WO2007102405A1 - 自車進路決定方法および自車進路決定装置 - Google Patents
自車進路決定方法および自車進路決定装置 Download PDFInfo
- Publication number
- WO2007102405A1 WO2007102405A1 PCT/JP2007/053955 JP2007053955W WO2007102405A1 WO 2007102405 A1 WO2007102405 A1 WO 2007102405A1 JP 2007053955 W JP2007053955 W JP 2007053955W WO 2007102405 A1 WO2007102405 A1 WO 2007102405A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- vehicle
- evaluation value
- predetermined value
- route
- candidates
- Prior art date
Links
Classifications
-
- 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, or advanced driver assistance systems for ensuring comfort, stability and safety or drive control systems for propelling or retarding the vehicle
- B60W30/10—Path keeping
-
- 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
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/02—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to ambient conditions
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0217—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with energy consumption, time reduction or distance reduction criteria
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/16—Anti-collision systems
- G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes
-
- 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
Definitions
- the present invention relates to a host vehicle route determination method and a host vehicle route determination device that determine one of a plurality of predicted host vehicle route candidates as an optimal travelable route, and more particularly BACKGROUND OF THE INVENTION 1.
- Non-Patent Document 1 A. Broadhurst, S. Baker, and T. Kanade, "Monte Carlo Road
- Non-Patent Document 1 constitutes a system. Since the main objective is to predict a path where all objects are safe, there are many cases where the path obtained by such prediction does not match the actual situation. For example, if you are traveling on a highway lane and there is another vehicle that is slower than your vehicle ahead of your vehicle lane, even if you can overtake it, Since it is safer to follow, there is a case where the route following the other vehicle is predicted and selected as a safe route and the arrival at the destination is delayed. That is, the driving safety may be extremely high, but the driving efficiency may be extremely poor.
- the present invention has been made in view of the above, and a host vehicle path determination method and host vehicle path determination capable of determining an appropriate host vehicle path from a plurality of predicted host vehicle path candidates.
- An object is to provide an apparatus.
- a method for determining a vehicle course is a step of calculating a first evaluation value for each of a plurality of predicted vehicle course candidates.
- the own vehicle route determining method includes a step of calculating a first evaluation value for each of a plurality of predicted vehicle route candidates, and each of the plurality of vehicle route candidates.
- a second evaluation value for the vehicle a step of selecting a first evaluation value size candidate! / ⁇ own vehicle route candidate from the plurality of own vehicle route candidates, and the selected own vehicle route Selecting a candidate course of the host vehicle having the maximum second evaluation value from the candidates as a path on which the host vehicle can travel.
- the method for determining the own vehicle route candidate according to the present invention includes the step of selecting the own vehicle route candidate having a first first evaluation value from the plurality of own vehicle route candidates. The route having the first evaluation value larger than the predetermined value is selected.
- the own vehicle route determination method is the above-described invention, wherein the plurality of own vehicles
- the step of selecting a self-vehicle course candidate having a large second evaluation value from the course candidates is characterized by selecting a course having a second evaluation value larger than a predetermined value.
- the first evaluation value is a value obtained by evaluating the safety of the own vehicle.
- the own vehicle route determination method according to the present invention is characterized in that, in the above invention, the second evaluation value is a value obtained by evaluating a traveling efficiency of the own vehicle.
- the own vehicle route determination method according to the present invention is characterized in that, in the above-mentioned invention, the step of inputting and setting the predetermined value is provided.
- the own vehicle route determination method is characterized in that, in the above invention, the step of inputting and setting the predetermined value sets the predetermined value to be variable.
- the step of inputting and setting the predetermined value increases the predetermined value in association with the depression amount of the accelerator pedal. It is characterized by variable setting.
- the step of inputting and setting the predetermined value causes the predetermined value to be lowered on the basis of the depression amount of the brake pedal. It is characterized by variable setting.
- the step of inputting and setting the predetermined value variably sets the predetermined value in conjunction with an operation of a mode selection switch related to a travel mode. It is characterized by that.
- the host vehicle route determination device includes a first calculation unit that calculates a first evaluation value for each of a plurality of predicted host vehicle route candidates, and the plurality of host vehicle routes.
- a second computation unit that computes a second evaluation value for each of the candidates; and a host vehicle route candidate having a large first evaluation value is selected from the plurality of vehicle route candidates, and the selected
- the second evaluation value of the own vehicle course candidate ⁇ Select the own car course candidate to be a suitable own car course candidate, and a selection unit that selects an arbitrary own car course from the suitable own car course candidate It is characterized by providing.
- the host vehicle route determination device includes a first calculation unit that calculates a first evaluation value for each of a plurality of predicted host vehicle route candidates, and the plurality of host vehicle routes.
- Each candidate A second computation unit that computes a second evaluation value for each of the plurality of vehicle candidates, and a host vehicle route candidate having a large first evaluation value is selected from the plurality of vehicle route candidates, and the selected vehicle route
- a selection unit that selects a candidate course of the host vehicle having the maximum second evaluation value from among the candidates as a course on which the host vehicle can travel.
- the selection unit selects a first evaluation value of the plurality of own vehicle route candidates, and determines the own vehicle route candidate. At the time of selection, a course having a first evaluation value larger than a predetermined value is selected.
- the selection unit selects a candidate of the own vehicle route from the plurality of own vehicle route candidates with a second evaluation value. In this case, a route having a second evaluation value larger than a predetermined value is selected.
- the first evaluation value is a value obtained by evaluating the safety of the own vehicle.
- the second evaluation value is a value obtained by evaluating a traveling efficiency of the host vehicle.
- the host vehicle course determination device is characterized in that, in the above invention, a predetermined value input unit for inputting and setting the predetermined value is provided.
- the predetermined value input unit sets the predetermined value to be variable.
- the predetermined value input unit variably sets the predetermined value to the ascending side in conjunction with the depression amount of the accelerator pedal. It is characterized by.
- the predetermined value input unit variably sets the predetermined value to the lower side in conjunction with a depression amount of the brake pedal. It is characterized by.
- the predetermined value input unit variably sets the predetermined value in conjunction with an operation of a mode selection switch related to a travel mode. It is characterized by that.
- the invention's effect [0029]
- the first evaluation value and the second evaluation value of the own vehicle for each of the predicted plurality of vehicle route candidates are obtained.
- the vehicle path candidate having a large first evaluation value and a large second evaluation value is selected as a suitable vehicle path candidate from among the plurality of vehicle path candidates. Since an arbitrary own vehicle route is selected, it is possible to determine an appropriate own vehicle route by appropriately setting the first evaluation value and the second evaluation value. Play.
- the own vehicle route determining method and the own vehicle route determining device determine an appropriate own vehicle course.
- the first evaluation value that evaluates the safety of the own vehicle with respect to each of a plurality of predicted vehicle route candidates.
- a second evaluation value that evaluates the traveling efficiency of each of the vehicle path candidates, and the first evaluation value is larger than the predetermined value set in the plurality of vehicle path candidates and is the maximum.
- the candidate for the own vehicle route having the second evaluation value is selected as the travelable route of the own vehicle, so that the predetermined value for allowing the first evaluation value is appropriately set according to the situation. For example, even if safety is slightly reduced within the range that satisfies the safety standards, additional V to reach the destination as soon as possible, allowing selection of the way over, etc. The effect is that it is possible to determine the course of the vehicle.
- FIG. 1 is a schematic block diagram showing a functional configuration of a host vehicle route determination device according to an embodiment of the present invention.
- FIG. 2 is a flowchart showing an outline of processing from an object course prediction method to a host vehicle course determination method according to the present embodiment.
- FIG. 3 is a flowchart showing details of trajectory generation processing in the trajectory generation unit.
- FIG. 4 is a diagram schematically showing a trajectory generated in a three-dimensional space-time.
- FIG. 5 is a diagram schematically showing a trajectory set generated in three-dimensional space-time for one object.
- FIG. 6 is a diagram schematically showing a configuration of a spatiotemporal environment formed by the object course prediction method.
- FIG. 7 is a flowchart showing an example of a course determination process in the interference evaluation 'action selection unit.
- FIG. 8 is a flowchart showing an example of an interference degree calculation process in the vehicle course safety evaluation unit.
- FIG. 9 is a diagram schematically showing a temporal and spatial relationship between the trajectory of the own vehicle and the trajectory of another vehicle.
- FIG. 10 is a characteristic diagram showing the time dependence of interference between objects.
