System and method for following a nearest-in-path vehicle using the movement flow of surrounding vehicles

Abstract

System for following a closest-to-path vehicle (CIPV, 30) using the movement flow of surrounding vehicles, comprising: a sensor device (210) of a host vehicle (20) that generates data relating to a plurality of vehicles on a drivable area in front of the host vehicle (20); a navigation control (220) which contains a computerized processor capable of being operated to: monitor the data from the sensor device (210); define a part of the majority of vehicles as a vehicle swarm (70); identify one of the several vehicles as the CIPV (30) to be followed; evaluate the data to determine whether the CIPV (30) to be followed exhibits good behavior with respect to the vehicle swarm (70); and If the CIPV (30) to be followed shows good behavior, generate a breadcrumb navigation path based on the data; and a vehicle control system that controls the host vehicle (20) based on the breadcrumb navigation path; wherein the computerized processor can further be operated in such a way as to warn a driver of the host vehicle (20) if the CIPV (30) to be followed does not exhibit good behavior.

Description

[0001] The description generally refers to a system and a method for following a nearest-to-path vehicle using the movement flow of surrounding vehicles for an autonomous or semi-autonomous vehicle.

[0002] Navigation systems and procedures for autonomous and semi-autonomous vehicles use computer algorithms to determine a navigation path for the vehicle being controlled. Digital maps and sensor inputs are useful for establishing the vehicle's navigation path. Sensor inputs can include image recognition of lane markings and road features. Sensor inputs can also include image, radar, light detection and rangefinder (LiDAR), or other similar sensor detection methods to monitor the positions of other vehicles relative to the controlled vehicle, for example, to prevent the controlled vehicle from getting too close to another vehicle in traffic.

[0003] German patent DE 10 2016 113 286 A1 describes a method and a system for operating an adaptive cruise control system. The method involves receiving data measured by a multitude of sensors, the measured data relating to one or more target vehicles within the carrier vehicle's field of vision. The method further involves generating a follow-up value for each target vehicle based on the measured data and controlling the carrier vehicle's response based on this follow-up value.

[0004] German patent DE 10 2012 222 301 A1 describes a method and a system that monitor the behavior of vehicles in the vicinity to predict and react to an impending hazard on the road, even in situations where the hazard has not been directly detected. The method monitors an area around the host vehicle and searches for the presence of one or more target vehicles. When target vehicles are detected, the method evaluates their behavior, classifies it into one of several categories, and, assuming that their behavior indicates a type of impending hazard, develops a suitable preventive response to control the host vehicle. The preventive response can include mimicking, copying, and / or integrating the behavior of the target vehicles in the vicinity using so-called "swarm" techniques to avoid the otherwise undetected hazard.

[0005] It can be considered a task to specify an improved system and procedure for following a nearest-in-path vehicle using the movement flow of surrounding vehicles in order to increase the safety of an autonomous or semi-autonomous vehicle.

[0006] A system according to the invention is described for following a closest-in-path vehicle (CIPV) using the movement flow of surrounding vehicles. The system comprises a sensor device on a host vehicle that generates data relating to a plurality of vehicles on a drivable surface in front of the host vehicle. The system further comprises a navigation controller that includes a computerized processor which can be operated to monitor the data from the sensor device, define a portion of the plurality of vehicles as a swarm, identify one of the plurality of vehicles as a CIPV to be followed, evaluate the data to determine whether the CIPV to be followed is behaving well in relation to the swarm, and, if the CIPV to be followed is behaving well, generate a breadcrumb navigation path based on the data.The system also includes a vehicle control unit that steers the host vehicle based on the breadcrumb navigation path. The computer processor can also be configured to warn the driver of the host vehicle if the CIPV being followed is not behaving correctly.

