Route Generation Device

Abstract

The technology disclosed in this specification is a technology for generating a route that vehicles can follow.A route generation device related to the technology disclosed in this specification includes an articulated vehicle that includes a first vehicle and at least one second vehicle towed by the first vehicle, and the route generation device includes a route generation unit that generates a route for the articulated vehicles, and a correction unit that corrects the route based on the relationship between the deviation between the route when the first vehicle is made to follow the route and the second vehicle and the shape of the route, to generate a corrected route.

Description

[Technical Field]

[0001] The technology disclosed in this specification relates to a route generation technology for articulated vehicles. [Background technology]

[0002] In recent years, autonomous driving technology has been attracting attention as a way to address labor shortages, particularly in the logistics sector.

[0003] On the other hand, articulated vehicles used in the logistics field, which are made up of a towing vehicle and a towed vehicle, tend to have long vehicle body lengths along the route direction, and the difference in inner wheel rotation on curved roads is likely to be large.

[0004] In response to this, a technology has been disclosed that warns a driver whether or not the vehicle can turn on a curved road based on the minimum turning radius of the vehicle. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Laid-Open No. 2006-27343 Summary of the Invention [Problem to be solved by the invention]

[0006] However, with the technology disclosed in Patent Document 1, it is unclear what kind of route shape will allow turning without deviation.

[0007] The technology disclosed in this specification has been made in consideration of the problems described above, and is a technology for generating a route that a vehicle can follow. [Means for solving the problem]

[0008] A route generation device according to a first aspect of the technology disclosed in the present specification is a route generation device for generating a route for an articulated vehicle having a first vehicle and at least one second vehicle towed by the first vehicle, the route generation device comprising: a route generation unit for generating a route for the articulated vehicle; ,before When the first vehicle is made to follow the route predicted to the second vehicle For the above route side The difference predetermined 1st threshold If the deviation exceeds the first threshold So that it becomes The shape of the path and a correction unit for performing correction to generate a corrected path. [Effects of the Invention]

[0009] According to at least the first aspect of the technology disclosed in the present specification, it is possible to generate a corrected route along which articulated vehicles can travel while suppressing deviation, by correcting the shape of the route.

[0010] Furthermore, objects, features, aspects, and advantages associated with the technology disclosed herein will become more apparent from the detailed description and accompanying drawings set forth below. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram conceptually illustrating an example of the configuration of a route generation device in a vehicle control device that controls articulated vehicles, according to an embodiment. [Figure 2] FIG. 10 is a diagram illustrating an example of the relationship between the curvature of a travel route and the deviation of an articulated vehicle. [Figure 3] FIG. 10 is a diagram illustrating an example of correction of a travel route. [Figure 4] FIG. 1 is a diagram illustrating an example of articulated vehicles. [Figure 5] FIG. 10 is a diagram showing an example of each parameter of a towing vehicle in the case of a two-wheel model. [Figure 6] FIG. 10 is a diagram showing an example of an articulated vehicle in which a dolly is included in the loading platform. [Figure 7] FIG. 10 is a diagram showing examples of parameters of a towing vehicle and a towed vehicle. [Figure 8] FIG. 10 is a diagram showing an example of each parameter on a travel route. [Figure 9] FIG. 10 is a diagram illustrating an example of correction of a travel route. [Figure 10] FIG. 1 is a diagram illustrating an example of articulated vehicles whose traveling is controlled along a route. [Figure 11] FIG. 10 is a diagram showing an example of an articulated vehicle whose travel is controlled along a route after a settling time Ts. [Figure 12] 1 is a diagram conceptually illustrating an example of the configuration of a vehicle control device according to an embodiment; [Figure 13] 1 is a diagram conceptually illustrating an example of the configuration of a vehicle control device according to an embodiment; [Figure 14] 1 is a diagram conceptually illustrating an example of the configuration of a vehicle control device according to an embodiment; [Figure 15] 1 is a diagram conceptually illustrating an example of the configuration of a vehicle control device according to an embodiment; [Figure 16] 1 is a diagram conceptually illustrating an example of the configuration of a vehicle control device according to an embodiment; [Figure 17] FIG. 17 is a diagram illustrating a schematic example of a hardware configuration when the vehicle control device shown in FIGS. 12, 13, 14, 15, and 16 is actually operated. [Figure 18] FIG. 17 is a diagram illustrating a schematic example of a hardware configuration when the vehicle control device shown in FIGS. 12, 13, 14, 15, and 16 is actually operated. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, embodiments will be described with reference to the accompanying drawings. In the following embodiments, detailed features are shown for the purpose of explaining the technology, but these are merely examples and are not necessarily essential features for enabling the embodiments to be implemented.

[0013] The drawings are schematic, and for the sake of convenience, components may be omitted or simplified as appropriate. The relative sizes and positions of components shown in different drawings are not necessarily accurately depicted and may be changed as appropriate. Hatching may also be used in drawings such as plan views that are not cross-sectional views to facilitate understanding of the embodiments.

[0014] In the following description, the same components are denoted by the same reference numerals, and their names and functions are also the same. Therefore, detailed descriptions of them may be omitted to avoid duplication.

[0015] Furthermore, in the description given in this specification, when a certain component is described as "comprising," "including," or "having," unless otherwise specified, this is not an exclusive expression that excludes the presence of other components.

[0016] Furthermore, although ordinal numbers such as "first" or "second" may be used in the descriptions in this specification, these terms are used for convenience to facilitate understanding of the contents of the embodiments, and the contents of the embodiments are not limited to the order that may result from these ordinal numbers.

[0017] <Embodiment> The vehicle control device according to this embodiment will be described below.

[0018] <Configuration of the route generation device> FIG. 1 is a diagram conceptually showing an example of the configuration of a route generation device in a vehicle control device that controls articulated vehicles according to this embodiment.

[0019] As shown in the example in FIG. 1, the route generation device 2000 includes at least a route generation unit 2004 for generating a route for the articulated vehicles, and a correction unit 2002 for correcting the route to generate a corrected route based on the relationship between the deviation between the route and the towed vehicle when the towing vehicle is made to follow the route and the shape of the route.

[0020] Here, a combination vehicle is a vehicle in which multiple vehicles are combined. The combination vehicle includes a towing vehicle and at least one towed vehicle towed by the towing vehicle. The combination vehicle may be equipped with a dolly.