- FIG. 11 is a diagram schematically showing an interference evaluation example using the total interference degree in the spatiotemporal environment between the host vehicle and another vehicle.
- FIG. 1 is a schematic block diagram showing a functional configuration of the host vehicle course determination device according to the embodiment of the present invention.
- This own vehicle route determination device is mounted on a host vehicle that is a vehicle traveling on a road, detects obstacles such as other vehicles existing in a predetermined range around the host vehicle, and detects the detected obstacle. This is for determining the course of the vehicle for automatically driving the vehicle in consideration of harmful substances.
- the own vehicle course determining apparatus 1 of the present embodiment includes an input unit 2 for inputting various information from the outside, a sensor unit 3 for detecting the position and internal state of an object existing in a predetermined range, and a sensor unit. Based on the results detected by 3), the trajectory generator 4 generates a change in the position that the object can take as time passes as a trajectory in time and space, and the trajectory generator 4 Using the generated trajectory, the prediction unit 5 that performs probabilistic prediction of the course of the object such as the host vehicle and other vehicles, and the other vehicle with respect to the host vehicle based on the object prediction result performed by the prediction unit 5 Interference evaluation and behavior selection unit 6 to calculate the possibility of interference of the vehicle and select the optimal travelable route as the vehicle route In the storage unit 7 that stores information including the results, and the interference evaluation and action selection unit 6 Includes am with a predetermined value input unit 8 for inputting setting the storage unit 7 to a predetermined value, the interference evaluation 'action selector 6 selected output by the output terminal 9 which receives the (operation signal).
- the input unit 2 has a function of inputting various setting information and the like when predicting the course of a moving object such as a host vehicle or another vehicle, and is provided with a remote control, a keyboard (input operation on the screen is possible) (Including touch panel format) and pointing devices (mouse, trackpad, etc.).
- a microphone capable of inputting information by voice may be provided as the input unit 2.
- the sensor unit 3 is realized by using a millimeter wave radar, a laser radar, an image sensor, or the like.
- the sensor unit 3 includes various sensors such as a speed sensor, an acceleration sensor, a rudder angle sensor, and an angular velocity sensor, and can also detect the movement state of the host vehicle.
- the internal state of the object detected by the sensor unit 3 is meaningful for the prediction of the object, and is preferably a physical quantity such as the speed, acceleration, angular velocity, and angular acceleration of the object. For example, a case where the value of a physical quantity such as the speed or angular velocity of a moving object such as the own vehicle is 0 (a state in which the object is stopped and stopped) is naturally included.
- the trajectory generation unit 4 includes an operation selection unit 41 that selects an operation on a moving object such as the own vehicle or another vehicle from a plurality of operations, and an object operation unit that performs the operation selected by the operation selection unit 41 for a predetermined time. 42 and the position and internal state of moving objects such as own vehicle and other vehicles after being operated by the object operation unit 42 And a determination unit 43 that determines whether or not the power satisfies a predetermined condition.
- the prediction unit 5 performs a probabilistic prediction calculation of the object course by using the trajectory for each moving object such as the own vehicle or other vehicle output from the trajectory generation unit 4.
- the interference evaluation 'behavior selection unit 6 calculates the possibility of interference such as a collision with another vehicle with respect to each of the plurality of vehicle path candidates predicted by the prediction unit 5, thereby calculating the safety of the vehicle.
- the vehicle path efficiency evaluation unit 62 that calculates an efficiency evaluation value (e.g., V, an evaluation value indicating whether or not the vehicle can quickly reach the destination, and a plurality of vehicle path candidates)
- a maximum efficiency route selection unit 63 within the setting that selects a candidate vehicle route having a safety evaluation value that exceeds a set predetermined value and that has a maximum efficiency evaluation value as a travelable route of the vehicle;
- the predetermined value input unit 8 is a predetermined value for determining whether or not the safety evaluation value for each candidate vehicle route is a value that is acceptable in terms of safety in the processing of the within-setting maximum efficiency route selecting unit 63.
- an accelerator pedal, a brake pedal, or a mode selection switch for driving mode for switching to sport mode Z luxury mode, etc. can be applied.
- the storage unit 7 stores an operation selected by the operation selection unit 41 of the trajectory generation unit 4 in addition to the trajectory generated by the trajectory generation unit 4 and the prediction result of the prediction unit 5.
- the storage unit 7 includes a predetermined value storage unit 71 that stores the predetermined value input and set by the predetermined value input unit 8, and the stored predetermined value is determined by the setting maximum efficiency course selection unit 63.
- the storage unit 7 includes a ROM (Read Only Memory) in which a program for starting a predetermined OS (Operation System), an object course prediction program according to the present embodiment, a host vehicle course determination program, and the like are stored in advance. This is realized by using RAM (Random Access Memory) that stores processing parameters and data.
- the storage unit 7 is realized by providing an interface capable of mounting a computer-readable recording medium on the host vehicle course determination device 1 and mounting a recording medium corresponding to this interface. Monkey.
- the evaluation / behavior selection unit 6 and the storage unit 7 are realized by a processor (computer) 10 having a CPU (Central Processing Unit) having calculation and control functions. That is, the CPU included in the host vehicle course determination device 1 reads information stored in and stored in the storage unit 7 and various programs including the above-described object course prediction program and host vehicle course determination program from the storage unit 7. Arithmetic processing relating to the object course prediction method and the vehicle course determination method according to the present embodiment is executed.
- the object course prediction method and the vehicle course determination program according to the present embodiment are stored in a computer-readable recording medium such as a hard disk, a flexible disk, a CD-ROM, a DVD-ROM, a flash memory, and an MO disk. It is also possible to record and distribute widely.
- FIG. 2 is a flowchart showing an outline of processing from the object course prediction method to the own vehicle course determination method according to the present embodiment.
- the course determination method can also be applied to the control of an object that moves in a three-dimensional space or an actuator (such as a robot arm) that has an arbitrary degree of freedom.
- the sensor unit 3 detects the position and internal state of a moving object such as another vehicle within a predetermined range with respect to the host vehicle, and stores the detected information in the storage unit 7 (step Sl).
- the internal state of the object shall be specified by the velocity (speed v, direction ⁇ ).
- the internal state of the vehicle is also detected and stored in the storage unit 7.
- FIG. 3 is a flowchart showing details of the trajectory generation processing in the trajectory generation unit 4.
- the total number of objects (including the vehicle) detected by sensor unit 3 is I, and the calculation to generate a trajectory for one object O (1 ⁇ i ⁇ I, i is a natural number) is performed. N times (in this sense, I and N are both natural numbers).
- the time for generating the trajectory is T (> 0). To do.
- initialization is performed so that the value of the counter i for identifying the object is set to 1 and the value of the counter n indicating the number of trajectory generations for the same object is set to 1 (step S201).
- the trajectory generation unit 4 reads the result detected by the sensor unit 3 from the storage unit 7 and sets the read detection result as an initial state (step S 202). Specifically, the time t is set to 0, the initial position (X (0), y (0)) and the initial internal state (V (0), 0 (0)) are respectively input information from the sensor unit 3 ( Let X, y) and (V, ⁇ ).
- the operation selection unit 41 performs the operation u (t) to be performed during the subsequent time At according to the operation selection probability given in advance to each operation from a plurality of selectable operations.
- Select one operation (step S203).
- the operation selection probability p (u) can be defined as a function depending on the position and internal state of the host vehicle and the surrounding road environment.
- the operation u is composed of a plurality of elements, and the contents of selectable operations differ depending on the type of the object O.
- the acceleration and angular velocity of the four-wheeled vehicle are determined by the degree of steering and the degree of depression of the accelerator.
- the operation u performed on the object O that is a four-wheeled vehicle is determined by factors including acceleration and angular velocity.
- the operation u can be determined by the speed and direction.
- the time At may be a value of about 0.1 to 0.5 (s), for example.
- the value of At may be fixed or may be a variable value that depends on the urgency of the surrounding situation. In the following, an example where At is a fixed value is shown.
- the trajectory generation time T is an integral multiple of ⁇ t.
- the determination unit 43 determines whether or not the internal state of the object O after operating the operation u in step S204 satisfies a predetermined control condition (step S205), It is determined whether or not the position of the object O after operating u is within the movable region (step S206).
- the control condition determined in step S205 is determined according to the type of the object O. For example, when the object O is a four-wheeled vehicle, the speed range after the operation in step S204, It is determined by the maximum vehicle G after acceleration.
