CN115187937A - Method and device for determining a road boundary for a vehicle - Google Patents
Method and device for determining a road boundary for a vehicle Download PDFInfo
- Publication number
- CN115187937A CN115187937A CN202110353245.2A CN202110353245A CN115187937A CN 115187937 A CN115187937 A CN 115187937A CN 202110353245 A CN202110353245 A CN 202110353245A CN 115187937 A CN115187937 A CN 115187937A
- Authority
- CN
- China
- Prior art keywords
- road boundary
- initial road
- initial
- vehicle
- boundary
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000011156 evaluation Methods 0.000 claims abstract description 27
- 230000004044 response Effects 0.000 claims description 9
- 230000015654 memory Effects 0.000 claims description 5
- 238000013145 classification model Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 2
- 238000004891 communication Methods 0.000 description 6
- 230000003936 working memory Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000010267 cellular communication Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The present disclosure relates to a method for determining a road boundary for a vehicle, comprising: obtaining one or more initial road boundaries by curve fitting a set of data points from sensors onboard the vehicle; evaluating the score of each initial road boundary according to a set evaluation rule; and determining whether each initial road boundary is a valid road boundary according to the score of each initial road boundary, wherein the evaluation rule comprises one or more of the following indexes: the distance between the estimated initial road boundary and the vehicle; the number of support points for the evaluated initial road boundary in the data point set; residual values of the set of data points with respect to the initial road boundary being evaluated; a curve length of the initial road boundary being evaluated; and the degree of curvature of the initial road boundary being evaluated. The disclosure also relates to an apparatus and a storage medium for determining a road boundary for a vehicle.
Description
Technical Field
The present disclosure relates to a method and apparatus for determining a road boundary for a vehicle.
Background
In the automatic driving process of a vehicle, MAP data around the vehicle is often extracted from a high precision MAP (HD MAP) according to positioning information of the vehicle to plan a driving track of the vehicle. For example, MAP data in a range in front of and behind the vehicle, which may include boundaries of roads (or lanes), may be extracted from the HD MAP based on the positioning information of the vehicle. The vehicle may plan to travel according to the boundaries of the road (or lane).
In some cases, the vehicle needs to detect the road boundary itself, for example, when no HD MAP is available or the location of the vehicle is inaccurate. Based on data from the onboard sensors, a set of data points (referred to herein as a "data point set") embodying a series of obstacles (typically inactive objects) may be detected. The vehicle needs to fit the data points in the data point set to a road boundary and select one or more valid road boundaries from the data points.
Disclosure of Invention
It is an object of the present disclosure to provide a method and apparatus for determining a road boundary for a vehicle.
According to a first aspect of the present disclosure, there is provided a method for determining a road boundary for a vehicle, comprising: obtaining one or more initial road boundaries by curve fitting a set of data points from sensors onboard the vehicle; evaluating the score of each initial road boundary according to a set evaluation rule; and determining whether each initial road boundary is a valid road boundary according to the score of each initial road boundary, wherein the evaluation rule comprises one or more of the following indexes: a distance between the estimated initial road boundary and the vehicle; the number of support points for the evaluated initial road boundary in the data point set; residual values of the set of data points with respect to the initial road boundary being evaluated; a curve length of the initial road boundary being evaluated; and the degree of curvature of the initial road boundary being evaluated.
In an exemplary embodiment of this aspect, in response to the evaluation rule including a plurality of metrics, the evaluating includes: respectively evaluating a plurality of sub-scores corresponding to the plurality of indexes; and combining the sub-scores in a weighted manner to obtain the score of the evaluated initial road boundary.
In one exemplary embodiment of this aspect, the evaluating comprises: evaluating one or more sub-scores corresponding to one or more metrics, the method further comprising: determining, using the trained classification model, whether the initial road boundary being evaluated is a valid road boundary based on the one or more sub-scores.
In an exemplary embodiment of the present aspect, the method further comprises: and updating the historical effective road boundary to obtain the one or more initial road boundaries. Optionally, the historical valid road boundaries are one or more valid road boundaries that were previously determined. Optionally, the updating is based on kalman filtering.