[0007] In some embodiments, the evaluation of the data includes comparing a course of the CIPV to be followed with a course of the swarm of vehicles to determine a course error of the CIPV to be followed, comparing a turning radius of the CIPV to be followed with a turning radius of the swarm of vehicles to determine a turning radius error of the CIPV to be followed, and determining that the CIPV to be followed is exhibiting good behavior based on the course error and the turning radius error.

[0008] In some embodiments, the system further comprises the computer processor, which is also capable of determining the speed of the CIPV to be followed, the average speed of the vehicle swarm, and the relative position of the CIPV to be followed with respect to the vehicle swarm. The system further comprises evaluating the data to determine whether the CIPV to be followed exhibits good behavior with respect to the vehicle swarm when the speed difference between the speed of the CIPV to be followed and the average speed of the vehicle swarm is less than a threshold speed difference, and when the relative position of the CIPV to be followed is closer to the vehicle swarm than a threshold distance.

[0009] In some embodiments, generating the breadcrumb navigation path based on the data involves weighting the CIPV as a high-quality candidate to follow, based on its good behavior.

[0010] In some embodiments, the sensor device includes a camera device, a radar device, a LiDAR device, or an ultrasonic device.

[0011] In some embodiments, the vehicle control system also controls a distance to the CIPV to be followed, based on the fact that the CIPV to be followed is exhibiting good behavior.

[0012] In some embodiments, the vehicle control system also controls autonomous braking based on the following CIPV, which demonstrates good behavior.

[0013] In some embodiments, defining part of the plurality of vehicles as the swarm of vehicles includes determining a speed of a first vehicle of the plurality of vehicles, determining a speed of a second vehicle of the plurality of vehicles, determining a relative position of the first vehicle to the second vehicle, and defining the first vehicle and the second vehicle as the swarm of vehicles if a speed difference between the speed of the first vehicle and the speed of the second vehicle is less than a threshold speed difference and if the relative position of the first vehicle to the second vehicle is closer than a threshold distance.

[0014] In some embodiments, defining part of the plurality of vehicles as a swarm further includes determining the speed of a third vehicle in the plurality, determining the average speed of the swarm, and determining the relative position of the third vehicle to the swarm. Defining part of the plurality of vehicles as the swarm further includes defining the swarm to include the third vehicle if the speed difference between the speed of the third vehicle and the average speed of the swarm is less than the threshold speed difference and if the relative position of the third vehicle to the swarm is closer than the threshold distance.

[0015] A method according to the invention for following a CIPV (Computer-Integrated Vehicle) using the movement of surrounding vehicles is described. The method comprises, in a computer processor of a host vehicle, monitoring data from a sensor device that collects data relating to a plurality of vehicles on a drivable surface in front of the host vehicle, defining a portion of the plurality of vehicles as a swarm, identifying one of the plurality of vehicles as a CIPV to be followed, and evaluating the data to determine whether the CIPV to be followed exhibits good behavior relative to the swarm. The method further comprises, if the CIPV to be followed exhibits good behavior, generating a breadcrumb navigation path based on the data and controlling the host vehicle based on the breadcrumb navigation path.Furthermore, the procedure includes informing the driver of the host vehicle if the CIPV being followed does not exhibit good behavior.

[0016] In some embodiments, the evaluation of the data includes comparing a course of the CIPV to be followed with a course of the swarm of vehicles to determine a course error of the CIPV to be followed, comparing a turning radius of the CIPV to be followed with a turning radius of the swarm of vehicles to determine a turning radius error of the CIPV to be followed, and determining that the CIPV to be followed is behaving well, based on the course error and the turning radius error.

