
- the prediction result of the behavior of the existing obstacle by the existing obstacle prediction unit 12 is stored in the storage unit 30 as the existing obstacle prediction data group 34 .
- the vehicle information data group 31 is a set of data regarding the behavior of the vehicle 2 detected by the vehicle sensor group 5 and the like.
- the data related to the behavior of the vehicle 2 is information representing the movement, state, etc. of the vehicle 2. For example, information such as the position of the vehicle 2, the traveling speed, the steering angle, the amount of accelerator operation, the amount of brake operation, and the travel route. is included.
- the road environment data group 32 is a set of data related to the road environment around the vehicle 2.
- the data on the road environment is information on roads around the vehicle 2 including the road on which the vehicle 2 is traveling. This includes, for example, information on the shape and attributes (advance direction, speed limit, travel regulation, etc.) of the lanes that make up the road around the vehicle 2, traffic signal information, and traffic conditions (average speed, etc.) on each road and lane. Information, statistical knowledge information based on past cases, etc. are included.
- Static information such as road/lane shapes and attributes is included in map information acquired from the map information management device 6 or the like, for example.
- quasi-dynamic or dynamic information such as signal information, traffic information, and statistical knowledge information is acquired via the external world communication device 9 .
- Statistical knowledge information includes, for example, information on geographical locations and time zones where there are many accident cases, information on the types of accidents, and the like. Note that the road environment data group 32 may not include all of these pieces of information.
- the actual obstacle prediction data group 34 is a set of information regarding the future behavior of each actual obstacle detected by the external sensor group 4, predicted by the actual obstacle prediction unit 12.
- the information on the future behavior of the existing obstacle includes, for example, information on the running state (position, traveling direction, running speed, etc.) of the existing obstacle at fixed time intervals from now until several seconds later.
- the actual obstacle prediction data group 34 is generated and stored by the actual obstacle prediction section 12 based on the road environment data group 32 and the sensor recognition data group 33 acquired by the information acquisition section 11 .
- the blind area data group 35 is a set of data relating to the blind area, which means an area around the vehicle 2 that is not included in the detection range of the external sensor group 4, that is, an area where the external sensor group 4 cannot detect sensing information. be. An example of representation of data regarding the blind area will be described later with reference to FIG.
- the blind area data group 35 is generated and stored by the blind area identification unit 13 based on the information of the sensor recognition data group 33 acquired by the information acquisition unit 11 .
- the communication unit 40 has a function of communicating with other devices connected via the in-vehicle network N.
- the communication unit 40 includes, for example, a network card conforming to communication standards such as IEEE802.3 and CAN (Controller Area Network).
- the communication unit 40 transmits and receives data based on various protocols between the vehicle control device 3 and other devices in the vehicle system 1 .
- the information acquisition unit 11 acquires necessary information from other devices via the in-vehicle network N and stores it in the storage unit 30 . Specifically, the information of the vehicle information data group 31 from the vehicle sensor group 5, the information of the road environment data group 32 from the map information management device 6 and the external world communication device 9, and the sensor recognition data from the external world sensor group 4 Each information of the group 33 is acquired, stored in the storage unit 30, and transferred to the subsequent processing unit.
- the existing obstacle prediction unit 12 predicts future information on existing obstacles around the vehicle 2, and based on the prediction result.
- the emergent obstacle prediction data group 34 is stored in the storage unit 30 and transferred to the lane risk map generation unit 15 .
- the predicted future information of an actual obstacle includes, for example, a set of future travel information (position, traveling direction, travel speed, etc.) of an actual obstacle at fixed time intervals from the present to several seconds later.
- the future information of existing obstacles is based, for example, on the representative information of the lane shape (for example, lane center line) included in the road environment data group 32 and the position information of the existing obstacles included in the sensor recognition data group 33. Then, the position, direction of travel, and speed of the obstacle can be obtained by predicting the position, traveling direction, and traveling speed of the obstacle along the representative information of the lane shape.
- the road on which the vehicle 2 is traveling consists of three lanes (L0 to L2), and the vehicle 2 travels in the middle lane L1.
- Curves 300, 310, 320 indicate the centerlines of lanes L0-L2, respectively.
- the concept of lane grid map generation based on the road shape and the position of the vehicle 2 will be described with reference to FIGS. 3(b) and 3(c).