- the movable area determined in step S206 refers to an area such as a road (including a roadway and a sidewalk). Hereinafter, the case where the object is located in the movable area is expressed as “satisfying the moving condition”.
- step S207 As a result of the determination by the determination unit 43 described above, if any one of the conditions is not satisfied (No in step S205 or No in step S206), the process returns to step S202. On the other hand, if the result of the determination in the determination unit 43 indicates that the position and internal state of the object ⁇ after completion of the operation u in step S204 satisfy all the conditions (Yes in step S205 and For (Yes), advance the time by At (t t + At), set the position after the operation of step S204 to (X (t), y (t)), the internal state to (V (t), ⁇ ( t)) (Step S207
- steps S202 to S207 described above are repeated until the trajectory generation time T is reached. That is, when the time t newly defined in step S207 has not reached T (No in step S208), the process returns to step S203 and is repeated. On the other hand, when the time t newly defined in step S207 reaches T (Yes in step S208), a trajectory for the object O is output and stored in the storage unit 7 (step S209).
- the trajectory P ; (m) (l ⁇ m ⁇ N, where m is a natural number) shown in the figure is a three-dimensional space-time (X, y, t) in two dimensions (x, y) and one time (t) Pass through.
- step S209 if the value of counter n has not reached N (No in step S210), the value of counter n is incremented by 1 (step S211), the process returns to step S203, and the above-described steps S203 to S208 are performed. This process is repeated until the trajectory generation time T is reached.
- FIG. 5 shows a set of trajectories ⁇ P (n) ⁇ consisting of N trajectories P (1), P (2), ..., P (N) generated for one object O in three dimensions. It is explanatory drawing typically shown on space. The starting points of the trajectories constituting the elements of the trajectory set ⁇ P (n) ⁇ , that is, the initial positions (X, y, 0) are the same (see step S202). Figure 5 is for reference only.
- N can take, for example, several thousand or more values.
- step S210 When the counter n reaches N in step S210, if the object identification counter i has not reached the total number of objects I (No in step S212), the counter i is incremented by 1 and a trajectory is generated. The counter n is initialized to 1 (step S213), and the process returns to step S202 to repeat the process. On the other hand, if the object counter i reaches I (Yes in step S212), the trajectory generation for all objects has been completed, so the trajectory generation process in step S2 is terminated, and the subsequent step S3 is entered. move on.
- FIG. 6 is an explanatory diagram schematically showing a configuration example of the spatiotemporal environment Env (P).
- the spatiotemporal environment Env (P) shown in the figure consists of the trajectory set ⁇ P (n) ⁇ of object O (shown as a solid line in Fig. 6) and the trajectory set ⁇ P (n) ⁇ of object O
- the spatiotemporal environment Env (P) is defined as two objects O and O force on a flat and straight road R such as a highway facing the + y axis.
- the trajectory generation is performed independently for each object without considering the correlation between the objects.
- Body trajectories may intersect in space and time.
- Density hereinafter referred to as “spatiotemporal probability density”. Therefore, by using the spatiotemporal environment Env (P) configured by the trajectory generation process in step S2, it is possible to obtain the probability that the object O will pass through a predetermined region on the three-dimensional spatiotemporal.
- the spatio-temporal probability density described above is merely a concept of probability in space-time, so it is not always 1 when the sum of the values of one object in space-time is taken.
- the probability density distribution in space-time is statistically evaluated. If the distribution is constant, the trajectory generation time T is reduced, and so on. If this is not the case, it is preferable to perform adaptive control that increases the trajectory generation time T.
- a plurality of routes that the host vehicle can take are prepared in advance, and the prediction is performed until the trajectory generation time T at which the probability of the intersection between the host vehicle route and the path of each object is constant. It is also possible to do this.
- the censorship condition may be that the risk increment for each course that the vehicle can take when the predicted time is increased by At is constant.
- the prediction unit 5 After the trajectory generation process for each object described above, the prediction unit 5 performs a probabilistic prediction of the paths (path candidates) that each object such as the own vehicle and other vehicles can take (step S3).
- a specific prediction calculation process in the prediction unit 5 a case where a probability that a specific trajectory P (m) is selected from the trajectory set ⁇ P (n) ⁇ generated for the object O is described.
- this prediction calculation is only an example.
- the probability p (P (m)) that one of the trajectories P (m) is an actual trajectory is calculated as follows: Is done.
- the operation sequence ⁇ u (t) ⁇ for realizing the trajectory P (m) of the object O is ⁇ u (0), u (At), u (2At), ..., u (T) ⁇
- the prediction calculation in the prediction unit 5 is simplified by standardizing the value of the probability p (P (m)) to 1, and the predetermined prediction calculation can be executed more quickly. .
- FIG. 7 is a flowchart showing the interference evaluation 'interference evaluation' course selection processing in the action selection unit 6.
- it is checked whether or not there is an input setting for changing the predetermined value from the predetermined value input unit 8 (step S401) . If there is a variable input of the predetermined value (Yes in step S401), the input is made.
- the predetermined value is stored in the predetermined value storage unit 71 of the storage unit 7 (step S402). This predetermined value may be set in the predetermined value storage unit 71 in advance.
- the safety evaluation value and the traveling efficiency that evaluate the safety of the vehicle are evaluated.
- the calculated efficiency evaluation values are sequentially calculated and used for route determination. Therefore, first, the safety evaluation value S (l) and the efficiency evaluation value E (l) of the first vehicle path candidate among a number of vehicle path candidates are calculated (step S403).
- the safety evaluation value of the host vehicle is compared with the candidate course of the host vehicle.
- the possibility of interference with other vehicles is calculated, and the degree of possibility is evaluated as, for example, the degree of interference based on the collision probability. The higher the degree of interference, the more likely it is to collide with other vehicles. Is high.
- the evaluation in this case is not limited to the collision probability, but may be evaluated as the degree of interference based on the degree of collision impact, the degree of collision damage, the degree of the shortest collision time, etc.
- the efficiency evaluation value of the vehicle is, for example, a value that evaluates whether it is possible to go to the destination quickly. When the predicted course candidate for each vehicle is taken, the vehicle advances from the current position toward the destination. The longer the distance, the higher the efficiency evaluation value.
- the vehicle's running efficiency is evaluated based on the power, fuel consumption, expected remaining time to the destination, etc. that can be accelerated and decelerated and steered when the predicted courses of each vehicle are taken. You may do it.
- FIG. 8 is a flowchart showing an example of an interference degree calculation process in the own vehicle course safety evaluation unit 61.
- the object O is the own vehicle.
- other objects O (k 2, 3,
- the The safety evaluation value is calculated as the degree of interference.
- step S441 the iterative process (Loopl) for all trajectories of the host vehicle O is started (step S441). At this time, one trajectory of the trajectory set ⁇ P (n) ⁇ is selected and the trajectory P (m) is selected.
- the counter k for identifying other vehicles is initialized to 2, and the value of k is incremented every time iterative processing is completed.
- Loop3 Repeat processing (Loop3) is performed (step S443).
- Lo opl that is, the value n that identifies the trajectory generated for the vehicle O and the other vehicle identification
- the interference degree determined by the counter k for 1 is set to r (n, k), and the value of r (n, k) is set to 0
- Step S444 the iteration for evaluating the interference between the trajectory P (n) of the host vehicle O and the trajectory P (n) of the other vehicle O is continued.
- Loop4 Repeat processing (Loop4) is started (step S445).
- Loop4 there are two trajectories P (n
- Figure 9 shows the trajectory P (11) of own vehicle O and the trajectory of other vehicle 0? Schematic relationship with (n) in space-time
- trajectory P (n) and trajectory P (n) are two points C and C
- p (P (n)) is expressed by the formula (lk lk k k
- F (t) is expressed as a function that gradually decreases with time. It may be defined.
- F (t) shown in Fig. 10 the most recent collision is weighted and important.
- step S447 if time t has not reached T, Loop4 is repeated (No in step S448). In this case, the value of t is increased by At (step S449), and the process returns to step S445 to repeat Loop4. On the other hand, if the time t has reached T after step S447, Loop4 is terminated (Yes in step S448). At some time t, own vehicle O and others
- step S450 a determination process is performed to determine whether Loop3 is to be repeated. That is, of the trajectory generated for other car O
- step S45 If there is one that has not been evaluated for interference with one locus P (n) of O (step S45
- n is set to n + 1 (step S451), return to step S443 and repeat Loop3
- step S450 If all the prices are confirmed (Yes in step S450), the other track O will have one trajectory P (n).