[0021] Tow vehicles include, for example, cars, crossovers, trucks, vans, sport utility vehicles (SUVs), recreational vehicles (RVs), or any other vehicle configured to attach to and tow a towed vehicle.

[0022] A towed vehicle is, for example, a non-powered vehicle that is towed by the power of a towing vehicle, and includes, among others, a utility trailer, a pop-up camper, a travel trailer, a livestock trailer, a flatbed trailer, an enclosed car carrier, or a boat trailer.

[0023] The combination vehicles are connected together using a coupling device such as a kingpin and coupler, a trailer hitch, or a drawbar.

[0024] For example, a towed vehicle may be coupled to a towing vehicle using a trailer hitch, which may be a ball and socket, fifth wheel and gooseneck, or trailer jack, with a receiver hitch attached to the towing vehicle.

[0025] In addition to the mechanical connection between the towed vehicle and the towing vehicle, the towed vehicle may be electrically connected to the towing vehicle, allowing the towed vehicle to be powered from the towing vehicle's rear light circuit and to have the towed vehicle's tail lights, turn signals, brake lights, etc. synchronized with the towing vehicle's lights.

[0026] The route along which the articulated vehicle travels (the route that serves as the target for travel) is defined as the driving route. The driving route is the route along which the articulated vehicle travels among routes (reference routes) obtained from a map database or other source. The driving route is defined in either a global coordinate system or a vehicle coordinate system. A global coordinate system can be a geographic coordinate system, a planar rectangular coordinate system developed on a plane based on a geographic coordinate system, or a coordinate system determined by the designer. A vehicle coordinate system is a coordinate system fixed to each of the towing vehicle and towed vehicle. As the articulated vehicle moves, its position and attitude (angle) relative to the global coordinate system change. A map database is a database that stores map information useful for driving articulated vehicles, such as the coordinates of the roads around which the articulated vehicle travels, the position of white lines, the position of curbs, and the position of traffic lights. Because map databases are often managed in a geographic coordinate system, matching this with a Global Navigation Satellite System (GNSS), which is also output in a geographic coordinate system, makes it possible to obtain information about the roads around the articulated vehicle.

[0027] The reference route is a route obtained from a map database, a video or image captured by a camera attached to a vehicle, or the like, and is defined in a global coordinate system or a vehicle coordinate system.

[0028] Specifically, for example, an image of the area ahead of the vehicle can be acquired using a camera or the like, white lines on the road can be detected in the image, the center of the lane can be calculated, and a route along the center of the lane can be extracted.

[0029] Furthermore, for example, it is possible to calculate the center of a lane by combining GNSS and a map database, and extract a route along the center of the lane.

[0030] Also, for example, a target position can be specified on a map database, and a route to the target position can be calculated using existing technology (for example, the Dijkstra method).

[0031] <Operation of the path generation device> Below, we will explain the operation of a route generation device that corrects a driving route based on the relationship between the deviation between the driving route and the towed vehicle when the towing vehicle is made to follow the driving route and the shape of the driving route.

[0032] In this embodiment, the curvature of the route among the route shapes will be described, but other elements included in the route shape, such as the rate of change of the curvature, may also be used.

[0033] The reference route may be corrected based on the relationship between the deviation between the towed vehicle and a reference route obtained from a map database or the like, rather than the driving route, and the shape of the reference route.

[0034] When an articulated vehicle travels on a curved road, there is a correlation between the curvature of the travel route and the deviation of the articulated vehicle. Here, the deviation of the articulated vehicle refers to the distance between the towing vehicle or towed vehicle that make up the articulated vehicle and the center line of the travel route (the center of the road lane) in a direction that intersects with the direction along the travel route (for example, a direction perpendicular to the direction along the travel route). When calculating this distance, the position of the vehicle, for example the position of the center of gravity, is used as the vehicle position.

[0035] Fig. 2 is a diagram showing an example of the relationship between the curvature of the travel route and the deviation of the articulated vehicle. In Fig. 2, the vertical axis represents the deviation e of the rearmost towed vehicle in the articulated vehicle. y The horizontal axis represents the curvature κ of the travel path.

[0036] Note that Figure 2 was created by performing a simulation using a kinematic model of articulated vehicles to calculate the deviation of an articulated vehicle (the last towed vehicle) traveling on a route with a certain curvature, but it may also be created from the results of an experiment in which articulated vehicles are made to travel on a route with a certain curvature.

[0037] As shown in the example in Figure 2, the deviation of the articulated vehicle (the last towed vehicle) increases as the absolute value of the curvature of the curved road increases (i.e., the sharper the curve). There is also a positive correlation between the absolute value of the curvature of the travel route and the deviation of the articulated vehicle (the last towed vehicle).

[0038] Therefore, if the relationship between the curvature of the travel route and the deviation of the articulated vehicle (the last towed vehicle) as shown in Figure 2 is known in advance, it is possible to predict the degree of deviation that the towing vehicle and towed vehicle that make up the articulated vehicle will have when the articulated vehicle travels on a curved road with a certain curvature.

[0039] In this way, by correcting the shape (particularly the curvature) of the travel route, it is possible to control the travel of the articulated vehicles so that they follow the travel route while suppressing deviation of the articulated vehicles. In other words, it is possible to adjust the deviation of the articulated vehicles simply by correcting the travel route.

[0040] Fig. 3 is a diagram showing an example of correcting a travel route. As shown in the example in Fig. 3, by correcting the curved road so that the curvature of travel route 1 changes to create corrected route 2, it is possible to adjust the deviation of the articulated vehicles.

[0041] <About deviation prediction> Below, we will explain a simulation that uses a kinematic model of the articulated vehicle and virtual articulated vehicle control to predict the deviation of the towed vehicle when the articulated vehicle travels on a curved road with a certain curvature. Using the results of this simulation, for example, if a deviation smaller than a predetermined threshold is predicted, the articulated vehicle can be controlled to travel along an uncorrected travel route, and if a deviation larger than the predetermined threshold is predicted, the deviation can be suppressed by correcting the travel route.

[0042] The kinematics model of an articulated vehicle is explained below. In the following, the articulated vehicle is assumed to be composed of N towed vehicles towed by one towing vehicle.