- step S503 the lane risk map generation unit 15 generates the actual obstacle based on the lane grid map data group 36 generated by the lane grid map generation unit 14 and the prediction information of the actual obstacle selected in step S502. Calculate the time it takes for an object to reach each grid point on the lane grid map. For example, using predicted information (position, running speed, etc.) of the actual obstacle and the road distance obtained from the xy coordinates of each grid point in the same manner as in step S501, the actual obstacle to each grid point is calculated. You can calculate arrival time. Unlike step S501, in step S503, it is not necessary to calculate the arrival time to all grid points. , it is only necessary to calculate the arrival time to each grid point on the lane determined to be possible.
- step S505 the lane risk map generating unit 15 determines whether or not the existing obstacle prediction data group 34 generated by the existing obstacle predicting unit 12 includes prediction information of an emerging obstacle to be selected next. determine whether If the existing obstacle prediction data group 34 includes prediction information of an unselected emerging obstacle, it is determined that there is prediction information of an emerging obstacle to be selected next, and the process returns to step S502, and steps S502 and after. By repeating the process of S505, the collision risk for the next actual obstacle is calculated. On the other hand, if the prediction information of all the existing obstacles has been selected in the existing obstacle prediction data group 34, the process moves to step S506.
- step S507 the lane risk map generator 15 selects one of the lanes included in the road on which the vehicle 2 travels in the lane grid map data as the lane L to be analyzed.
- the lane IDs included in the lane grid map data group 36 are selected one by one in order, and the selection result is passed to step S508, thereby selecting the lane L to be analyzed.
- step S509 the lane risk map generation unit 15 virtually generates a latent obstacle on the boundary of the blind area based on the boundary points of the blind area identified in step S508.
- Generate forecast information considering the possibility that a latent obstacle will pop out toward the vehicle 2 from the blind spot area, for example, the position, geometric shape, popping speed, driving lane, etc. of the latent obstacle are predicted, and these prediction results are expressed.
- Generate forecast information At this time, for example, by referring to the road environment data group 32, the details of the road regulation (running speed limit, direction of orientation, etc.) on which the vehicle 2 is traveling are acquired, and based on this, the behavior of the potential obstacle is predicted. You may
- step S501 the lane risk map generator 15 determines the time when the own vehicle 2 reaches each grid point of each lane L0, L1, L2 of the road on which the own vehicle 2 is traveling as the intrusion start time of the own vehicle 2. The end point is calculated for each grid point and stored.
- step S ⁇ b>502 the lane risk map generator 15 selects prediction information about the other vehicle 600 from the existing obstacle prediction data group 34 .
- information indicating that other vehicle 600 will travel along lane L2 at the same speed as at present is selected as the prediction information of other vehicle 600 .
- step S504 the lane risk map generator 15 compares the intrusion start and end times of the own vehicle 2 and the other vehicle 600 stored in steps S501 and S503 for each grid point.
- Grid points whose periods up to the end point overlap are stored as grid points at which there is a risk of collision with an apparent obstacle.
- black dots 622-1 to 624-1 indicate grid points at which there is a risk of collision with an actual obstacle.
- a grid point 624-2 far from the own vehicle 2 is a grid point with no collision risk.
- the grid point 621-1 on the side of the own vehicle 2 is a grid point with no collision risk
- a certain grid point 621-2 is calculated as a grid point at which there is a risk of collision with an actual obstacle.
- step S511 the lane risk map generator 15 converts the arrival time information of the own vehicle 2 calculated in step S501 and the arrival time information of the virtual vehicles 741 and 742 calculated in step S510 to each grid point.
- each grid point where the periods from the entry start point to the end point of the host vehicle 2 and the virtual vehicles 741 and 742 overlap. are stored as grid points at risk of collision with potential obstacles.
- each grid point 702 on lane L0 and each grid point 722 on lane L2 are stored as grid points at which there is a risk of collision with a potential obstacle. Since one lane is selected at a time as a lane to be analyzed in step S507, the processing for lane L0 and the processing for lane L2 are performed in separate processing cycles.