- step S452 the assigned value is output and stored in the storage unit 7 (step S453).
- the value of the interference degree r (n, k) output in step S453 is equal to one of the other tracks O.
- k is the probability p (P (n)) for each trajectory P (n) and the trajectory P (n) and the vehicle O
- the value obtained is proportional to the collision probability between one track P (11) of the own vehicle O and the other vehicle 0.
- step S453 a process for determining whether or not to repeat Loop2 is performed.
- step S454 when there is another vehicle O that should be evaluated for interference with vehicle O (No in step S454), Increase the value of k by 1 (step S455), return to step S442, and repeat Loop2.
- step S454 if there is no other vehicle O to be evaluated for interference with own vehicle O (Y in step S454)
- step S456 the interference degree r (n, k) obtained by Loop2 to Loop4 is determined based on the other vehicle O.
- R 1 (n 1 ) X a (k) r 1 (n 1 , k) (6) is calculated, and the calculation result is output and stored in the storage unit 7.
- the value of the weight a (k) may be all equal or a constant (for example, 1), or k depending on the risk according to the conditions such as the type of the object O.
- the trajectory P (n) of own vehicle O includes all other vehicles O,
- the risk can be accurately measured.
- a determination process is performed for repetition of Loopl. That is, the own car O
- step S458 increase the value of n by 1 (step S458), return to step S441, and repeat.
- the trajectory to be evaluated for interference in the trajectory set ⁇ P (n) ⁇ of the vehicle O is
- step S447 the values of c and F (t) when increasing the interference degree r (n, k) are
- the magnitude of the relative speed between vehicles at the time of a collision is stored in the storage unit 7 by creating a correlation between the damage scale evaluation value evaluated by quantifying the damage scale and Z or damage loss amount,
- the stored value may be read from the storage unit 7 and given the coefficient c.
- the damage scale evaluation value and Z or the amount of damage loss may be determined according to the object type.
- the possibility of collision with a human being is minimized as much as possible by keeping the value of c when colliding with a human being remarkably large.
- the own vehicle route efficiency evaluation unit 62 evaluates the traveling efficiency according to how quickly the destination can be reached, for example, the operation time when each predicted candidate vehicle route is taken.
- the advance distance y per interval t eg, 0.1 second, 0.5 second
- the advance distance y when the control time tmax eg, 5 seconds
- the efficiency evaluation value increases.
- the safe path saftypath and the optimum path bestpath are initially set to non (none) (step S403), and the variable i is set to 1 (step S404).
- the safety evaluation value S (i) of the vehicle course candidate corresponds to the overall interference degree
- the efficiency evaluation value E (i) are calculated (step S405).
- Evaluation value S (i) is the minimum safety evaluation value Smin It is determined whether it is small (step S407).
- Safety path If saftypath is non (No) (Yes in step S406), or safety evaluation value S (i) is smaller than minimum value Smin (Yes in step S407), the minimum value of safety evaluation value Smin is set to S (i), and the safe path saftypath is set to i (meaning the i-th own vehicle path candidate) (step S408).
- step S410 it is determined whether or not the safety evaluation value S (i) exceeds the predetermined value set in the predetermined value storage unit 71 and satisfies the safety condition.
- “exceeding the predetermined value” means that the safety evaluation value is lower than the set predetermined value, and means that safety is higher than the predetermined value (risk is low).
- the safety evaluation value S (i) satisfies the safety condition exceeding the predetermined value (Yes in Step S410)
- step S411 it is determined whether or not the calculated efficiency evaluation value E (i) is larger than the maximum efficiency evaluation value Emax (step S412). If the optimal path bestpath is non (none) (Yes in step S411), or the efficiency evaluation value E (i) is greater than the maximum value Emax! /, (Yes in step S41 2), the efficiency evaluation value The maximum value Emax is set to E (i), and the optimum route bestpath is set to i (meaning the i-th vehicle route candidate) (step S413).
- step S414 the variable i is incremented by +1 (step S414), and the same process is repeated for all predicted vehicle path candidates (step S415).
- the i-th own vehicle path candidate is selected as a path where the own vehicle can travel, and information on X (t) and u (t) corresponding to the i-th own vehicle path candidate (trajectory) is output terminal 9 side. Output to.
- the safety route saftypath i for which the minimum value Smin of the safety evaluation value S (i) is obtained.
- a predetermined value that is arbitrarily set within a range that satisfies the safety standards is considered, and a plurality of vehicle path candidates that satisfy a safety condition that exceeds the predetermined value are selected in this embodiment.
- the actuator unit force corresponding to the output terminal 9 is an operation signal output from the setting maximum efficiency course selection unit 63 in the case of a steering, accelerator or brake itself directly driven by an electric control system in automatic operation ( The steering, accelerator, or brake can be operated using the selected trajectory x (t), u (t) as is.
- the actuator unit force corresponding to the output terminal 9 is an operation that the maximum efficiency course selection unit 63 within the setting outputs if it is an actuator that operates the steering, accelerator pedal, or brake pedal (that is, the driver's hand or foot). Calculate the operating torque based on the signal (corresponding to x (t), u (t) of the selected trajectory), and perform the operation by applying the torque to the steering wheel or brake.
- the automatic operation can be overridden by a human operation, and can be applied not only to automatic driving but also to a driving operation assisting device.
- the predetermined value input unit 8 may be an accelerator pedal, and the predetermined value may be variably set so as to increase from the initial set value of the predetermined value in conjunction with the amount of depression of the accelerator pedal by the driver.
- the driver it is a driver's knowledge that the greater the accelerator pedal depression amount, the greater the driving risk related to the vehicle's own driving from the current driving state, and the driving efficiency is given priority (early arrived at the destination).
- the variable setting of the predetermined value (increasing driving risk) linked to the amount of depression of the accelerator pedal can be said to be a response in accordance with the actual situation.
- the predetermined value input unit 8 is used as a brake pedal, and the predetermined value is decreased from the initial set value of the predetermined value or the current set value force in conjunction with the depression amount of the brake pedal by the driver. May be variably set. That is, from the current running state, the brake pedal The greater the amount of pedal depression, the less the driving risk associated with driving the vehicle, the more it can be recognized as the intention, and the variable setting of the predetermined value linked to the amount of depression of the brake pedal (lowering the driving risk) is also a reality. It can be said that it corresponds to.
- the predetermined value input unit 8 is a mode selection switch (may be a lever) related to the driving mode, and a luxury mode and a sports mode are prepared as driving modes
- the predetermined value may be variably set so as to rise from the initial set value of the predetermined value in conjunction with the mode selection operation.
- the selection of the sport mode can be recognized as a manifestation of intention, given the fact that driving efficiency related to driving the vehicle increases, and prioritizing the driving efficiency by increasing the speed (arriving at the destination earlier).
- the variable setting of the predetermined value linked to the selection operation of the mode selection switch also seems to correspond to the actual situation.
- the upper limit when the predetermined value that defines the allowable level of the safety evaluation value is made variable is changed as a fixed value in advance by the insurance company of the car insurance in accordance with the insurance premium. It is also possible to set the disabled state. In other words, the insurance company shall preliminarily set an upper limit value that defines the variable range of the predetermined value that can be changed by the accelerator pedal operation, etc., under the insurance contract with each driver. It is also feasible to conclude an insurance contract with the driver of the vehicle with an insurance premium corresponding to the upper limit value.
- the upper limit value defines the allowable range of the risk level.If the upper limit value allowed by the driver is high, the driving risk increases, so the insurance premium increases, while the upper limit value allowed by the driver is low. If it is acceptable, the insurance risk can be reduced by reducing the insurance premium, so it is possible to make an insurance contract that matches the driving risk and the driving efficiency.
- the safety evaluation value obtained by evaluating the safety of the vehicle is used as the first evaluation value, and the efficiency evaluation obtained by evaluating the traveling efficiency of the vehicle as the second evaluation value.
- different evaluation values other than safety evaluation values and efficiency evaluation values may be used as the first and second evaluation values.
- selecting the own vehicle route candidate based on the second evaluation value it is not limited to selecting the own vehicle route candidate having the maximum second evaluation value, and may be the second, third, etc. The important point is that it is not a candidate for the own vehicle route with the smallest second evaluation value. Therefore, in determining the own vehicle route from among a plurality of own vehicle route candidates, The value of the evaluation value of 1 is selected! /, The own vehicle route candidate is selected, and the second evaluation value is selected from the selected own vehicle route candidates. It is also possible to select an arbitrary own vehicle route from the relevant own vehicle route candidates.