[0043] FIG. 4 is a diagram showing an example of an articulated vehicle. As shown in the example of FIG. 4, articulated vehicle 100 includes towing vehicle 10, towed vehicle 11, towed vehicle 12, towed vehicle 13, and towed vehicle 14. As shown in FIG. 4, towing vehicle 10 and towed vehicle 11 are connected at hitch point 20. Similarly, towed vehicles are connected to each other at hitch point 20. Hitch point 20 is rotatable horizontally (i.e., within the XY plane). Note that at least one towed vehicle is sufficient, and the number of towed vehicles may be more or less than that shown in FIG. 4.

[0044] Here, the towed vehicles are designated as the first towed vehicle, the second towed vehicle, and the third towed vehicle from the closest to the towing vehicle. The axle center position of the kth towed vehicle relative to the global coordinate system (X, Y) is (x k ,y k ), then the following relation can be obtained from the geometric relationship:

[0045]

number

[0046] Here, t indicates time, and k=0 indicates the towing vehicle. That is, (x0, y0) is the rear axle center position of the towing vehicle. Also, γ kindicates the orientation (angle, not shown) relative to the global coordinate system, and h k f is the distance between the axle center of the towed vehicle and the front hitch point (front hitch offset), and h k r indicates the distance between the axle center of the towed vehicle and the rear hitch point (rear hitch offset).

[0047] Using the above, under the assumption that no sideslip angle occurs, the kinematic model shown below is obtained.

[0048]

number

[0049] where ν0 denotes the translational velocity of the towing vehicle and ζ0 denotes the angular velocity of the towing vehicle.

[0050] According to equation (2), the angular velocity of the towed vehicle can be calculated based on the translational velocity ν0 and the angular velocity ζ0 of the towing vehicle. Furthermore, by integrating the angular velocity of the towed vehicle, the attitude γ of the towed vehicle at each time can be calculated. k can be obtained.

[0051] Furthermore, according to equation (1), the rear axle center position (x0, y0) and the attitude γ k If the axle center position (x k ,y k ) can be obtained.

[0052] As a kinematic model of the towing vehicle, for example, the following kinematic model can be considered, in which the translational velocity ν0 of the towing vehicle and the angular velocity ζ0 of the towing vehicle are input.

[0053]

number

[0054] In addition, the front and rear wheels are often treated as one wheel each. Such models are called two-wheel models because they treat a four-wheeled vehicle as a two-wheeled vehicle.

[0055] In the two-wheel model above, the steering angle δ0 or acceleration α0 of the towing vehicle is input, and the center of gravity of the towing vehicle (x g0 ,y g0 ) and geometric relationships, the following kinematic model is sometimes used:

[0056]

number

[0057] FIG. 5 is a diagram showing an example of each parameter of the towing vehicle in the case of a two-wheel model. As shown in FIG. 5, the steering angle δ of the towing vehicle, the center of gravity (x g0 ,y g0 ), the center position of the rear axle of the towing vehicle (x0, y0), the translational velocity ν0 of the towing vehicle, the angular velocity ζ0 of the towing vehicle, and the attitude γ0 of the towing vehicle are defined.

[0058] Here, the loading platform of the towed vehicle may include an axle called a dolly that can rotate freely in the horizontal direction.

[0059] Fig. 6 is a diagram showing an example of articulated vehicles in which the loading platform includes a dolly. As shown in the example in Fig. 6, loading platform 31 is coupled to towing vehicle 30, and loading platform 32 is further coupled to loading platform 31.

[0060] In such a case, by treating the dolly as one towed vehicle (i.e., treating one loading platform as two towed vehicles), a kinematic model can be constructed using equations (1) and (2) in the same manner as above, and the deviation from the travel path can be calculated. In the case of Figure 6, dolly 11A of loading platform 31 is treated as one towed vehicle, rear axle wheel 12A of loading platform 31 is treated as one towed vehicle, dolly 13A of loading platform 32 is treated as one towed vehicle, and rear axle wheel 14A of loading platform 32 is treated as one towed vehicle.

[0061] The method for calculating the deviation from the travel route will be described below.

[0062] First, the position and orientation (x0, y0, γ0) of the towing vehicle and its translational velocity ν0 are determined from the kinematic model of the towing vehicle or the output of the position and orientation sensors attached to the towing vehicle.

[0063] Next, the position and attitude of the k-th towed vehicle (x k ,y k ,γ k ) is found.

[0064] The position and attitude (route direction) of the travel route can be obtained from a map database or the like, so the deviation of the position of the articulated vehicles (towing vehicle and towed vehicle) can be found by calculating the difference between their positions and the position of the travel route. Similarly, the deviation of the attitude of the articulated vehicles can be found by calculating the difference between their attitude and the attitude of the travel route.

[0065] Here, the deviation between the k-th towed vehicle and the travel route in the direction perpendicular to the route direction is called the position deviation e k,y The deviation of the attitude (angle direction) between the k-th towed vehicle and the travel path is defined as the angular deviation e k,θ Let's say.

[0066] FIG. 7 is a diagram showing examples of parameters for the towing vehicle and the towed vehicle. As shown in FIG. 7, the position (x0, y0) of the towing vehicle, the position deviation e 0,y , the angular deviation of the towing vehicle e 0,θ , the position of the nth towed vehicle (x n ,y n ), the position deviation of the nth towed vehicle e n,y , the angle deviation of the nth towed vehicle e n,θ is defined.

[0067] The following methods are available for calculating the attitude (angle) and curvature of the travel route.

[0068] First, let the lengthwise parameter of the travel path be s, and then use that parameter to calculate the (x, y) coordinates of travel path 1. r (s),y r (s)).

[0069] When using a map database, road coordinates may be incorporated into the map database as point cloud information, but by fitting the point cloud with an appropriate function such as a polynomial or spline, it is possible to express it using such parameters.

[0070] (x r (s),y r (s)), the angle θ at each point s on the travel path 1 r (s) and curvature κ r (s) can be calculated as follows:

[0071]

number

[0072]

number

[0073] Note that the curvature at each point s on the travel route 1 may be incorporated into the map database, in which case it is not necessary to calculate the curvature from the travel route 1 as described above. If the curvature is incorporated into the map database, the curvature at each point s can be referenced or read from the map database.