[0017] In some embodiments, the method further comprises, within the computer-based processor, determining the speed of the CIPV to be followed, determining the average speed of the vehicle swarm, and determining the relative position of the CIPV to be followed to the vehicle swarm. The method further comprises evaluating the data to determine whether the CIPV to be followed exhibits good behavior with respect to the vehicle swarm when the speed difference between the speed of the CIPV to be followed and the average speed of the vehicle swarm is less than a threshold speed difference, and when the relative position of the CIPV to be followed to the vehicle swarm is closer than a threshold distance. Fig. 1 shows terms that may be useful in defining a procedure for quantifying CIPV behavior; Fig. Figure 2 schematically shows an exemplary control architecture that is useful for the operation of the process and the system; Fig. Figure 3 schematically shows an exemplary data communication system within a vehicle to be controlled; Fig. Figure 4 shows an exemplary vehicle controlled by the procedure and system, including devices and modules that are useful for certifying a CIPV destination as high-quality; Fig. Figure 5 schematically shows an example of a computerized navigation control system; Fig. Figure 6 graphically illustrates exemplary position data collected over a period of time with respect to a vehicle swarm, including a CIPV target; and Fig. Figure 7 is a flowchart illustrating an exemplary procedure 600 for evaluating a CIPV target and determining whether the CIPV target exhibits good CIPV behavior or bad CIPV behavior.

[0018] A method and system for following a CIPV for an autonomous or semi-autonomous host vehicle is described, comprising a real-time determination of whether a nearest vehicle in a current path for the controlled vehicle is exhibiting good behavior to be followed or bad behavior indicating that the host vehicle should not follow the CIPV.

[0019] Breadcrumb navigation, by following the nearest vehicle in the path or the Closest In Path Vehicle (CIPV), can be used to address the intermittent quality of lane markings in lane-following control. Breadcrumb navigation refers to using the positions of other vehicles in the path of the vehicle being controlled to establish a path for the controlled vehicle. Breadcrumb navigation strategies may not distinguish between good and poor CIPV behavior. A real-time process and system are provided that analyzes and determines the quality of CIPV behavior based on the behavior of other vehicles near the CIPV. A close grouping of vehicles can be described as a swarm. Individual vehicles may drive poorly or exhibit adverse behavior.A swarm of vehicles comprising multiple drivers and exhibiting consistent behavior relative to one another is more likely to represent acceptable driving behavior. A swarm of vehicles traveling at uniform speeds on a roadway, all moving uniformly within their own lanes, can be useful for establishing a standard for good vehicle behavior. By comparing the behavior of a CIPV (Combined In-Person Vehicle) to the behavior of a swarm of vehicles, or to a swarm of vehicles to which the CIPV belongs, the CIPV's behavior can be analyzed and classified.

[0020] By examining the behavior of the CIPV driver and selectively using the CIPV's position and trajectory data for breadcrumb path planning, the described system can increase feature availability and safety. The collected breadcrumb data, certified as high-quality, can be used individually or to enhance and streamline camera inputs for lane following. The described system can provide improved camera / lane interpretation, visibility, and quality without requiring new hardware. In one embodiment, the method and system compare CIPV states, including but not limited to course error and curve radius error, with swarm-related data to certify and selectively use high-quality CIPV data.The course error describes the discrepancy between the actual course of the CIPV and a target course based on the behavior of the vehicle swarm. Curve radius error describes the discrepancy between a curvature navigated by the CIPV and a nominal or desired curvature based on the behavior of the vehicle swarm. By measuring or estimating the course error and curve radius error of the CIPV relative to the vehicle swarm, the behavior of the CIPV as a candidate to be followed can be evaluated. As described here, the behavior of a CIPV can be classified as good or poor relative to the vehicle swarm. Instead of good or poor, other descriptors can be used, such as terms like swarm-conforming behavior, non-swarm-conforming behavior, threshold-stable behavior, and unstable behavior of the vehicle swarm.