- the lane risk map generation unit 15 generates the collision risks of actual and potential obstacles at each grid point of the lane grid map and blind spot information by the above-described processing described with reference to FIGS. . Finally, as described in step S513 of FIG. 5, these pieces of information are combined to generate and store the lane risk map data group 37.
- FIG. 5 The lane risk map generation unit 15 generates the collision risks of actual and potential obstacles at each grid point of the lane grid map and blind spot information by the above-described processing described with reference to FIGS. .
- step S801 the travel control planning unit 16 combines the road environment data group 32 acquired by the information acquiring unit 11, the existing obstacle prediction data group 34 generated by the existing obstacle prediction unit 12, and the HMI device group 8, for example. Based on the driver's and passenger's input signals acquired by , it is determined whether the vehicle 2 starts changing lanes or maintains the current lane. When changing lanes, the process proceeds to step S802. When not changing lanes, the process proceeds to step S808.
- step S804 the driving control planning unit 16 collects the road environment data group 32 acquired by the information acquisition unit 11, the lane risk map data group 37 generated by the lane risk map generation unit 15, and the vehicle data generated in step S803. 2, the traveling trajectory is evaluated.
- the degree of risk of the traveling trajectory can be evaluated. conduct.
- step S805 the travel control planning unit 16 determines whether or not it is necessary to correct the travel trajectory generated in step S803 based on the evaluation result of step S804. For example, if the evaluation result that the travel trajectory overlaps with the risk is sent from step S804, it may be determined that the travel trajectory needs to be corrected. In addition, for example, if the evaluation value of the travel track sent from step S804 is low, it may be determined that the travel track does not need to be corrected. In addition to simply correcting the trajectory of the lane change, for example, it is conceivable to reduce the degree of risk according to the traveling trajectory of the vehicle 2 and take action to increase the evaluation value.
- a travel trajectory is generated that improves the visibility of the vehicle 2 and reduces the potential risks, thereby changing the travel trajectory when changing lanes. It is also conceivable to control the vehicle 2 to take actions that raise the evaluation value.
- FIG. 9 is a diagram showing a specific example of trajectory generation, evaluation, and correction in the processing of FIG.
- the host vehicle 2 is about to change lanes from lane L1 to lane L2, another vehicle 900, which is an apparent obstacle traveling in lane L2, is approaching from behind.
- the travel control planning unit 16 combines the road environment information around the own vehicle 2 represented by the road environment data group 32 with the behavior information of the own vehicle 2 represented by the vehicle information data group 31. , and the information on the existing obstacle represented by the existing obstacle prediction data group 34, the target lane when the own vehicle 2 changes lanes is determined. Specifically, for example, as shown in FIG. 9A, the target lane after the lane change is determined to be the lane L2 for the own vehicle 2 traveling in the lane L1, and the lane change from the lane L1 to the lane L2 is determined. Generate trajectory 931 .
- step S805 the cruise control planning unit 16 determines that it is necessary to correct the lane change track 931, and corrects the lane change track 931 in step S806.
- a new lane change trajectory 932 is generated instead of the lane change trajectory 931, for example, as shown in FIG. 9(c).
- FIG. 10 is a diagram showing an example of a scene when the own vehicle 2 changes lanes according to the modified lane change trajectory 932 shown in FIG. 9(c).
- FIGS. 10(a), (b), and (c) fix the collision risk between the corrected lane change trajectory 932 and each grid point, and the automatic The motions of the vehicle 2 and another vehicle 900 are shown.
- another vehicle 900 has overtaken own vehicle 2 .
- the host vehicle 2 can avoid a collision with the other vehicle 900, so it moves to the lane L2 in the area behind the other vehicle 900 and enters the grid point 924 where there is no collision risk.
- the own vehicle 2 can complete the lane change to the lane L2 without colliding with the other vehicle 900 .
- the lane risk map data group 37 generated by the lane risk map generation unit 15 is for each lane of the road on which the vehicle 2 is traveling, each in its extending direction. Represents the risk status for a position. Because of this expression, when the travel control planning unit 16 performs travel track evaluation (processing of step S804 in FIG. 8), it compares with the risk state stored at each grid point in the lane risk map data group 37. It is possible to evaluate the running trajectory only by Therefore, the amount of calculation required for evaluating the travel track in the vehicle control device 3 can be greatly reduced.