[0074] FIG. 8 is a diagram showing an example of each parameter on a travel route. As shown in FIG. 8, when the (x, y) coordinates of travel route 1 are (x r (s),y r (s)), the angle θ at s on the travel path 1 r (s), curvature κ r (s) is defined.

[0075] <About corrections> As mentioned above, the angle θ at s of the travel path r (s), curvature κ r (s) is defined. Then, the angle θ of the target towed vehicle is r (s) and curvature κ r The relationship between (s) and (s) is obtained in advance by the above kinematic model or experiments. Here, the relationship is expressed as a function g k Using the above, it is assumed that the following is shown:

[0076]

number

[0077] For example, in Figure 2, e k,y =c k κ r Here, c = -05.66. Note that linear approximation may not be possible depending on the configuration of the articulated vehicles.

[0078] e obtained from the above equation (7) k,y (s) is the amount of correction for the travel path, and θ r (S) perpendicular to the direction of the travel path e k,yIt can be corrected by (s).

[0079] 9 is a diagram showing an example of correction of a travel route. As shown in the example in FIG. 9, the curvature of the travel route 1 is changed by changing θ r (S) perpendicular to the direction e k,y By correcting by (s) to obtain corrected route 2, the deviation of the articulated vehicles can be adjusted.

[0080] In reality, the above equation (7) contains errors, so an adjustment coefficient e k,y Alternatively, it may be multiplied by

[0081] The above formula (7) is applied to the configuration of FIG. 12, which will be described later. In the configuration of FIG. 13 and subsequent figures, the deviation calculated by the deviation prediction unit is expressed as e k,y Let's say.

[0082] Here, the coupling angle will be explained. The coupling angle is a relative angle (γ i -γ i-1 ), but if the initial value of the coupling angle is known, the attitude of each towed vehicle can be estimated by integrating the above equation (2) from time to time.

[0083] One method for determining the initial value of the coupling angle is to utilize the fact that if the towing vehicle is controlled to travel along a straight route, the attitude (angle) of the route and the reference coupling angle will match after a certain number of seconds (settlement time Ts). Note that the settling time Ts can be roughly predicted based on a kinematic model of the articulated vehicles. Whether the route is straight or not can be determined by referring to the curvature of the route.

[0084] Figure 10 is a diagram showing an example of articulated vehicles whose travel is controlled along a route. As shown in the example in Figure 10, of articulated vehicles 100 traveling along route 3, the posture of towing vehicle 10 is in line with the posture (angle, route direction) of route 3, but the joint of towed vehicle 11 is bent at hitch point 20 (having a joint angle greater than 0°), and its posture does not follow the posture of route 3.

[0085] On the other hand, Figure 11 is a diagram showing an example of an articulated vehicle whose travel is controlled along a route after settling time Ts. As the example shown in Figure 11 shows, the attitudes of towing vehicle 10, towed vehicle 11, and towed vehicle 12 of articulated vehicle 100 traveling along route 3 are aligned with the attitude of route 3. In this state, the attitude of articulated vehicle 100 matches the attitude of route 3, and the coupling angles between each vehicle in articulated vehicle 100 are also initialized. By knowing the initial values of the coupling angles, the above equation (2) can be integrated from moment to moment to estimate the attitude of each towed vehicle.

[0086] First Embodiment Figure 12 is a diagram conceptually showing an example of the configuration of a vehicle control device related to this embodiment. As shown in the example in Figure 12, the vehicle control device 200 includes a route generation device 40 and an articulated vehicle 100. The route generation device 40 generates a route for the articulated vehicle 100 using towing position and attitude data input from a position and attitude sensor 50 that estimates the position and attitude of the towing vehicle, and map data obtained from a map database 52.

[0087] The position and orientation sensor 50 estimates the position and orientation of the towing vehicle relative to a global coordinate system. The position and orientation sensor 50 can estimate the position and orientation of the towing vehicle by, for example, using GNSS or a known self-position estimation technology. The position and orientation sensor 50 may be attached to the towing vehicle.

[0088] The route generation device 40 comprises a route generation unit 42, a curvature calculation unit 44, and a route correction unit 46. The route generation unit 42 generates a route (before correction) for the articulated vehicle 100 using towing position and orientation data input from the position and orientation sensor 50 and map data acquired from the map database 52. The route generation unit 42 may generate a reference route, which is an arbitrary route based on the towing position and orientation data and the map data, or may generate a travel route, which is a route along which the articulated vehicle 100 will travel, from among the reference routes.

[0089] The curvature calculation unit 44 calculates the curvature at any point of the route generated by the route generation unit 42. The curvature can be calculated, for example, by referring to map data or by using the above formula (6).

[0090] The route correction unit 46 corrects the route generated by the route generation unit 42 based on the route curvature calculated by the curvature calculation unit 44. Specifically, the route correction unit 46 predicts the deviation of the articulated vehicles traveling on the generated route based on the relationship between the route curvature and the deviation of the articulated vehicles (particularly the towed vehicle). The route correction unit 46 then corrects the route so that the deviation of the articulated vehicles (particularly the towed vehicle) traveling on the route becomes a desired value. Note that if the predicted deviation is the desired value, the route correction unit 46 does not need to correct the route.

[0091] Here, if the relationship between the curvature of the route and the deviation of the articulated vehicles is known in advance through simulation or experiment, such a relationship as shown in FIG. 2 is followed.

[0092] Furthermore, the route correction unit 46 may correct the route using a trained model that has been generated in advance by machine learning the relationship between the shape of the route (including curvature) and the deviation of the articulated vehicles.

[0093] The articulated vehicle 100 includes a towing vehicle control unit 102 and an actuator 104 that drives the towing vehicle. The towing vehicle control unit 102 controls the operation of the actuator 104 so that the articulated vehicle drives along the route corrected by the route correction unit 46 (or a route that has not been corrected). The actuator 104 is, for example, an electric motor. The towing vehicle control unit 102 can use, for example, the pure pursuit method to determine the control amount for the actuator 104.

[0094] With this configuration, by correcting the shape (curvature) of the route, it is possible to control the travel of the articulated vehicles so that they follow the route while suppressing deviation of the articulated vehicles. In other words, it is possible to adjust the deviation of the articulated vehicles simply by correcting the route.