[0021] An exemplary algorithm for determining or quantifying the behavior of a CIPV as a successor candidate is given as Equation 1. f(Xc)=∫t−Δtt(α1|eψ|+α2|eρ|)dt+α3∫ω=0Hz5HzFFT(〈ev〉t,〈eψ〉t,〈eρ〉t)2dω

[0022] Equations 2 and 3 describe terms in equation 1. eψ=ψcipv−ψswarm eρ=ρcipv−(ρswarm)

[0023] eψ describes a course error for the CIPV. ep describes a curve radius error for the CIPV. The terms α1, α2 and α3 Equations 1 and 5 describe weighting factors for quantification. The term Δt describes the length of the moving time window. The FFT operation describes a Fast Fourier Transform algorithm applied in Equation 1. The term ω describes a frequency of the low-energy band. Equations 4 and 5 describe further terms of Equation 1 that modify the vector over the window of the last Δt² seconds since t.jetzt . 〈eψ〉tnow={eψ(t):∀t ∈[tnow−Δt2,now]} 〈eρ〉tnow={eρ(t):∀t ∈[tnow−Δt2,now]} Equation 1 is an example algorithm for evaluating whether a target CIPV exhibits good or bad CIPV behavior. A number of alternative algorithms are conceivable, and disclosure is not limited to the examples listed here.

[0024] Fig. Equation 1 shows terms that may be useful in defining a procedure for quantifying CIPV 30 behavior. Some of the terms in Equation 1 are explained in Fig. Figure 1 describes the host vehicle 20 to be controlled, which is depicted on a road surface 10. The CIPV 30, or the CIPV target, is also depicted on the road surface 10. Additionally, vehicle 50 and vehicle 60 are depicted on the road surface 10. The CIPV 30, vehicle 50, and vehicle 60 are located close to each other and are traveling at a relatively similar speed, so a vehicle swarm 70 consisting of the CIPV 30, vehicle 50, and vehicle 60 can be defined.

[0025] Several terms can be defined to describe the CIPV 30 and its movement relative to the road surface 10 and the vehicle swarm 70. Term 32 describes eψ, or a course error, for the CIPV 30. Term 34 describes ep, or a turning radius error, for the CIPV 30. Term 52 describes a course error for vehicle 50. Term 54 describes a turning radius error for vehicle 50. Term 62 describes a course error for vehicle 60.

[0026] Term 64 describes a curve radius error for vehicle 60. Term 72 describes an average course error for the swarm of vehicles 70. Term 74 describes an average curve radius error for the swarm of vehicles 70.

[0027] Controlling the host vehicle based on a breadcrumb navigation path can encompass a number of alternative embodiments. In one exemplary embodiment, the host vehicle can include devices for determining a lane geometry on the drivable surface. The vehicle can include a controller to merge the lane geometry with the breadcrumb navigation path to create a merged navigation path. The trajectory of the host vehicle can then be controlled based on the merged navigation path.

[0028] Fig. Figure 2 schematically shows an exemplary control architecture useful for the operation of the procedure and the system. The control architecture 100 is represented by a camera device 110, a digital map database 120, a data fusion module 130, a mission planning module 140, a longitudinal controller 150, a lateral controller 160, and an electronic power steering / acceleration / braking module 170. The camera device 110 captures a series of images relating to the environment and path of the vehicle to be controlled, including, but not limited to, images of the road surface, images of lane markings, images of potential obstacles near the vehicle, images of vehicles in the vicinity of the vehicle to be controlled, and other images containing relevant information for controlling a vehicle.The digital map database 120 contains data relating to an area around the vehicle being controlled, including historically documented road geometry, synthesized data such as vehicle-to-vehicle or infrastructure-to-vehicle data relating to road geometry, and other information that can be monitored and stored over a specific area in which the vehicle can travel. The data fusion module 130 comprises the CIPV module 132, the CIPV behavior analysis module 134, and the breadcrumb navigation module 136. The CIPV module 132 collects information about a CIPV and a vehicle swarm and generates data from this information, including sample values ​​of the CIPV's trajectory within a lane and relative to the vehicle swarm. The CIPV behavior analysis module 134 receives the generated data from the CIPV module 132 and analyzes the data to determine whether the CIPV is exhibiting good or bad CIPV behavior.If the CIPV behavior analysis module 134 determines that the CIPV is exhibiting good CIPV behavior, the breadcrumb navigation module 136 uses the data from the CIPV module 132 to generate a breadcrumb navigation graph that allows the controlled vehicle to partially or completely base navigation movements on or follow the movement of the CIPV.