- the vehicle control device 3 mounted on the own vehicle 2 includes an information acquisition section 11 , an actual obstacle prediction section 12 , and a lane risk map generation section 15 .
- the information acquisition unit 11 acquires a vehicle information data group 31 representing vehicle information related to the behavior of the own vehicle 2, a road environment data group 32 representing road environment information related to the environment of the road on which the own vehicle 2 is traveling, and the own vehicle 2. and a sensor recognition data group 33 representing sensor recognition information regarding the surrounding environment of the own vehicle 2 recognized by the external sensor group 4 mounted on the vehicle.
- the actual obstacle prediction unit 12 predicts the future behavior of the actual obstacles that may hinder the travel of the own vehicle 2.
- the lane risk map generation unit 15 calculates the collision risk between the own vehicle 2 and the obstacle on the road. Generate a lane risk map for each lane. Since it did in this way, regardless of the number of surrounding vehicles, the driving
- the lane grid map generation unit 14 determines the intervals between positions corresponding to a plurality of grid points on each lane of the road according to the difference in the shape of each lane on the road.
- a normalization process is performed to change each lane according to the difference in route length between the two lanes.
- the normalization process includes a process of setting a plurality of representative points on the driving lane of the own vehicle on the road at equal intervals, and a process of setting the driving lane at the set representative points.
- the process of setting multiple straight lines that are orthogonal to the extension direction of the road and pass through multiple representative points, and the intersections of the set straight lines and each lane of the road other than the driving lane are set to multiple representative points. It includes a process of setting a plurality of corresponding reference points, and a process of recording the positional information of the representative points and the reference points in association with each grid point of the lane grid map. Since this is done, each lane of the road can be represented accurately on the lane grid map even if there is a difference in route length between each lane of the road due to reasons such as the road being curved. can be done.
- the lane risk map generation unit 15 corrects the distance between each grid point of the lane grid map based on the difference in path length between the lanes (steps S501, S503, S510), and based on the corrected distance A collision risk is calculated (steps S504, S511). Since this is done, even if there is a difference in route length between lanes of the road due to reasons such as the road being curved, it is possible to appropriately calculate the collision risk at each grid point.
- the vehicle control device 3 includes a blind area identification unit 13 that identifies a blind area around the own vehicle 2 that cannot be recognized by the group of external sensors 4 .
- the lane risk map generation unit 15 predicts potential obstacles that may appear from the blind spot area (step S509), and based on the vehicle information data group 31, the future behavior of the potential obstacles, and the prediction results of the potential obstacles. to generate a lane risk map (step S513). By doing so, it is possible to generate a lane risk map with a higher degree of safety by further taking into consideration the obstacles that may protrude from the blind spot area that cannot be recognized by the group of external sensors 4 .
- the vehicle control device 3 Based on the vehicle information data group 31 and the road environment data group 32, the vehicle control device 3 creates a lane grid having a plurality of grid points set at equal intervals on a plurality of straight lines representing each lane of the road.
- a lane grid map generator 14 is provided for generating a map.
- the lane risk map generation unit 15 calculates a collision risk (first collision risk) between the vehicle and an actual obstacle at each grid point on the lane grid map, and a potential obstacle between the vehicle and the actual obstacle at each grid point on the lane grid map.
- a collision risk with an object (second collision risk) is calculated, and a lane risk map is generated based on the calculation results of the first and second collision risks.
- the lane risk map generator 15 calculates arrival times of the own vehicle, actual obstacles, and potential obstacles at each grid point of the lane grid map (steps S501, S503, S510). Then, by comparing the arrival time of the host vehicle and the arrival time of the actual obstacle, the first collision risk is calculated (step S504), and the arrival time of the host vehicle and the arrival time of the latent obstacle are compared. Thus, the second collision risk is calculated (step S511). Since this is done, both actual obstacles that can be recognized by the external sensor group 4 and latent obstacles from blind spots that cannot be recognized by the external sensor group 4 are considered, and these obstacles around the own vehicle are detected. It is possible to generate a lane risk map that appropriately represents the risk of collision with the
- FIG. 3B an example was described in which lane center line information used when performing lane grid map generation processing was obtained from the road environment data group 32. However, when this cannot be obtained, There is also In that case, for example, additional calculation of the lane centerline based on the lane boundary information, the travelable area, etc. may be performed, and the lane centerline information may be acquired from the calculation result.