[0095] <Second embodiment> Figure 13 is a diagram conceptually illustrating an example of the configuration of a vehicle control device related to this embodiment. As shown in the example of Figure 13, a vehicle control device 200A includes a route generation device 40A and an articulated vehicle 100. The route generation device 40A generates a route for the articulated vehicle 100 using towing position and attitude data input from a position and attitude sensor 50, map data acquired from a map database 52, and articulation angle data input from a articulation angle sensor 54 that detects the articulation angle between the vehicles. The articulation angle sensor 54 can calculate the articulation angle based on measurements taken using a hall sensor, an encoder, or a camera attached near the hitch point.

[0096] The path generation device 40A includes a path generation unit 42, a path correction unit 46A, and a deviation prediction unit 48 that predicts the deviation of the articulated vehicle based on the articulation angle data and the towing position and attitude data.

[0097] The deviation prediction unit 48 performs virtual vehicle control (simulation) based on the towing position and attitude data and coupling angle data of the articulated vehicle and a kinematic model of the articulated vehicle, and as a result is able to directly predict the deviation of the articulated vehicle (and further the travel trajectory of the articulated vehicle) without taking into account the curvature of the route.The positions and attitudes of all towed vehicles can be calculated based on the position and attitude of the towing vehicle and the coupling angle data, so the deviation prediction unit 48 can predict the deviation of the articulated vehicle.

[0098] The route correction unit 46A corrects the route generated by the route generation unit 42 based on the deviation of the articulated vehicle predicted by the deviation prediction unit 48. Specifically, the route correction unit 46 corrects the route based on the relationship between the deviation of the articulated vehicle and the curvature of the route so that the predicted deviation of the articulated vehicle becomes a desired value. Note that if the predicted deviation is a desired value, the route correction unit 46 does not need to correct the route.

[0099] Here, if the relationship between the curvature of the route and the deviation of the articulated vehicles is known in advance through simulation or experiment, such a relationship as shown in FIG. 2 is followed.

[0100] Furthermore, the route correction unit 46A may correct the route using a trained model that is generated in advance by machine learning the relationship between the shape of the route (including curvature) and the deviation of the articulated vehicles.

[0101] With this configuration, deviation is predicted (estimated) based on the coupling angle data and the shape of the route is corrected, making it possible to suppress deviation of the articulated vehicle while controlling the travel of the articulated vehicle so that it follows the route. In other words, deviation of the articulated vehicle can be adjusted simply by correcting the route.

[0102] <Third embodiment> Figure 14 is a diagram conceptually showing an example of the configuration of a vehicle control device related to this embodiment. As shown in the example in Figure 14, a vehicle control device 200B includes a route generation device 40B and an articulated vehicle 100. The route generation device 40B generates a route for the articulated vehicle 100 using towing position and attitude data input from the position and attitude sensor 50, map data acquired from a map database 52, and articulation angle data input from the articulation angle sensor 54.

[0103] The path generating device 40B includes a path generating unit 42, a path correcting unit 46B, a deviation predicting unit 48, and a determining unit 49 that determines whether or not path correction is required based on the predicted deviation.

[0104] Based on the deviation of the articulated vehicles predicted by the deviation prediction unit 48 (and further, the travel trajectory of the articulated vehicles), the determination unit 49 determines whether the maximum deviation of the towed vehicles is equal to or less than a predetermined threshold value. Here, since the deviation of the towed vehicles tends to increase the further back the vehicle is in the articulated vehicle series, the maximum deviation of the towed vehicles may be the deviation of the last towed vehicle in the articulated vehicle series. Alternatively, the above determination may be made by comparing the average deviation of multiple towed vehicles with a predetermined threshold value.

[0105] The route correction unit 46B references the determination result from the determination unit 49, and if the maximum deviation of the towed vehicle exceeds a predetermined threshold value, corrects the route generated by the route generation unit 42. Specifically, the route correction unit 46B corrects the route based on the relationship between the deviation of the articulated vehicles and the curvature of the route so that the predicted deviation of the articulated vehicles is equal to or less than the predetermined threshold value.

[0106] Here, the relationship between the curvature of the route and the deviation of the articulated vehicles may be determined in accordance with, for example, the relationship shown in FIG. 2 if it is known in advance through simulation or experiment using a kinematic model.

[0107] Furthermore, the route correction unit 46B may correct the route using a trained model that has been generated in advance by machine learning the relationship between the shape of the route (including curvature) and the deviation of the articulated vehicles.

[0108] Furthermore, the path correction unit 46B may correct the path so that the vehicle body deviation does not exceed a predetermined threshold. Here, the vehicle body deviation is the deviation between the end of the vehicle body of the towed vehicle 11 and the path. The larger the vehicle, the greater the distance between the center of gravity of the vehicle body and the end of the vehicle body, and therefore the greater the vehicle body deviation. By correcting the path based on the vehicle body deviation, the allowable deviation is limited to a smaller value than when only the deviation based on the center of gravity of the vehicle body is considered.

[0109] With this configuration, the shape of the route is corrected only when the deviation exceeds the threshold value, thereby making it possible to suppress deviation of the articulated vehicles and control the travel of the articulated vehicles so that they follow the route.

[0110] <Fourth embodiment> Figure 15 is a diagram conceptually showing an example of the configuration of a vehicle control device related to this embodiment. As shown in the example in Figure 15, a vehicle control device 200C includes a route generation device 40C and an articulated vehicle 100. The route generation device 40C generates a route for the articulated vehicle 100 using towing position and orientation data input from a position and orientation sensor 50, towed position and orientation data input from a position and orientation sensor 51 attached to the towed vehicle, and map data obtained from a map database 52.

[0111] The position and attitude sensor 51 estimates the position and attitude of the towed vehicle relative to the global coordinate system. Methods for the position and attitude sensor 51 to estimate the position and attitude of the towed vehicle include, for example, using GNSS or using known self-position estimation technology. The position and attitude sensor 51 does not need to be attached to all towed vehicles, and may be attached to some of the towed vehicles.

[0112] The path generating device 40C includes a path generating unit 42, a path correcting unit 46B, a deviation predicting unit 48, a determining unit 49, and a coupling angle estimating unit 47 that estimates the coupling angle based on the towing position and attitude data and the towed position and attitude data. Note that instead of including the determining unit 49 and the path correcting unit 46B, the path generating device 40C may be configured to include a path correcting unit 46A.