[0029] The mission planning module 140 uses the breadcrumb navigation graphic from the breadcrumb navigation module 136 and other available information to generate a commanded navigation graphic. The longitudinal controller 150 and the lateral controller 160 use the commanded navigation plan to determine the desired vehicle speed and trajectory. The electronic power steering / acceleration / braking module 170 uses the outputs of the longitudinal controller 150 and the lateral controller 160 to control the navigation of the host vehicle 20. The control architecture 100 is provided as an exemplary embodiment of a control architecture that can be used to implement the method and the system. Other embodiments are conceivable, and the description is not limited to the examples presented here.

[0030] Fig. Figure 3 schematically shows an exemplary data communication system within a vehicle to be controlled. The data communication system 200 is depicted with a camera device 110, a digital map database 120, a sensor device 210, a navigation controller 220, and a vehicle controller 230, each of which is communicatively connected to the vehicle data bus 240. The sensor device 210 can include one or more radar devices, LiDAR devices, ultrasonic devices, or other similar devices useful for collecting data about a vehicle's surroundings and the behavior of other vehicles on a roadway. The vehicle data bus 240 comprises a communication network capable of rapidly transferring data back and forth between various connected devices and modules.Data can be collected from any of the camera devices 110, the digital map database 120, and the sensor device 210 and transmitted to the navigation control unit 220. The navigation control unit 220 comprises a computer processor and programmed code that can generate a commanded navigation display useful for navigating the controlled vehicle over a road surface around the vehicle.

[0031] Fig. Figure 4 shows an exemplary vehicle controlled by the method and system, including devices and modules useful for certifying a CIPV target as high-quality. The vehicle 300 to be controlled is shown on a road surface 310 with lane markings 320. The vehicle 300 is shown with a navigation controller 220, a vehicle controller 230, a camera device 110, and a sensor device 210. The camera device 110 covers the field of view 112 and is positioned to capture images of the road surface 310 and other objects and obstacles near the controlled vehicle 300, including a nearby vehicle that may be a CIPV. The sensor device 210 can additionally provide data about objects near the controlled vehicle 300.The navigation controller 220 receives data from the camera device 110 and other sources and generates a commanded navigation display according to the described method. The vehicle controller 230 uses the commanded navigation display to control the navigation of the controlled vehicle 300 on the road surface 310. The controlled vehicle 300 is an example of a vehicle that uses the described method and system. Other embodiments are conceivable, and the description is not limited to the examples presented here.

[0032] Within the described system, various controllers can be used to operate the described process. Controllers can comprise a computerized device containing a computerized processor with memory capable of storing programmed executable code. A controller can operate on a single computerized device or extend across multiple computerized devices. Fig. Figure 5 schematically shows an exemplary computerized navigation controller. The navigation controller 220 comprises a computer-based processor device 410, a communication module 430, a data input / output module 420, and a storage device 440. It should be noted that the navigation controller 220 may contain additional components, and some of the components are not present in some embodiments.

[0033] The processor unit 410 can include memory, such as read-only memory (ROM) and random-access memory (RAM), in which processor-executable instructions are stored, as well as one or more processors that execute the processor-executable instructions. In embodiments in which the processor device 410 includes two or more processors, the processors can operate in parallel or in a distributed manner. The processor device 410 can execute the operating system of the navigation controller 220. The processor device 410 can comprise one or more modules that execute programmed code or computer-aided processes or methods with executable steps. The modules shown can comprise a single physical device or functionality that extends over several physical devices.In the embodiment shown, the processor device 410 also includes the data fusion module 130, the mission planning module 140 and the track data synthesis module 412, which are described in more detail below.