- the own vehicle route determination method and the own vehicle route determination device are useful for determining one of a plurality of predicted vehicle route candidates as an optimum travelable route. Yes, especially suitable for automatic driving of own vehicles.
Abstract
Description
Claims
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP07715118A EP1990788B1 (en) | 2006-03-01 | 2007-03-01 | Vehicle path determining method and vehicle course determining device |
US12/083,239 US8457892B2 (en) | 2006-03-01 | 2007-03-01 | Own-vehicle-path determining method and own-vehicle-path determining apparatus |
JP2008503814A JP4743275B2 (ja) | 2006-03-01 | 2007-03-01 | 自車進路決定方法および自車進路決定装置 |
CN2007800072116A CN101395648B (zh) | 2006-03-01 | 2007-03-01 | 本车路线确定方法和本车路线确定设备 |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2006055441 | 2006-03-01 | ||
JP2006-055441 | 2006-03-01 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2007102405A1 true WO2007102405A1 (ja) | 2007-09-13 |
Family
ID=38474836
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2007/053955 WO2007102405A1 (ja) | 2006-03-01 | 2007-03-01 | 自車進路決定方法および自車進路決定装置 |
Country Status (5)
Country | Link |
---|---|
US (1) | US8457892B2 (ja) |
EP (1) | EP1990788B1 (ja) |
JP (1) | JP4743275B2 (ja) |
CN (1) | CN101395648B (ja) |
WO (1) | WO2007102405A1 (ja) |
Cited By (34)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2009122770A (ja) * | 2007-11-12 | 2009-06-04 | Toyota Motor Corp | 走行軌跡生成方法及び走行軌跡生成装置 |
JP2009137410A (ja) * | 2007-12-05 | 2009-06-25 | Toyota Motor Corp | 走行軌跡生成方法及び走行軌跡生成装置 |
JP2009166623A (ja) * | 2008-01-15 | 2009-07-30 | Toyota Motor Corp | 走行軌跡生成装置及び走行軌跡生成方法 |
JP2009262837A (ja) * | 2008-04-25 | 2009-11-12 | Toyota Motor Corp | 車両の走行制御装置 |
JP2010228740A (ja) * | 2009-03-05 | 2010-10-14 | Nissan Motor Co Ltd | 走行経路生成装置、走行経路生成方法、及び運転操作支援装置 |
WO2011052247A1 (ja) * | 2009-10-30 | 2011-05-05 | トヨタ自動車株式会社 | 運転支援装置 |
WO2012029878A1 (ja) * | 2010-09-03 | 2012-03-08 | トヨタ自動車株式会社 | 環境マップ作成装置及び方法、行動予測装置及び方法 |
CN104412309A (zh) * | 2012-06-27 | 2015-03-11 | 三菱电机株式会社 | 推荐行驶模式生成装置 |
JP5682563B2 (ja) * | 2009-08-20 | 2015-03-11 | 日本電気株式会社 | 移動体軌跡識別システム、移動体軌跡識別方法および移動体軌跡識別プログラム |
EP3282226A1 (en) | 2016-08-10 | 2018-02-14 | Toyota Jidosha Kabushiki Kaisha | Autonomous driving system and autonomous driving vehicle |
US20180260907A1 (en) * | 2007-05-10 | 2018-09-13 | Allstate Insurance Company | System for risk mitigation based on road geometry and weather factors |
US10343686B2 (en) | 2016-08-10 | 2019-07-09 | Toyota Jidosha Kabushiki Kaisha | Autonomous driving system |
US10464604B2 (en) | 2016-08-10 | 2019-11-05 | Toyota Jidosha Kabushiki Kaisha | Autonomous driving system |
US10530569B2 (en) | 2017-07-20 | 2020-01-07 | International Business Machines Corporation | Game data offloading to a blockchain |
US10535207B1 (en) | 2019-03-29 | 2020-01-14 | Toyota Motor North America, Inc. | Vehicle data sharing with interested parties |
US10664918B1 (en) | 2014-01-24 | 2020-05-26 | Allstate Insurance Company | Insurance system related to a vehicle-to-vehicle communication system |
US10663973B2 (en) | 2016-08-10 | 2020-05-26 | Toyota Jidosha Kabushiki Kaisha | Autonomous driving system |
US10684621B2 (en) | 2016-02-29 | 2020-06-16 | Toyota Jidosha Kabushiki Kaisha | Vehicle control device and vehicle control method |
JP2020114689A (ja) * | 2019-01-17 | 2020-07-30 | マツダ株式会社 | 車両運転支援装置 |
US10733673B1 (en) | 2014-01-24 | 2020-08-04 | Allstate Insurance Company | Reward system related to a vehicle-to-vehicle communication system |
US10740850B1 (en) | 2014-01-24 | 2020-08-11 | Allstate Insurance Company | Reward system related to a vehicle-to-vehicle communication system |
US10783586B1 (en) | 2014-02-19 | 2020-09-22 | Allstate Insurance Company | Determining a property of an insurance policy based on the density of vehicles |
US10783587B1 (en) | 2014-02-19 | 2020-09-22 | Allstate Insurance Company | Determining a driver score based on the driver's response to autonomous features of a vehicle |
US10796369B1 (en) | 2014-02-19 | 2020-10-06 | Allstate Insurance Company | Determining a property of an insurance policy based on the level of autonomy of a vehicle |
US10803525B1 (en) | 2014-02-19 | 2020-10-13 | Allstate Insurance Company | Determining a property of an insurance policy based on the autonomous features of a vehicle |
US10885592B2 (en) | 2016-02-02 | 2021-01-05 | Allstate Insurance Company | Subjective route risk mapping and mitigation |
US10896555B2 (en) | 2019-03-29 | 2021-01-19 | Toyota Motor North America, Inc. | Vehicle data sharing with interested parties |
US10956983B1 (en) | 2014-02-19 | 2021-03-23 | Allstate Insurance Company | Insurance system for analysis of autonomous driving |
US11062341B2 (en) | 2007-05-10 | 2021-07-13 | Allstate Insurance Company | Road segment safety rating system |
US11440566B2 (en) | 2019-08-29 | 2022-09-13 | Toyota Jidosha Kabushiki Kaisha | Vehicle control system |
US11565695B2 (en) | 2007-05-10 | 2023-01-31 | Arity International Limited | Route risk mitigation |
WO2023053165A1 (ja) * | 2021-09-28 | 2023-04-06 | 株式会社Subaru | 運転支援装置及びコンピュータプログラムを記録した記録媒体 |
US11634132B2 (en) | 2019-08-29 | 2023-04-25 | Toyota Jidosha Kabushiki Kaisha | Vehicle deceleration control system |
US11869281B2 (en) | 2019-03-29 | 2024-01-09 | Toyota Motor North America, Inc. | Vehicle data sharing with interested parties |
Families Citing this family (52)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8793066B2 (en) | 2006-06-27 | 2014-07-29 | Microsoft Corporation | Route monetization |
US7610151B2 (en) | 2006-06-27 | 2009-10-27 | Microsoft Corporation | Collaborative route planning for generating personalized and context-sensitive routing recommendations |
US10157422B2 (en) | 2007-05-10 | 2018-12-18 | Allstate Insurance Company | Road segment safety rating |
US8060297B2 (en) | 2007-12-14 | 2011-11-15 | Microsoft Corporation | Route transfer between devices |
US8428859B2 (en) | 2007-12-14 | 2013-04-23 | Microsoft Corporation | Federated route production |
US8090532B2 (en) | 2007-12-14 | 2012-01-03 | Microsoft Corporation | Pedestrian route production |