[0113] The coupling angle estimator 47 estimates the coupling angle from a kinematic model (including the above equations (1) and (2)) of the towing vehicle and the towed vehicle based on the towing position and attitude data and the towed position and attitude data. Methods for estimating the coupling angle include, for example, a method using an extended Kalman filter or a particle filter.

[0114] With this configuration, by estimating the coupling angle without using the coupling angle sensor 54 and correcting the shape of the route, it is possible to control the travel of the articulated vehicles so that they follow the route while suppressing deviation of the articulated vehicles.

[0115] <Fifth embodiment> Figure 16 is a diagram conceptually showing an example of the configuration of a vehicle control device related to this embodiment. As shown in the example in Figure 16, a vehicle control device 200D includes a route generation device 40D and an articulated vehicle 100. The route generation device 40D generates a route for the articulated vehicle 100 using towing position and orientation data input from the position and orientation sensor 50 and map data obtained from the map database 52.

[0116] Path generation device 40D includes a path generation unit 42, a path correction unit 46B, a deviation prediction unit 48, a determination unit 49, and a coupling angle estimation unit 47D that estimates a coupling angle based on towing position and attitude data and the path generated by path generation unit 42. Note that instead of including determination unit 49 and path correction unit 46B, a configuration may also be provided that includes path correction unit 46A.

[0117] The coupling angle estimator 47D estimates the coupling angle based on the towing position and attitude data and the route generated by the route generator 42. Specifically, when the route generated by the route generator 42 is a straight line, the coupling angle estimator 47D utilizes the fact that the attitude (angle) of the route and the reference coupling angle match after the settling time Ts has elapsed, and initializes the coupling angle at that location. Then, using the initialized coupling angle as a reference, the coupling angle estimator 47D estimates any coupling angle on the route based on a kinematic model of the articulated vehicles.

[0118] With this configuration, by estimating the coupling angle and correcting the shape of the route without using the position and orientation sensor 51, it is possible to control the travel of the articulated vehicles so that they follow the route while suppressing deviation of the articulated vehicles.

[0119] <Hardware configuration of vehicle control device> 17 and 18 are diagrams illustrating schematic examples of hardware configurations when the vehicle control devices shown in FIGS. 12, 13, 14, 15, and 16 are actually operated.

[0120] Note that the hardware configurations illustrated in Figures 17 and 18 may not match the numbers and other details of the configurations illustrated in Figures 12, 13, 14, 15, and 16, but this is because the configurations illustrated in Figures 12, 13, 14, 15, and 16 represent conceptual units.

[0121] Therefore, at least the following cases can be envisaged: a configuration illustrated in Figures 12, 13, 14, 15, and 16 is made up of multiple hardware configurations illustrated in Figures 17 and 18; a configuration illustrated in Figures 12, 13, 14, 15, and 16 corresponds to a part of the hardware configuration illustrated in Figures 17 and 18; and further, a case can be envisaged in which multiple configurations illustrated in Figures 12, 13, 14, 15, and 16 are provided in one hardware configuration illustrated in Figures 17 and 18.

[0122] 17 shows a processing circuit 1102A that performs calculations, a storage device 1103 that can store information, and a measuring device 1106A such as a sensor or analyzer that can measure physical quantities, as hardware configurations for realizing the position and orientation sensor 50, position and orientation sensor 51, map database 52, connecting angle sensor 54, path generation device 40, path generation device 40A, path generation device 40B, path generation device 40C, path generation device 40D, etc. in Figures 12, 13, 14, 15, and 16. This configuration is the same in all of the above embodiments.

[0123] 18 shows a processing circuit 1102B that performs calculations and a measuring device 1106B such as a sensor or analyzer that can measure physical quantities, as a hardware configuration for realizing the position and orientation sensor 50, position and orientation sensor 51, map database 52, connecting angle sensor 54, path generation device 40, path generation device 40A, path generation device 40B, path generation device 40C, path generation device 40D, etc. in Figures 12, 13, 14, 15, and 16. This configuration is the same in all of the above embodiments.

[0124] The map database 52 is realized by the storage device 1103 or another storage device (not shown here).

[0125] The storage device 1103 may be, for example, a memory (recording medium) including a volatile or non-volatile semiconductor memory such as a hard disk drive (i.e., HDD), random access memory (i.e., RAM), read only memory (i.e., ROM), flash memory, erasable programmable read only memory (EPROM), and electrically erasable programmable read-only memory (EEPROM), a magnetic disk, a flexible disk, an optical disk, a compact disk, a mini disk, or a DVD, or any recording medium that will be used in the future.

[0126] The processing circuit 1102A may execute a program stored in the storage device 1103, an external CD-ROM, an external DVD-ROM, an external flash memory, etc. That is, it may be, for example, a central processing unit (CPU), a microprocessor, a microcomputer, or a digital signal processor (DSP).

[0127] When the processing circuit 1102A executes a program stored in the storage device 1103, an external CD-ROM, an external DVD-ROM, an external flash memory, or the like, the path generation device 40, the path generation device 40A, the path generation device 40B, the path generation device 40C, and the path generation device 40D are realized by software, firmware, or a combination of software and firmware in which the program stored in the storage device 1103 is executed by the processing circuit 1102A. Note that the functions of the path generation device 40, the path generation device 40A, the path generation device 40B, the path generation device 40C, and the path generation device 40D may be realized, for example, by a plurality of processing circuits working together.

[0128] The software and firmware may be written as a program and stored in the storage device 1103. In this case, the processing circuit 1102A realizes the above functions by reading and executing the program stored in the storage device 1103. In other words, the storage device 1103 may store a program that, when executed by the processing circuit 1102A, results in the above functions being realized.

[0129] The processing circuit 1102B may also be dedicated hardware, i.e., for example, a single circuit, multiple circuits, a programmed processor, a parallel programmed processor, an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a combination thereof.

[0130] When the processing circuit 1102B is dedicated hardware, the path generation device 40, the path generation device 40A, the path generation device 40B, the path generation device 40C, and the path generation device 40D are realized by the operation of the processing circuit 1102B. Note that the functions of the path generation device 40, the path generation device 40A, the path generation device 40B, the path generation device 40C, and the path generation device 40D may be realized by separate circuits or by a single circuit.