[0034] The 420 data input / output module is a device that can receive data from sensors and devices throughout the vehicle and process it into formats that can be used by the 410 processor unit. The 420 data input / output module can also process the output from the 410 processor unit and enable this output to be used by other devices or controllers in the vehicle.

[0035] The communication module 430 can include a communication / data link with a bus device configured to transmit data to various components of the system, and can include one or more wireless transceivers to perform wireless communication.

[0036] The storage device 440 is a device that stores data generated or received by the navigation controller 220. The storage device 440 may include, but is not limited to, a hard disk drive, an optical drive, and / or a flash memory drive.

[0037] The data fusion module 130 is used in relation to Fig. 2 described and may include programming that is able to monitor data regarding a CIPV target, evaluate whether the CIPV target is exhibiting good CIPV behavior based on the data regarding the CIPV target and a vehicle swarm, and selectively generate a breadcrumb navigation plan.

[0038] Mission Planning Module 140 is used in relation to Fig. 2 described and may include programming that generates a commanded navigation display based on the generated breadcrumb navigation display and other navigation information, such as track data generated by the track data synthesis module 412.

[0039] The Lane Data Synthesis Module 412 monitors information about a current lane from various sources, including data from a camera device, a sensor device, and a digital mapping device. The Lane Data Synthesis Module 412 projects or estimates the dimensions and boundaries of a current lane from available sources. Map errors may be present in the map database or in data relating to a current location. The Lane Data Synthesis Module 412 may include algorithms useful for locating information, merging different information sources, and reducing map errors. This measurement data is provided to other modules as lane data.

[0040] The navigation controller 220 is an exemplary computer-based device capable of executing programmed code to evaluate data from a CIPV target and selectively use it to generate a breadcrumb navigation plan. A number of different embodiments of the navigation controller 220, the devices connected to it, and the modules operable therein are conceivable, and disclosure is not intended to be limited to the examples listed here.

[0041] Fig. Figure 6 shows a graphical representation of exemplary position data collected over a period of time with respect to a vehicle swarm including a CIPV target. A graph 500 is shown. A vertical axis 510 is shown, representing the lateral distance from each data point to a centerline of the host vehicle. A horizontal axis 520 is shown, representing the longitudinal distance from each data point to the host vehicle. With respect to a CIPV target, a first data point 530, recorded at the earliest time, a second data point 531, recorded later than the earliest time, and a third data point 532, recorded later than the second data point 531, are shown. The time span of the data extends from the earliest time of recording of the first data point 530 to the time of recording of the third data point 532.With respect to a second vehicle in the swarm, the first data point 550, recorded at the earliest time, a second data point 551, recorded at the same time as the second data point 531, and a third data point 552, recorded at the same time as the third data point 532, are shown. With respect to a third vehicle in the swarm, the first data point 560, recorded at the earliest time, a second data point 561, recorded at the same time as the second data point 531, and a third data point 562, recorded at the same time as the third data point 532, are shown. By analyzing the various data points, details about the position and movement of the different vehicles can be analyzed and evaluated.

[0042] Fig.Figure 7 is a flowchart illustrating an exemplary Procedure 600 for evaluating a CIPV target and determining whether the CIPV target exhibits good or bad CIPV behavior. The Procedure 600 begins in step 602. In step 604, a CIPV target is identified. In step 606, a vehicle swarm near the CIPV target is identified, which may contain the CIPV target. Proximity to the CIPV target can be defined by a distance threshold, such as within 10 to 20 meters of the CIPV target. In step 608, the speeds of the CIPV target and the other vehicles in the swarm are determined. In step 610, the relative position of the CIPV target to each of the other vehicles in the swarm is determined.In step 612, the speed of the CIPV target, the speeds of the other vehicles in the swarm, and the relative position of the CIPV target to the other vehicles in the swarm are analyzed. This analysis determines whether the CIPV target can be considered part of the swarm. If the CIPV target can be considered part of the swarm, process 600 continues with step 614. If the CIPV target cannot be considered part of the swarm, process 600 continues with step 618.