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Traffic Control Systems (AREA)
Abstract
Description
図1は、本発明の実施の形態に係る車両制御装置3を含む車両システム1の構成を示す機能ブロック図である。車両システム1は、車両2に搭載される。車両システム1は、車両2の周辺における走行道路や周辺車両等の障害物の状況を確認したうえで、適切な運転支援や走行制御を行う。図1に示すように、車両システム1は、車両制御装置3、外界センサ群4、車両センサ群5、地図情報管理装置6、アクチュエータ群7、HMI装置群8、および外界通信装置9を含んで構成される。車両制御装置3、外界センサ群4、車両センサ群5、地図情報管理装置6、アクチュエータ群7、HMI装置群8、および外界通信装置9は、車載ネットワークNにより互いに接続される。なお以下では、車両2を他の車両と区別するために「自車両」2と呼ぶこともある。
次に図2~図10を用いて、本実施形態の車両システム1の動作を説明する。
図3は、車線グリッドマップ生成部14が行う車線グリッドマップ生成処理の説明図である。図3(a)は、車両2が走行する道路形状の一例を示す図であり、図3(b)は、図3(a)の道路形状に合わせて車線グリッドマップ生成に用いられる参照点の概念を示す図である。図3(c)は、図3(b)で示された参照点に基づいて生成される車線グリッドマップの一例を示す図である。
図4は、車線グリッドマップデータ群36の一例を示している。図4の車線グリッドマップデータ群36は、例えば、車線の識別子である車線ID401と、グリッド点のID402と、参照点のx-y位置情報403と、を含んで構成される。
図5は、車両制御装置3の車線リスクマップ生成部15が実行する処理を説明するフローチャートである。
続いて、図6~図7を用いて、図5のフローチャートで説明した車線リスクマップ生成部15の処理の具体的な動作例を説明する。
図8は、車両制御装置3の走行制御計画部16が実行する処理を説明するフローチャートである。
続いて、図9~図10を用いて、図8のフローチャートで説明した走行制御計画部16の処理の具体的な動作例を説明する。
Claims (8)
- 自車両に搭載される車両制御装置であって、
前記自車両の挙動に関する車両情報と、前記自車両が走行している道路の環境に関する道路環境情報と、前記自車両に搭載されたセンサによって認識された前記自車両の周囲環境に関するセンサ認識情報と、を取得する情報取得部と、
前記道路環境情報および前記センサ認識情報に基づいて、前記自車両の走行の障害となり得る顕在障害物の将来の挙動を予測する顕在障害物予測部と、
前記車両情報と、前記顕在障害物予測部により予測された前記顕在障害物の将来の挙動とに基づいて、前記自車両と障害物との衝突リスクを前記道路の車線ごとに表した車線リスクマップを生成する車線リスクマップ生成部と、
を備える車両制御装置。 - 前記車両情報および前記道路環境情報に基づいて、前記道路の各車線を表す複数の直線上にそれぞれ等間隔で設定された複数のグリッド点を有する車線グリッドマップを生成する車線グリッドマップ生成部を備え、
前記車線リスクマップ生成部は、前記車線グリッドマップの各グリッド点における前記衝突リスクを算出することにより、前記車線リスクマップを生成する、
請求項1に記載の車両制御装置。 - 前記車線グリッドマップ生成部は、前記車線グリッドマップを生成する際に、前記道路の各車線上で前記複数のグリッド点にそれぞれ対応する位置の間隔を、前記道路の各車線の形状の違いによる車線間での経路長の差に応じて車線毎に変化させる正規化処理を行う、
請求項2に記載の車両制御装置。 - 前記正規化処理は、
前記道路における前記自車両の走行車線上に複数の代表点を等間隔で設定する処理と、
前記複数の代表点における前記走行車線の延伸方向とそれぞれ直交し、かつ前記複数の代表点をそれぞれ通る複数の直線を設定する処理と、
前記複数の直線と前記走行車線を除いた前記道路の各車線との交点を、前記複数の代表点にそれぞれ対応する複数の参照点として設定する処理と、
前記代表点および前記参照点の位置情報を、前記車線グリッドマップの各グリッド点に対応付けてそれぞれ記録する処理と、を含む、
請求項3に記載の車両制御装置。 - 前記車線リスクマップ生成部は、前記車線グリッドマップの各グリッド点間の距離を前記経路長の差に基づいて補正し、補正後の距離に基づいて前記衝突リスクを算出する、
請求項3に記載の車両制御装置。 - 前記自車両の周囲で前記センサが認識できない死角領域を特定する死角領域特定部を備え、
前記車線リスクマップ生成部は、前記死角領域から出現し得る潜在障害物を予測し、前記車両情報と、前記顕在障害物の将来の挙動と、前記潜在障害物の予測結果とに基づいて、前記車線リスクマップを生成する、
請求項1に記載の車両制御装置。 - 前記車両情報および前記道路環境情報に基づいて、前記道路の各車線を表す複数の直線上にそれぞれ等間隔で設定された複数のグリッド点を有する車線グリッドマップを生成する車線グリッドマップ生成部を備え、
前記車線リスクマップ生成部は、前記車線グリッドマップ上の各グリッド点における前記自車両と前記顕在障害物との第1の衝突リスクと、前記車線グリッドマップ上の各グリッド点における前記自車両と前記潜在障害物との第2の衝突リスクとをそれぞれ算出し、前記第1および第2の衝突リスクの算出結果に基づいて前記車線リスクマップを生成する、
請求項6に記載の車両制御装置。 - 前記車線リスクマップ生成部は、
前記車線グリッドマップの各グリッド点における前記自車両、前記顕在障害物および前記潜在障害物の到達時間をそれぞれ算出し、