US8473198B2 (en) | 2007-12-14 | 2013-06-25 | Microsoft Corporation | Additional content based on intended travel destination |
US20090210142A1 (en) * | 2008-02-19 | 2009-08-20 | Microsoft Corporation | Safe route configuration |
US20090210302A1 (en) * | 2008-02-19 | 2009-08-20 | Microsoft Corporation | Route reward augmentation |
US8352112B2 (en) * | 2009-04-06 | 2013-01-08 | GM Global Technology Operations LLC | Autonomous vehicle management |
DE102009045661A1 (de) * | 2009-10-14 | 2011-04-21 | Robert Bosch Gmbh | Verfahren zur Bestimmung wenigstens eines befahrbaren Bereichs in der, insbesondere für die Fahrzeugführung relevanten Umgebung eines Kraftfahrzeugs |
DE112009005485T5 (de) * | 2009-12-28 | 2012-10-18 | Toyota Jidosha Kabushiki Kaisha | Fahrunterstützungsvorrichtung |
DE102010045461A1 (de) * | 2010-09-14 | 2012-03-15 | Siemens Aktiengesellschaft | Verfahren zur Visualisierung der Gleisbelegung |
CN103155014B (zh) | 2010-10-05 | 2015-04-29 | 丰田自动车株式会社 | 碰撞判断装置 |
EP2562060B1 (en) | 2011-08-22 | 2014-10-01 | Honda Research Institute Europe GmbH | A method and system for predicting movement behavior of a target traffic object |
JP5979352B2 (ja) * | 2012-04-16 | 2016-08-24 | セイコーエプソン株式会社 | 情報処理装置、移動予測システム及び移動予測方法 |
US9037399B2 (en) | 2012-06-20 | 2015-05-19 | Microsoft Technology Licensing, Llc | Pluggable route-planning module |
JP5981332B2 (ja) * | 2012-12-21 | 2016-08-31 | 株式会社日本自動車部品総合研究所 | 走行経路生成装置 |
KR20140104610A (ko) * | 2013-02-20 | 2014-08-29 | 한국전자통신연구원 | 조명 통신을 이용한 실시간 이동 경로 추정 장치 및 방법 |
US9147353B1 (en) | 2013-05-29 | 2015-09-29 | Allstate Insurance Company | Driving analysis using vehicle-to-vehicle communication |
US8930060B1 (en) * | 2013-07-15 | 2015-01-06 | Ford Global Technologies | Post-impact path assist for vehicles |
US9552735B2 (en) * | 2013-11-22 | 2017-01-24 | Ford Global Technologies, Llc | Autonomous vehicle identification |
US9340207B2 (en) * | 2014-01-16 | 2016-05-17 | Toyota Motor Engineering & Manufacturing North America, Inc. | Lateral maneuver planner for automated driving system |
DE102014200687A1 (de) * | 2014-01-16 | 2015-07-16 | Robert Bosch Gmbh | Verfahren zum Betreiben eines Fahrzeugs |
JP6298322B2 (ja) * | 2014-02-27 | 2018-03-20 | 株式会社ゼンリン | 経路探索装置、経路探索方法およびプログラム |
US10249189B1 (en) * | 2015-01-26 | 2019-04-02 | State Farm Mutual Automobile Insurance Company | Generating emergency vehicle warnings |
EP3845427A1 (en) * | 2015-02-10 | 2021-07-07 | Mobileye Vision Technologies Ltd. | Sparse map for autonomous vehicle navigation |
JP6025273B2 (ja) * | 2015-03-17 | 2016-11-16 | 富士重工業株式会社 | 車両の走行制御装置 |
EP3115942B1 (en) * | 2015-07-10 | 2019-10-16 | Volvo Car Corporation | Method and system for smart use of in-car time with advanced pilot assist and autonomous drive |
EP3144919B1 (de) * | 2015-09-18 | 2020-06-24 | Continental Automotive GmbH | Vorrichtung und verfahren zur anfahrassistenz für ein kraftfahrzeug |
KR101714250B1 (ko) * | 2015-10-28 | 2017-03-08 | 현대자동차주식회사 | 주변 차량의 이동 경로의 예측 방법 |
US20190084561A1 (en) * | 2016-03-15 | 2019-03-21 | Honda Motor Co., Ltd. | Vehicle control apparatus, vehicle control method, and vehicle control program |
CN105922994B (zh) * | 2016-04-21 | 2018-08-03 | 深圳市元征科技股份有限公司 | 一种生成指示车辆直线行驶方向的方法及装置 |
CN106125076A (zh) * | 2016-07-13 | 2016-11-16 | 南京慧尔视智能科技有限公司 | 一种应用于城市交通的防撞雷达预警方法与装置 |
DE102017001707A1 (de) * | 2017-02-22 | 2018-08-23 | GM Global Technology Operations LLC (n. d. Ges. d. Staates Delaware) | Benachrichtigung über einen geschätzten Bewegungspfad eines Fahrzeugs |
JP6558393B2 (ja) * | 2017-04-06 | 2019-08-14 | トヨタ自動車株式会社 | 進路設定装置及び進路設定方法 |
CN107180277B (zh) * | 2017-05-24 | 2020-03-27 | 江西理工大学 | 应用精英反向和声搜索的无人机巡检路径规划方法 |
JP6897349B2 (ja) * | 2017-06-09 | 2021-06-30 | トヨタ自動車株式会社 | 運転支援装置 |
CN109109865B (zh) * | 2017-06-23 | 2020-05-08 | 长城汽车股份有限公司 | 车辆位置检测方法与装置以及一种车辆 |
EP3686864A4 (en) * | 2017-09-22 | 2021-01-27 | Sony Corporation | INFORMATION PROCESSING DEVICE, AUTONOMOUS TRAVELING DEVICE, PROCESS AND PROGRAM |
GB2570887B (en) * | 2018-02-07 | 2020-08-12 | Jaguar Land Rover Ltd | A system for a vehicle |
DE102018109885A1 (de) * | 2018-04-24 | 2018-12-20 | Continental Teves Ag & Co. Ohg | Verfahren und Vorrichtung zum kooperativen Abstimmen von zukünftigen Fahrmanövern eines Fahrzeugs mit Fremdmanövern zumindest eines Fremdfahrzeugs |
DE102018109883A1 (de) * | 2018-04-24 | 2018-12-20 | Continental Teves Ag & Co. Ohg | Verfahren und Vorrichtung zum kooperativen Abstimmen von zukünftigen Fahrmanövern eines Fahrzeugs mit Fremdmanövern zumindest eines Fremdfahrzeugs |
JP7111517B2 (ja) * | 2018-06-14 | 2022-08-02 | シャープ株式会社 | 走行装置、走行装置の走行制御方法、走行装置の走行制御プログラムおよび記録媒体 |
CN109739246B (zh) * | 2019-02-19 | 2022-10-11 | 阿波罗智能技术(北京)有限公司 | 一种变换车道过程中的决策方法、装置、设备及存储介质 |
US11364936B2 (en) * | 2019-02-28 | 2022-06-21 | Huawei Technologies Co., Ltd. | Method and system for controlling safety of ego and social objects |
WO2020242065A1 (ko) * | 2019-05-31 | 2020-12-03 | 주식회사 라운지랩 | 위험도 판단에 기초한 로봇 움직임 제어 방법 및 이를 이용한 이동 로봇 장치 |
US11345342B2 (en) * | 2019-09-27 | 2022-05-31 | Intel Corporation | Potential collision warning system based on road user intent prediction |
JP2021142788A (ja) * | 2020-03-10 | 2021-09-24 | トヨタ自動車株式会社 | 運転支援システム |
CN111724598B (zh) * | 2020-06-29 | 2022-04-05 | 北京百度网讯科技有限公司 | 用于自动驾驶规划路径的方法、装置、设备以及存储介质 |
US11858536B1 (en) * | 2020-10-31 | 2024-01-02 | Uatc, Llc | Systems and methods for interactive prediction and planning |
US11884304B2 (en) | 2021-09-08 | 2024-01-30 | Ford Global Technologies, Llc | System, method, and computer program product for trajectory scoring during an autonomous driving operation implemented with constraint independent margins to actors in the roadway |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09303544A (ja) * | 1996-03-15 | 1997-11-25 | Toyota Motor Corp | 変速機の制御装置 |
JPH10207504A (ja) * | 1997-01-20 | 1998-08-07 | Komatsu Ltd | 人工知能機械および人工知能機械システム |
JPH11126294A (ja) * | 1997-10-23 | 1999-05-11 | Toyota Motor Corp | 移動体交通制御システム |
WO2000040929A1 (en) | 1998-12-31 | 2000-07-13 | Honeywell Inc. | Multi-dimensional route optimizer |
JP2002260155A (ja) * | 2001-03-05 | 2002-09-13 | Natl Inst For Land & Infrastructure Management Mlit | 走行支援情報処理装置 |