[0043] In step 614, if the CIPV destination can be considered part of the vehicle swarm, the CIPV can be weighted as a high-quality candidate for breadcrumb navigation. In step 616, the data regarding the CIPV destination can be forwarded to breadcrumb navigation module 136. Process 600 then proceeds to step 622, where the process ends.

[0044] In step 618, if the CIPV target cannot be considered part of the vehicle swarm, the CIPV can be weighted as a low-quality candidate for breadcrumb navigation. In step 620, the driver can be informed that the CIPV target is unreliable. In an optional embodiment, the driver can be given the option to select a new CIPV target or to take manual control of the host vehicle. Process 600 then proceeds to step 622, where the process ends.

[0045] Process 600 is provided as an exemplary process for evaluating and selectively using data from a CIPV for breadcrumb navigation. A number of similar processes are conceivable, and disclosure is not intended to be limited to the examples listed here.

[0046] Several methods can be used to identify a vehicle swarm. In step 612, the speed of the CIPV target, the speeds of the other vehicles in the swarm, and the relative position of the CIPV target to the other vehicles in the swarm are analyzed. This analysis determines whether the CIPV target can be considered part of the vehicle swarm. Similarly, a plurality of vehicles ahead of the host vehicle can be analyzed, and the speeds and relative positions of some of these vehicles can be analyzed.To identify a portion of a group of vehicles as a swarm, the navigation control system can determine that the speeds of a first vehicle and a second vehicle are within a threshold speed difference and that the relative position of the first vehicle to the second vehicle is within a threshold distance. It can then identify the first and second vehicles as a swarm. Similar determinations can be made between the swarm comprising the first and second vehicles and a third vehicle to determine whether the third vehicle should be included in the swarm. Swarms with a larger number of vehicles may be identified as more reliable or given more weight compared to smaller swarms of two or three vehicles.

[0047] The navigation diagrams described here can be useful for controlling the navigation of a fully autonomous vehicle. Likewise, the navigation plots described here can be useful for controlling the navigation of a semi-autonomous vehicle, for example, to enable automatic braking, lane keeping, or obstacle avoidance. Similarly, the navigation plots described here can be useful for providing navigation aids such as projected graphics or generated sounds to assist a driver in efficiently controlling a vehicle. Examples of how generated navigation plots can be used are given here. Other embodiments are conceivable, and the description is not limited to the examples listed here.

[0048] A breadcrumb navigation path, once generated by the described method and system, can be useful for creating or influencing a merged navigation path that is beneficial for guiding or autonomously driving the vehicle. Such a breadcrumb navigation path, or more specifically, the detection of poor CIPV behavior, can be used to further modulate other factors, such as the distance maintained by the CIPV. For example, if a CIPV receives good marks for good behavior, a normal following distance can be implemented. If the same CIPV begins to exhibit poor behavior, such as due to driver distraction, this poor behavior can be used to instruct the host vehicle to increase the distance to the CIPV, as confidence in the driver decreases.In another exemplary embodiment, the detection of poor behavior by the CIPV can be used to initiate automatic braking or deceleration of the vehicle. In another embodiment, the driver of the host vehicle can be additionally or alternatively warned, for example, by visual graphics or an audio warning, when the CIPV exhibits poor behavior.

[0049] The described method and system improve feature availability for autonomous and semi-autonomous vehicles. Under conditions where some navigation processes lack sufficient data and guidance to effectively navigate the vehicle, such as in a construction zone with missing, conflicting, or displaced lane markings, the described method and system can be used to validate and successfully utilize a path taken by a CIPV ahead of the host vehicle to navigate the vehicle through the exemplary construction zone.