前記自車両の到達時間と前記顕在障害物の到達時間とを比較することにより、前記第1の衝突リスクを算出し、
前記自車両の到達時間と前記潜在障害物の到達時間とを比較することにより、前記第2の衝突リスクを算出する、
請求項7に記載の車両制御装置。
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US18/833,056 US12676066B2 (en) | 2022-02-07 | 2022-08-25 | Vehicle control device |
| CN202280090074.1A CN118613849A (zh) | 2022-02-07 | 2022-08-25 | 车辆控制装置 |
| DE112022005447.6T DE112022005447T5 (de) | 2022-02-07 | 2022-08-25 | Fahrzeugsteuervorrichtung |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2022-017561 | 2022-02-07 | ||
| JP2022017561A JP7615068B2 (ja) | 2022-02-07 | 2022-02-07 | 車両制御装置 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2023149003A1 true WO2023149003A1 (ja) | 2023-08-10 |
Family
ID=87552037
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2022/032103 Ceased WO2023149003A1 (ja) | 2022-02-07 | 2022-08-25 | 車両制御装置 |
Country Status (5)
| Country | Link |
|---|---|
| US (1) | US12676066B2 (ja) |
| JP (1) | JP7615068B2 (ja) |
| CN (1) | CN118613849A (ja) |
| DE (1) | DE112022005447T5 (ja) |
| WO (1) | WO2023149003A1 (ja) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102022212567A1 (de) * | 2022-11-24 | 2024-05-29 | Robert Bosch Gesellschaft mit beschränkter Haftung | Verfahren zur Kontrolle eines Spurwechsels eines Fahrzeuges |
| KR20250001260A (ko) * | 2023-06-28 | 2025-01-06 | 현대자동차주식회사 | 차량 경로 생성 장치 및 그 방법 |
| JP2026008035A (ja) * | 2024-07-04 | 2026-01-19 | 本田技研工業株式会社 | 運転支援装置、運転支援方法、およびプログラム |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101503473B1 (ko) * | 2014-01-10 | 2015-03-18 | 한양대학교 산학협력단 | 차량의 주행 상황 판단 시스템 및 방법 |
| JP2021047644A (ja) * | 2019-09-18 | 2021-03-25 | 日立オートモティブシステムズ株式会社 | 電子制御装置 |
| JP2021172264A (ja) * | 2020-04-28 | 2021-11-01 | 日産自動車株式会社 | 車両の走行支援方法及び走行支援装置 |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6297956B2 (ja) | 2014-05-13 | 2018-03-20 | 株式会社Soken | 経路生成装置 |
| JP6304504B2 (ja) | 2015-10-28 | 2018-04-04 | 本田技研工業株式会社 | 車両制御装置、車両制御方法、および車両制御プログラム |
| JP6548029B2 (ja) | 2015-12-03 | 2019-07-24 | 株式会社デンソー | 自動運転システム |
| US11731639B2 (en) * | 2020-03-03 | 2023-08-22 | GM Global Technology Operations LLC | Method and apparatus for lane detection on a vehicle travel surface |
| US11625009B2 (en) * | 2020-03-26 | 2023-04-11 | Intel Corporation | Non-uniform occupancy grid manager |
-
2022
- 2022-02-07 JP JP2022017561A patent/JP7615068B2/ja active Active
- 2022-08-25 WO PCT/JP2022/032103 patent/WO2023149003A1/ja not_active Ceased
- 2022-08-25 CN CN202280090074.1A patent/CN118613849A/zh active Pending