WO2003025507A2 (en) | 2001-09-20 | 2003-03-27 | Honeywell International, Inc. | Four-dimensional route planner |
JP2003123185A (ja) * | 2001-10-11 | 2003-04-25 | Hitachi Ltd | 危険情報集配信装置、警報発生装置、車両危険情報送信装置および経路探索装置 |
JP2004504216A (ja) * | 2000-07-26 | 2004-02-12 | ダイムラークライスラー・アクチェンゲゼルシャフト | 車両用自動制動及び操縦システム |
JP2004199389A (ja) * | 2002-12-18 | 2004-07-15 | Toyota Motor Corp | 運転補助システム及び装置 |
JP2004257852A (ja) * | 2003-02-26 | 2004-09-16 | Nissan Motor Co Ltd | ナビゲーション装置 |
Family Cites Families (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2840946B2 (ja) * | 1988-04-13 | 1998-12-24 | 本田技研工業株式会社 | ナビゲーション装置における推奨ルートの検索表示方法 |
JP2782135B2 (ja) * | 1991-12-18 | 1998-07-30 | 本田技研工業株式会社 | 車両走行案内装置 |
JP3214122B2 (ja) | 1993-01-19 | 2001-10-02 | 三菱電機株式会社 | 危険状況警報装置 |
JP2799375B2 (ja) | 1993-09-30 | 1998-09-17 | 本田技研工業株式会社 | 衝突防止装置 |
JPH07225612A (ja) | 1994-02-15 | 1995-08-22 | Fujitsu Ltd | 時間軸を探索空間に取り入れた経路探索方法,及び装置 |
JP3218865B2 (ja) | 1994-06-28 | 2001-10-15 | 富士通株式会社 | 時間軸を探索空間に取り入れた経路探索装置 |
JP3017956B2 (ja) * | 1997-03-26 | 2000-03-13 | 運輸省船舶技術研究所長 | 飛行場管制支援システム |
US6253129B1 (en) * | 1997-03-27 | 2001-06-26 | Tripmaster Corporation | System for monitoring vehicle efficiency and vehicle and driver performance |
US6192314B1 (en) * | 1998-03-25 | 2001-02-20 | Navigation Technologies Corp. | Method and system for route calculation in a navigation application |
JP2004508627A (ja) * | 2000-09-08 | 2004-03-18 | レイセオン・カンパニー | 経路予測システムおよび方法 |
JP4200131B2 (ja) * | 2002-05-07 | 2008-12-24 | ローベルト ボツシユ ゲゼルシヤフト ミツト ベシユレンクテル ハフツング | 第1の対象物の事故の危険性を少なくとも1つの第2の対象物により判定する方法 |
JP4145644B2 (ja) | 2002-12-17 | 2008-09-03 | 富士重工業株式会社 | 車両の走行制御装置 |
JP2004212160A (ja) | 2002-12-27 | 2004-07-29 | Matsushita Electric Ind Co Ltd | 経路検索装置及び車輌内環境変化用装置 |
JP2005043068A (ja) * | 2003-07-22 | 2005-02-17 | Toyota Motor Corp | 経路案内装置、センターおよび経路探索方法 |
JP2005098714A (ja) * | 2003-09-22 | 2005-04-14 | Casio Comput Co Ltd | ナビゲーションシステム、地図データ提供方法、及び、プログラム |
US20060247852A1 (en) * | 2005-04-29 | 2006-11-02 | Kortge James M | System and method for providing safety-optimized navigation route planning |
EP1926654B1 (de) * | 2005-09-15 | 2009-12-09 | Continental Teves AG & Co. oHG | Verfahren und vorrichtung zum lenken eines kraftfahrzeugs |
US7579942B2 (en) * | 2006-10-09 | 2009-08-25 | Toyota Motor Engineering & Manufacturing North America, Inc. | Extra-vehicular threat predictor |
-
2007
- 2007-03-01 WO PCT/JP2007/053955 patent/WO2007102405A1/ja active Application Filing
- 2007-03-01 EP EP07715118A patent/EP1990788B1/en not_active Expired - Fee Related
- 2007-03-01 US US12/083,239 patent/US8457892B2/en active Active
- 2007-03-01 JP JP2008503814A patent/JP4743275B2/ja active Active
- 2007-03-01 CN CN2007800072116A patent/CN101395648B/zh not_active Expired - Fee Related
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH09303544A (ja) * | 1996-03-15 | 1997-11-25 | Toyota Motor Corp | 変速機の制御装置 |
JPH10207504A (ja) * | 1997-01-20 | 1998-08-07 | Komatsu Ltd | 人工知能機械および人工知能機械システム |
JPH11126294A (ja) * | 1997-10-23 | 1999-05-11 | Toyota Motor Corp | 移動体交通制御システム |
US6169495B1 (en) | 1997-10-23 | 2001-01-02 | Toyota Jidosha Kabushiki Kaisha | Vehicle traffic control system |
WO2000040929A1 (en) | 1998-12-31 | 2000-07-13 | Honeywell Inc. | Multi-dimensional route optimizer |
JP2004504216A (ja) * | 2000-07-26 | 2004-02-12 | ダイムラークライスラー・アクチェンゲゼルシャフト | 車両用自動制動及び操縦システム |
JP2002260155A (ja) * | 2001-03-05 | 2002-09-13 | Natl Inst For Land & Infrastructure Management Mlit | 走行支援情報処理装置 |
WO2003025507A2 (en) | 2001-09-20 | 2003-03-27 | Honeywell International, Inc. | Four-dimensional route planner |
JP2003123185A (ja) * | 2001-10-11 | 2003-04-25 | Hitachi Ltd | 危険情報集配信装置、警報発生装置、車両危険情報送信装置および経路探索装置 |
JP2004199389A (ja) * | 2002-12-18 | 2004-07-15 | Toyota Motor Corp | 運転補助システム及び装置 |
JP2004257852A (ja) * | 2003-02-26 | 2004-09-16 | Nissan Motor Co Ltd | ナビゲーション装置 |
Non-Patent Citations (2)
Title |
---|
BROADHURST, S. BAKER, T. KANADE: "Monte Carlo Road Safety Reasoning", IEEE INTELLIGENT VEHICLE SYMPOSIUM (IV2005), IEEE, June 2005 (2005-06-01) |
See also references of EP1990788A4 |
Cited By (52)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US11062341B2 (en) | 2007-05-10 | 2021-07-13 | Allstate Insurance Company | Road segment safety rating system |
US11565695B2 (en) | 2007-05-10 | 2023-01-31 | Arity International Limited | Route risk mitigation |
US10872380B2 (en) | 2007-05-10 | 2020-12-22 | Allstate Insurance Company | Route risk mitigation |
US11087405B2 (en) * | 2007-05-10 | 2021-08-10 | Allstate Insurance Company | System for risk mitigation based on road geometry and weather factors |
US20180260907A1 (en) * | 2007-05-10 | 2018-09-13 | Allstate Insurance Company | System for risk mitigation based on road geometry and weather factors |
US11847667B2 (en) | 2007-05-10 | 2023-12-19 | Allstate Insurance Company | Road segment safety rating system |
US11037247B2 (en) | 2007-05-10 | 2021-06-15 | Allstate Insurance Company | Route risk mitigation |
US11004152B2 (en) | 2007-05-10 | 2021-05-11 | Allstate Insurance Company | Route risk mitigation |
JP2009122770A (ja) * | 2007-11-12 | 2009-06-04 | Toyota Motor Corp | 走行軌跡生成方法及び走行軌跡生成装置 |
JP2009137410A (ja) * | 2007-12-05 | 2009-06-25 | Toyota Motor Corp | 走行軌跡生成方法及び走行軌跡生成装置 |
JP2009166623A (ja) * | 2008-01-15 | 2009-07-30 | Toyota Motor Corp | 走行軌跡生成装置及び走行軌跡生成方法 |
JP2009262837A (ja) * | 2008-04-25 | 2009-11-12 | Toyota Motor Corp | 車両の走行制御装置 |
JP2010228740A (ja) * | 2009-03-05 | 2010-10-14 | Nissan Motor Co Ltd | 走行経路生成装置、走行経路生成方法、及び運転操作支援装置 |
JP5682563B2 (ja) * | 2009-08-20 | 2015-03-11 | 日本電気株式会社 | 移動体軌跡識別システム、移動体軌跡識別方法および移動体軌跡識別プログラム |
JP2011096105A (ja) * | 2009-10-30 | 2011-05-12 | Toyota Motor Corp | 運転支援装置 |
WO2011052247A1 (ja) * | 2009-10-30 | 2011-05-05 | トヨタ自動車株式会社 | 運転支援装置 |
US8947218B2 (en) | 2009-10-30 | 2015-02-03 | Toyota Jidosha Kabushiki Kaisha | Driving support device |
JP2012058780A (ja) * | 2010-09-03 | 2012-03-22 | Toyota Motor Corp | 環境マップ作成装置及び方法、行動予測装置及び方法 |
WO2012029878A1 (ja) * | 2010-09-03 | 2012-03-08 | トヨタ自動車株式会社 | 環境マップ作成装置及び方法、行動予測装置及び方法 |
US9696167B2 (en) | 2012-06-27 | 2017-07-04 | Mitsubishi Electric Corporation | Recommended-drive-pattern generation device and recommended-drive-pattern generation method |