Claims

[1] System for following a closest-in-path vehicle (CIPV, 30) using the movement flow of surrounding vehicles, comprising: a sensor device (210) of a host vehicle (20) that generates data relating to a plurality of vehicles on a drivable area in front of the host vehicle (20); a navigation control (220) which contains a computerized processor capable of being operated to: monitor the data from the sensor device (210); define a part of the majority of vehicles as a vehicle swarm (70); identify one of the several vehicles as the CIPV (30) to be followed; evaluate the data to determine whether the CIPV (30) to be followed exhibits good behavior with respect to the vehicle swarm (70); and If the CIPV (30) to be followed shows good behavior, generate a breadcrumb navigation path based on the data; and a vehicle control system that controls the host vehicle (20) based on the breadcrumb navigation path; wherein the computerized processor can further be operated in such a way as to warn a driver of the host vehicle (20) if the CIPV (30) to be followed does not exhibit good behavior. [2] System according to claim 1, wherein the evaluation of the data comprises: Comparing a course of the following CIPV (30) with a course of the swarm of vehicles (70) to determine a course error of the following CIPV (30); Comparing a curve radius of the following CIPV (30) with a curve radius of the vehicle swarm (70) to determine a curve radius error of the following CIPV (30); and Determining the CIPV (30) that shows good behavior, based on the course error and the curve radius error. [3] System according to claim 1, wherein the computerized processor is further capable of being operated to: to determine a speed of the following CIPV (30); to determine an average speed of the swarm of vehicles (70); to determine a relative position of the following CIPV (30) to the vehicle swarm (70); and evaluate the data to determine whether the CIPV (30) to be followed exhibits good behavior with respect to the swarm of vehicles (70) when a speed difference between the speed of the CIPV (30) to be followed and the average speed of the swarm of vehicles (70) is less than a threshold speed difference and when the relative position of the nearest vehicle in the path to be followed is closer to the swarm of vehicles (70) than a threshold distance. [4] System according to claim 1, wherein generating the breadcrumb navigation path based on the data includes weighting the CIPV (30) to be followed as a high-quality candidate based on its good behavior. [5] System according to claim 1, wherein the sensor device (210) comprises a camera device (110), a radar device, a LiDAR device or an ultrasound device. [6] System according to claim 1, wherein the vehicle control further controls a distance to the CIPV (30) to be followed, based on the fact that the CIPV (30) to be followed exhibits good behavior. [7] System according to claim 1, wherein the vehicle control further controls autonomous braking based on the CIPV (30) to follow, which exhibits good behavior. [8] System according to claim 1, wherein defining part of the plurality of vehicles as the vehicle swarm (70) includes: Determining the speed of a first vehicle from among the majority of vehicles; Determining the speed of a second vehicle from among the majority of vehicles; Determining the relative position of the first vehicle to the second vehicle; and Defining the first vehicle and the second vehicle as a swarm of vehicles (70) if a speed difference between the speed of the first vehicle and the speed of the second vehicle is less than a threshold speed difference and when the relative position of the first vehicle to the second vehicle is closer than a threshold distance. [9] Method for following a CIPV (30) using the movement flow of the surrounding vehicles, comprising: within a computerized processor of a host vehicle (20), Monitoring the data from a sensor device (210) that collects data relating to a plurality of vehicles on a drivable area in front of the host vehicle (20); Defining a part of the majority of vehicles as a vehicle swarm (70); Identifying one of the several vehicles as the one to be followed by CIPV (30); Evaluating the data to determine whether the CIPV (30) to be followed exhibits good behavior with respect to the vehicle swarm (70); and if the CIPV (30) to be followed shows good behavior, generate a breadcrumb navigation path based on the data; Controlling the host vehicle (20) based on the breadcrumb navigation path; and Informing a driver of the host vehicle (20) if the CIPV (30) to be followed does not exhibit good behavior.

Images