In an exemplary embodiment of the present aspect, the method further comprises: before the curve fitting is carried out, dividing a data point set into two subsets respectively corresponding to a left road boundary and a right road boundary; and performing the curve fitting, the evaluating, and the determining separately for each subset. Optionally, the partitioning is performed according to a historical travel trajectory and/or a predicted travel trajectory of the vehicle. Optionally, the road type is determined according to the distribution of the data points in the data point set, and the division is performed according to the road type.
In an exemplary embodiment of this aspect, the plurality of initial road boundaries comprises a first initial road boundary and a second initial road boundary, the merging comprises one or more of: in response to the fact that the first initial road boundary and the second initial road boundary have a continuation relation in the length direction, determining a curve capable of showing the continuation of the first initial road boundary and the second initial road boundary in the length direction as a fused initial road boundary formed by fusing the first initial road boundary and the second initial road boundary; determining a curve including a portion of one of the first and second initial road boundaries that is closer to the vehicle than the other initial road boundary as a fused initial road boundary into which the first and second initial road boundaries are fused, in response to the first and second initial road boundaries crossing; and in response to the first initial road boundary being substantially parallel to the second initial road boundary, determining an initial road boundary of the first initial road boundary and the second initial road boundary, which is closer to the vehicle, as a fused initial road boundary into which the first initial road boundary and the second initial road boundary are fused.
In an exemplary embodiment of this aspect, the sensor is in plurality and the set of data points is based on a fusion of data sensed by the plurality of sensors.
According to a second aspect of the present disclosure, an apparatus for determining a road boundary for a vehicle is provided. The apparatus includes: one or more processors; and one or more memories configured to store a series of computer-executable instructions, wherein when executed by the one or more processors, cause the one or more processors to perform the method as described above.
According to a third aspect of the disclosure, a non-transitory computer-readable storage medium is provided. The non-transitory computer-readable storage medium has stored thereon a series of computer-executable instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform the method as described above.
Other features of the present disclosure and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description, serve to explain the principles of the disclosure.
The present disclosure may be more clearly understood from the following detailed description, taken with reference to the accompanying drawings, in which:
FIG. 1 is a flow chart schematically illustrating a method for determining a road boundary for a vehicle, in accordance with one embodiment of the present disclosure.
Fig. 2A to 2C are schematic diagrams schematically illustrating a method for determining a road boundary for a vehicle according to an embodiment of the present disclosure.
Fig. 3 is an exemplary block diagram schematically illustrating a general hardware system applicable to the present disclosure according to an embodiment of the present disclosure.
Note that in the embodiments described below, the same reference numerals are used in common between different drawings to denote the same portions or portions having the same functions, and a repetitive description thereof will be omitted. In some cases, similar items are indicated using similar reference numbers and letters, and thus, once an item is defined in a figure, it need not be discussed further in subsequent figures.
Detailed Description
The present disclosure will now be described with reference to the accompanying drawings, which illustrate several embodiments of the disclosure. It should be understood, however, that the present disclosure may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein; rather, the embodiments described below are intended to provide a more complete disclosure of the present disclosure, and to fully convey the scope of the disclosure to those skilled in the art. It is also to be understood that the embodiments disclosed herein can be combined in various ways to provide further additional embodiments.
It is to be understood that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the disclosure. All terms (including technical and scientific terms) used herein have the meaning commonly understood by one of ordinary skill in the art unless otherwise defined. Well-known functions or constructions may not be described in detail for brevity and/or clarity.
Herein, the term "a or B" includes "a and B" and "a or B" rather than exclusively including only "a" or only "B" unless otherwise specifically stated.
In this document, the term "exemplary" means "serving as an example, instance, or illustration," and not as a "model" that is to be reproduced exactly. Any implementation exemplarily described herein is not necessarily to be construed as preferred or advantageous over other implementations. Furthermore, there is no intention to be bound by any expressed or implied theory presented in the preceding technical field, background, brief summary or the detailed description.
In addition, "first," "second," and like terms may also be used herein for reference purposes only, and thus are not intended to be limiting. For example, the terms "first," "second," and other such numerical terms referring to structures or elements do not imply a sequence or order unless clearly indicated by the context.