[0131] In addition, the functions of the path generation device 40, the path generation device 40A, the path generation device 40B, the path generation device 40C, and the path generation device 40D may be partially realized in a processing circuit 1102A that executes a program stored in a memory device 1103, and partially realized in a processing circuit 1102B that is dedicated hardware.

[0132] Furthermore, the position and orientation sensor 50, the position and orientation sensor 51, and the coupling angle sensor 54 are realized by the measurement device 1106A or the measurement device 1106B.

[0133] <Effects Produced by the Multiple Embodiments Described Above> Next, examples of effects obtained by the above-described embodiments will be described. Note that in the following description, the effects will be described based on the specific configurations exemplified in the above-described embodiments, but these may be replaced with other specific configurations exemplified in the present specification as long as the same effects are obtained. In other words, for convenience, only one of the associated specific configurations may be described as a representative below, but the representatively described specific configuration may be replaced with another associated specific configuration.

[0134] Furthermore, the replacement may be made across multiple embodiments, i.e., configurations illustrated in different embodiments may be combined to produce the same effect.

[0135] According to the embodiment described above, the route generation device includes a route generation unit 42 and a correction unit. Here, the correction unit corresponds to, for example, route correction unit 46, route correction unit 46A, route correction unit 46B, etc. Articulated vehicle 100 includes a first vehicle and at least one second vehicle towed by the first vehicle. Here, the first vehicle corresponds, for example, towing vehicle 10, etc. The second vehicle corresponds, for example, towed vehicle 11, towed vehicle 12, towed vehicle 13, towed vehicle 14, etc. The route generation unit 42 generates a route for the articulated vehicles. Then, the route correction unit 46 corrects the route (for example, traveling route 1) based on the relationship between the deviation between the route of towed vehicle 11 when towing vehicle 10 follows the route and the shape of the route, and generates corrected route 2.

[0136] Furthermore, according to the embodiment described above, the path generation device includes a processing circuit 1102A that executes a program and a storage device 1103 that stores the program to be executed. The processing circuit 1102A executes the program to realize the following operations.

[0137] That is, the route (for example, travel route 1) is corrected based on the relationship between the deviation between the route and the towed vehicle 11 when the towing vehicle 10 is made to follow the route and the shape of the route, and a corrected route 2 is generated.

[0138] Furthermore, according to the embodiment described above, the path generation device includes the processing circuit 1102B, which is dedicated hardware. The processing circuit 1102B, which is dedicated hardware, performs the following operations.

[0139] That is, the processing circuit 1102B, which is dedicated hardware, corrects the route (for example, driving route 1) based on the relationship between the deviation between the route and the towed vehicle 11 when the towing vehicle 10 is made to follow the route and the shape of the route, to generate corrected route 2.

[0140] With this configuration, by correcting the shape of the route, it is possible to generate a corrected route that allows articulated vehicles to travel while suppressing deviation. As a result, it is possible to control the travel of the articulated vehicles so that they follow the corrected route. In other words, it is possible to adjust the deviation of the articulated vehicles simply by correcting the route.

[0141] Furthermore, even if other configurations shown as examples in this specification are appropriately added to the above configuration, that is, even if other configurations in this specification that were not mentioned as the above configuration are appropriately added, the same effect can be achieved.

[0142] Furthermore, according to the embodiment described above, the route correction unit 46 corrects the reference route obtained from the map data. With this configuration, by correcting the shape of the reference route obtained from the map data, it is possible to generate a corrected route that allows articulated vehicles to travel while suppressing deviation.

[0143] Furthermore, according to the embodiment described above, the route correction unit 46 corrects the travel route, which is the route traveled by the articulated vehicle 100, from among the routes obtained from map data. With this configuration, by correcting the shape of the travel route, it is possible to generate a corrected route that the articulated vehicle can travel while minimizing deviation.

[0144] Furthermore, according to the embodiment described above, the route correction unit 46 corrects the route curvature based on the relationship between deviation and route curvature. With this configuration, by correcting the route curvature, it is possible to generate a corrected route on which articulated vehicles can travel while suppressing deviation. In other words, it is possible to adjust the deviation of articulated vehicles simply by correcting the route curvature.

[0145] Furthermore, according to the embodiment described above, the route correction unit 46B corrects the route when the deviation exceeds a predetermined first threshold value. With this configuration, by correcting the shape of the route only when the deviation exceeds the threshold value, it is possible to generate a corrected route that allows articulated vehicles to travel while suppressing deviation.

[0146] Furthermore, according to the embodiment described above, the route correction unit 46 corrects the route based on the relationship between the maximum deviation of each towed vehicle 11 when the towing vehicle 10 is caused to follow the route and the shape of the route. With this configuration, by correcting the route based on the maximum deviation from the route, it is possible to suppress deviation from the corrected route within a desired range without having to consider the deviations of all towed vehicles.

[0147] Furthermore, according to the embodiment described above, the route correction unit 46 corrects the route based on the relationship between the deviation of the last towed vehicle 11 among the deviations of each towed vehicle 11 when the towing vehicle 10 is made to follow the route and the shape of the route. With this configuration, by correcting the route based on the deviation of the last towed vehicle, which tends to have a larger deviation from the route, it is possible to suppress deviation from the corrected route with high accuracy even when correcting the route based on the deviations of some of the towed vehicles.

[0148] Furthermore, according to the embodiment described above, the route correction unit 46 corrects the route using a trained model that has been generated in advance through machine learning of the relationship between deviation and route shape. With this configuration, the route can also be corrected within a range that is predicted from the known relationship between the route shape and the deviation of the articulated vehicle, using a trained model that has been generated in advance through machine learning of the relationship between the route shape (including curvature) and the deviation of the articulated vehicle.

[0149] Furthermore, according to the embodiment described above, the deviation is estimated using the position and attitude of the towed vehicle 11 when it follows the route, which are calculated based on a kinematic model. With this configuration, the position and attitude of the towed vehicle can be estimated by simulation based on the kinematic model.

[0150] Furthermore, according to the embodiment described above, the deviation is estimated using the position and attitude of the towed vehicle 11 when it is made to follow the route, which is calculated based on the coupling angles between the multiple vehicles in the articulated vehicle 100 and a kinematic model. With this configuration, by predicting (estimating) the deviation based on the coupling angle data and correcting the shape of the route, it is possible to generate a corrected route on which the articulated vehicle can travel while suppressing the deviation.