- 2022-08-25 DE DE112022005447.6T patent/DE112022005447T5/de active Pending
- 2022-08-25 US US18/833,056 patent/US12676066B2/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101503473B1 (ko) * | 2014-01-10 | 2015-03-18 | 한양대학교 산학협력단 | 차량의 주행 상황 판단 시스템 및 방법 |
| JP2021047644A (ja) * | 2019-09-18 | 2021-03-25 | 日立オートモティブシステムズ株式会社 | 電子制御装置 |
| JP2021172264A (ja) * | 2020-04-28 | 2021-11-01 | 日産自動車株式会社 | 車両の走行支援方法及び走行支援装置 |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2023114943A (ja) | 2023-08-18 |
| JP7615068B2 (ja) | 2025-01-16 |
| DE112022005447T5 (de) | 2024-09-12 |
| US20250157333A1 (en) | 2025-05-15 |
| US12676066B2 (en) | 2026-07-07 |
| CN118613849A (zh) | 2024-09-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114126940B (zh) | 电子控制装置 | |
| JP7546580B2 (ja) | 自動車の可能な軌道のサンプリングベースの計画のための制御システムおよび制御方法 | |
| US11851090B2 (en) | Vehicle control apparatus, vehicle control method, and storage medium | |
| JP7435787B2 (ja) | 経路確認装置および経路確認方法 | |
| JP7200970B2 (ja) | 車両制御装置 | |
| CN109313857B (zh) | 周边环境识别装置 | |
| JP6308233B2 (ja) | 車両制御装置及び車両制御方法 | |
| JP7362899B2 (ja) | 車両の走行支援方法及び走行支援装置 | |
| US9708004B2 (en) | Method for assisting a driver in driving an ego vehicle and corresponding driver assistance system | |
| JP6562386B2 (ja) | 車両運転支援システム及び方法 | |
| JP6508114B2 (ja) | 移動体の自動運転制御システム | |
| JP6611080B2 (ja) | 車両運転支援システム及び方法 | |
| JP7615068B2 (ja) | 車両制御装置 | |
| JP7379033B2 (ja) | 運転支援方法及び運転支援装置 | |
| JP2020163970A (ja) | 車両運転支援システム | |
| JP2018138402A (ja) | 車両運転支援システム及び方法 | |
| JP2013242615A (ja) | 運転シーン遷移予測装置および車両用推奨運転操作提示装置 | |
| JP2018138404A (ja) | 車両運転支援システム及び方法 | |
| JP2018138405A (ja) | 車両運転支援システム及び方法 | |
| JP6838769B2 (ja) | 周辺環境認識装置、表示制御装置 | |
| JP6607526B2 (ja) | 車両運転支援システム及び方法 | |
| JP6562387B2 (ja) | 車両運転支援システム及び方法 | |
| US20230339507A1 (en) | Contextual right-of-way decision making for autonomous vehicles | |
| JP7839721B2 (ja) | 運転支援装置 | |
| JP2020053069A (ja) | 車載用電子制御装置 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 22924908 Country of ref document: EP Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 18833056 Country of ref document: US Ref document number: 202280090074.1 Country of ref document: CN |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 22924908 Country of ref document: EP Kind code of ref document: A1 |
|
| WWP | Wipo information: published in national office |
Ref document number: 18833056 Country of ref document: US |
|
| WWG | Wipo information: grant in national office |
Ref document number: 18833056 Country of ref document: US |