CN104412309A (zh) * | 2012-06-27 | 2015-03-11 | 三菱电机株式会社 | 推荐行驶模式生成装置 |
US10740850B1 (en) | 2014-01-24 | 2020-08-11 | Allstate Insurance Company | Reward system related to a vehicle-to-vehicle communication system |
US11295391B1 (en) | 2014-01-24 | 2022-04-05 | Allstate Insurance Company | Reward system related to a vehicle-to-vehicle communication system |
US10664918B1 (en) | 2014-01-24 | 2020-05-26 | Allstate Insurance Company | Insurance system related to a vehicle-to-vehicle communication system |
US11551309B1 (en) | 2014-01-24 | 2023-01-10 | Allstate Insurance Company | Reward system related to a vehicle-to-vehicle communication system |
US10733673B1 (en) | 2014-01-24 | 2020-08-04 | Allstate Insurance Company | Reward system related to a vehicle-to-vehicle communication system |
US10803525B1 (en) | 2014-02-19 | 2020-10-13 | Allstate Insurance Company | Determining a property of an insurance policy based on the autonomous features of a vehicle |
US10783586B1 (en) | 2014-02-19 | 2020-09-22 | Allstate Insurance Company | Determining a property of an insurance policy based on the density of vehicles |
US10783587B1 (en) | 2014-02-19 | 2020-09-22 | Allstate Insurance Company | Determining a driver score based on the driver's response to autonomous features of a vehicle |
US10796369B1 (en) | 2014-02-19 | 2020-10-06 | Allstate Insurance Company | Determining a property of an insurance policy based on the level of autonomy of a vehicle |
US10956983B1 (en) | 2014-02-19 | 2021-03-23 | Allstate Insurance Company | Insurance system for analysis of autonomous driving |
US10885592B2 (en) | 2016-02-02 | 2021-01-05 | Allstate Insurance Company | Subjective route risk mapping and mitigation |
US10684621B2 (en) | 2016-02-29 | 2020-06-16 | Toyota Jidosha Kabushiki Kaisha | Vehicle control device and vehicle control method |
US11835956B2 (en) | 2016-02-29 | 2023-12-05 | Toyota Jidosha Kabushiki Kaisha | Vehicle control device and vehicle control method |
EP3282226A1 (en) | 2016-08-10 | 2018-02-14 | Toyota Jidosha Kabushiki Kaisha | Autonomous driving system and autonomous driving vehicle |
US10699579B2 (en) | 2016-08-10 | 2020-06-30 | Toyota Jidosha Kabushiki Kaisha | Autonomous driving system and autonomous driving vehicle |
US10663973B2 (en) | 2016-08-10 | 2020-05-26 | Toyota Jidosha Kabushiki Kaisha | Autonomous driving system |
KR20180018379A (ko) | 2016-08-10 | 2018-02-21 | 도요타 지도샤(주) | 자동 운전 시스템 및 자동 운전 차량 |
US11275382B2 (en) | 2016-08-10 | 2022-03-15 | Toyota Jidosha Kabushiki Kaisha | Autonomous driving system |
US10343686B2 (en) | 2016-08-10 | 2019-07-09 | Toyota Jidosha Kabushiki Kaisha | Autonomous driving system |
US11703876B2 (en) | 2016-08-10 | 2023-07-18 | Toyota Jidosha Kabushiki Kaisha | Autonomous driving system |
US10464604B2 (en) | 2016-08-10 | 2019-11-05 | Toyota Jidosha Kabushiki Kaisha | Autonomous driving system |
US10530569B2 (en) | 2017-07-20 | 2020-01-07 | International Business Machines Corporation | Game data offloading to a blockchain |
JP7225816B2 (ja) | 2019-01-17 | 2023-02-21 | マツダ株式会社 | 車両運転支援装置 |
JP2020114689A (ja) * | 2019-01-17 | 2020-07-30 | マツダ株式会社 | 車両運転支援装置 |
US11100728B2 (en) | 2019-03-29 | 2021-08-24 | Toyota Motor North America, Inc. | Vehicle data sharing with interested parties |
US10535207B1 (en) | 2019-03-29 | 2020-01-14 | Toyota Motor North America, Inc. | Vehicle data sharing with interested parties |
US10896555B2 (en) | 2019-03-29 | 2021-01-19 | Toyota Motor North America, Inc. | Vehicle data sharing with interested parties |
US11869281B2 (en) | 2019-03-29 | 2024-01-09 | Toyota Motor North America, Inc. | Vehicle data sharing with interested parties |
US11634132B2 (en) | 2019-08-29 | 2023-04-25 | Toyota Jidosha Kabushiki Kaisha | Vehicle deceleration control system |
US11440566B2 (en) | 2019-08-29 | 2022-09-13 | Toyota Jidosha Kabushiki Kaisha | Vehicle control system |
WO2023053165A1 (ja) * | 2021-09-28 | 2023-04-06 | 株式会社Subaru | 運転支援装置及びコンピュータプログラムを記録した記録媒体 |
Also Published As
Publication number | Publication date |
---|---|
EP1990788B1 (en) | 2012-09-05 |
US8457892B2 (en) | 2013-06-04 |
JPWO2007102405A1 (ja) | 2009-07-23 |
CN101395648A (zh) | 2009-03-25 |
EP1990788A1 (en) | 2008-11-12 |
EP1990788A4 (en) | 2010-04-07 |
JP4743275B2 (ja) | 2011-08-10 |
US20090012703A1 (en) | 2009-01-08 |
CN101395648B (zh) | 2011-05-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2007102405A1 (ja) | 自車進路決定方法および自車進路決定装置 | |
JP4353192B2 (ja) | 進路設定方法、装置、プログラム、および自動運転システム | |
WO2007102367A1 (ja) | 物体進路予測方法、装置、プログラム、および自動運転システム | |
JP4211794B2 (ja) | 干渉評価方法、装置、およびプログラム | |
JP6650214B2 (ja) | 衝突後操縦計画を行う方法及びシステム、並びに当該システムを備える車両 | |
JP4396653B2 (ja) | 物体進路予測方法、装置、およびプログラム | |
JP4062353B1 (ja) | 障害物進路予測方法、装置、およびプログラム | |
JP4730137B2 (ja) | 移動体安全性評価方法および移動体安全性評価装置 | |
JP4807385B2 (ja) | 干渉評価方法、装置、およびプログラム | |
JP5082433B2 (ja) | 移動体周囲危険度判定方法、装置、およびプログラム | |
EP3474254A1 (en) | Surrounding environment recognition device | |
US9708004B2 (en) | Method for assisting a driver in driving an ego vehicle and corresponding driver assistance system | |
JP4946739B2 (ja) | 移動体進路取得方法、および、移動体進路取得装置 | |
CN112639849A (zh) | 路径选择方法和路径选择装置 | |
CN109690650A (zh) | 车辆的行驶控制方法及行驶控制装置 | |
CN109407660B (zh) | 用于操作自主车辆的系统和自主车辆 | |
JP2011227582A (ja) | 車両用衝突予測装置 | |
WO2019034514A1 (en) | METHOD AND SYSTEM FOR AVOIDING THE COLLISION OF A VEHICLE | |
JP2012164159A (ja) | 危険度判定装置、危険度判定プログラム及び危険度判定方法 | |
CN114291116B (zh) | 周围车辆轨迹预测方法、装置、车辆及存储介质 | |
WO2022113504A1 (ja) | 電子制御装置 | |
CN114274955A (zh) | 车辆主动避险方法、装置、电子设备及存储介质 | |
JP7405050B2 (ja) | 自動運転装置、自動運転方法及びプログラム |
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: 07715118 Country of ref document: EP Kind code of ref document: A1 |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2008503814 Country of ref document: JP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 12083239 Country of ref document: US |
|
WWE | Wipo information: entry into national phase |
Ref document number: 2007715118 Country of ref document: EP |
|
WWE | Wipo information: entry into national phase |
Ref document number: 200780007211.6 Country of ref document: CN |
|
NENP | Non-entry into the national phase |
Ref country code: DE |