[0151] Furthermore, according to the embodiment described above, the coupling angle is estimated based on the position and attitude of the towing vehicle 10 and the position and attitude of the towed vehicle 11. With this configuration, by estimating the coupling angle without using the coupling angle sensor 54 and correcting the shape of the route, it is possible to generate a corrected route on which the articulated vehicles can travel while minimizing deviation.

[0152] Furthermore, according to the embodiment described above, the coupling angle is estimated based on the route and the position and attitude of the towing vehicle 10. With this configuration, by estimating the coupling angle and correcting the shape of the route without using the position and attitude sensor 51, it is possible to generate a corrected route along which the articulated vehicles can travel while minimizing deviation.

[0153] Furthermore, according to the embodiment described above, the deviation between the end of the body of the towed vehicle 11 and the route is referred to as the body deviation (the larger the total body length, the greater the deviation is likely to be, as the distance between the center of gravity and the end of the body is greater. This can be the deviation from the center of the route, the amount of overhang, whether front-to-back or side-to-side).

[0154] The route correction unit 46B corrects the route so that the vehicle body deviation does not exceed a predetermined second threshold value (limiting the deviation to be smaller than the first threshold value). With this configuration, deviations at the ends of the vehicle bodies are taken into consideration, and the shape of the route is corrected only when the deviation exceeds the threshold value, making it possible to generate a corrected route that allows articulated vehicles to travel while suppressing deviation.

[0155] <Modifications of the above-described embodiments> In the multiple embodiments described above, the dimensions, shapes, relative positional relationships, and implementation conditions of each component may also be described, but these are merely examples in all aspects and are not limiting.

[0156] Therefore, countless modifications and equivalents not shown as examples are contemplated within the scope of the technology disclosed in the present specification, including, for example, modifying, adding, or omitting at least one component, and further, extracting at least one component in at least one embodiment and combining it with a component in another embodiment.

[0157] Furthermore, unless a contradiction arises, when it is stated in the above-described embodiments that "one" component is provided, "one or more" of that component may also be provided.

[0158] Furthermore, the descriptions in this specification are incorporated by reference for all purposes related to the present technology, and none of them are admitted to be prior art.

[0159] Furthermore, each component described in the above-described embodiments is envisioned as software or firmware, as well as corresponding hardware, and as software it is referred to as, for example, a "unit," and as hardware it is referred to as, for example, a "processing circuit" (circuitry). [Explanation of symbols]

[0160] 1 Travel path, 2 Corrected path, 3 Path, 10 Towing vehicle, 11 Towed vehicle, 11A Dolly, 12 Towed vehicle, 12A Rear axle wheel, 13 Towed vehicle, 13A Dolly, 14 Towed vehicle, 14A Rear axle wheel, 20 Hitch point, 30 Towing vehicle, 31 Loading platform, 32 Loading platform, 40 Path generation device, 40A Path generation device, 40B Path generation device, 40C Path generation device, 40D Path generation device, 42 Path generation unit, 44 Curvature calculation unit, 46 Path correction unit, 46A Path correction unit, 46B Path correction unit, 47 Coupling angle estimation unit, 47D Coupling angle estimation unit, 48 Deviation prediction unit, 49 Determination unit, 50 Position and orientation sensor, 51 Position and orientation sensor, 52 Map database, 54 Coupling angle sensor, 100 Articulated vehicles, 102 towing vehicle control unit, 104 actuator, 200 vehicle control device, 200A vehicle control device, 200B vehicle control device, 200C vehicle control device, 200D vehicle control device, 2000 route generation device, 2002 correction unit, 2004 route generation unit.

Claims

1. A route generation device for generating a route for a combination vehicle in which a plurality of vehicles are combined, the combination vehicle comprises a first vehicle and at least one second vehicle towed by the first vehicle; The path generation device a route generation unit for generating a route for the articulated vehicles; a correction unit that corrects the route to generate a corrected route based on a relationship between a deviation between the route and the second vehicle when the first vehicle is caused to follow the route and a shape of the route, Route generation device.

2. The path generation device according to claim 1, the correction unit corrects the route acquired from map data; Route generation device.

3. The route generation device according to claim 2, the correction unit corrects a travel route, which is the route on which the articulated vehicles travel, from among the routes acquired from the map data. Route generation device.

4. 4. A path generation device according to claim 1, the correction unit corrects the curvature of the path based on a relationship between the deviation and the curvature of the path. Route generation device.

5. 4. A path generation device according to claim 1, the correction unit corrects the path when the deviation exceeds a predetermined first threshold value; Route generation device.

6. 4. A path generation device according to claim 1, a plurality of the second vehicles; the correction unit corrects the route based on a relationship between a maximum value of each of the deviations when each of the first vehicles is caused to follow the route and a shape of the route. Route generation device.

7. 4. A path generation device according to claim 1, a plurality of the second vehicles; the correction unit corrects the route based on a relationship between the deviation of the second vehicle at the rear of the route among the deviations when the first vehicles are caused to follow the route and a shape of the route. Route generation device.

8. 4. A path generation device according to claim 1, The correction unit corrects the route using a trained model generated in advance by machine learning a relationship between the deviation and the shape of the route. Route generation device.

9. 4. A path generation device according to claim 1, The deviation is estimated using a position and an attitude of the second vehicle when it follows the path, the position and the attitude being calculated based on a kinematic model. Route generation device.

10. 4. A path generation device according to claim 1, the deviation is estimated using a position and attitude of the second vehicle when it is caused to follow the route, the position and attitude being calculated based on a kinematic model and a coupling angle between the plurality of vehicles in the coupled vehicle; Route generation device.

11. The path generation device according to claim 10, The coupling angle is estimated based on the position and attitude of the first vehicle and the position and attitude of the second vehicle. Route generation device.

12. The path generation device according to claim 10, The coupling angle is estimated based on the position and attitude of the first vehicle and the path. Route generation device.

13. 4. A path generation device according to claim 1, a deviation between the end of the body of the second vehicle and the route as a body deviation; the correction unit corrects the path so that the vehicle body deviation does not exceed a predetermined second threshold value. Route generation device.

Images