It will be further understood that the terms "comprises/comprising," "includes" and/or "including," when used herein, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
In the prior art, methods for fitting data points in a data point set to a road boundary exist, for example, a road boundary fitting method based on RANdom SAmple Consensus (RANSAC) algorithm. A known road boundary fitting process may include:
step 1: randomly selecting a specific number of data points (for example, 4 points or 6 points, etc.) in the data point set, and fitting an initial polynomial based on the data points;
step 2: projecting other data points in the data point set to the initial polynomial, and if the projection distance is not greater than a first distance threshold (namely, the data points are closer to the initial polynomial), classifying the data points as local points of the initial polynomial;
and step 3: taking data points with projection distance greater than a second distance threshold (i.e. farther from the initial polynomial) as interference points of the initial polynomial, wherein the first and second distance thresholds are both preset values and may be equal or different;
and 4, step 4: fitting a polynomial again on all local points of the initial polynomial based on the fitting, wherein the polynomial is used as a result polynomial of the fitting, namely a road boundary fitted at this time; and
and 5: steps 1 to 4 are repeated to exhaust all data points in the set of data points. One or more (typically a plurality of) resulting polynomials, i.e. one or more (typically a plurality of) road boundaries, are finally obtained.
Because the data detected by the sensors is sometimes less reliable, the fitting results based on the set of data points may be biased. For one or more road boundaries fitted by the above method, how to select one or more valid road boundaries is a technical problem faced in the art.
To this end, the present disclosure proposes a method and a device for determining a road boundary for a vehicle. FIG. 1 is a flow chart schematically illustrating a method 100 for determining a road boundary for a vehicle, according to one embodiment of the present disclosure. Specifically, the method 100 includes steps S11 to S13 described below.
Step S11: one or more initial road boundaries are obtained by curve fitting a set of data points from sensors onboard the vehicle. There are various sensors mounted on a vehicle, such as an image sensor, a radar sensor, a laser radar sensor, and the like. Each sensor may include one or more. The set of data points may be generated based on a fusion of data sensed by a plurality of in-vehicle sensors. The term "curve fitting" as used herein refers to fitting one or more polynomials based on individual data points in the set of data points, and may be performed by any known curve fitting method, such as the road boundary fitting process described above. It should be noted that "curve" as referred to herein refers to a graphical representation of a polynomial, which may or may not have curved portions, such as straight lines, broken lines, or curved lines.
Step S12: and evaluating the score of each initial road boundary according to a set evaluation rule. Step S13: and determining whether each initial road boundary is an effective road boundary according to the score of each initial road boundary. The vehicle may control the travel of the vehicle according to the one or more valid road boundaries determined in step S13.
The evaluation rule may comprise one or more evaluation indicators, each initial road boundary being evaluated in accordance with each indicator to give a corresponding score, whereby a valid road boundary is selected in accordance therewith. And whether the evaluation index is reasonable or not determines whether the real effective road boundary can be selected or not. The present disclosure proposes that the evaluation rule may include one or more of index 1 to index 5 described below.
Index 1: the distance between the estimated initial road boundary and the vehicle. To ensure safe driving, the closer the road boundary to the ego-vehicle should be prioritized. Therefore, the set evaluation rule may include index 1 to consider a distance factor between the initial road boundary being evaluated and the vehicle, and such that the initial road boundary closer to the ego-vehicle may have a higher score.
Index 2: the number of support points in the data point set for the initial road boundary being evaluated. In one embodiment, the support points are points that fall entirely on the polynomial of the initial road boundary.
In one embodiment, the support points are points that fall completely on the polynomial of the initial road boundary and points that are very close to the polynomial (e.g., less than a preset distance threshold). The greater the number of support points, the greater the likelihood of indicating that the initial road boundary is close to the actual road boundary. Therefore, the set evaluation rule may include index 2 to consider the number of support points in the data point set for the initial road boundary being evaluated, and make the initial road boundary with more support points may have a higher score.
Index 3: residual values of the set of data points with respect to the initial road boundary being evaluated. In one embodiment, the residual values of the set of data points with respect to the initial road boundary being evaluated are the mean of the residuals of the polynomial for each data point in the set of data points to the initial road boundary. In one embodiment, the residual values of the set of data points with respect to the initial road boundary being evaluated are the mean of the residuals of the polynomial for each data point in the set of data points, except for the disturbance point, to the initial road boundary. The interference points in the data point set refer to data points that are farther away from the initial road boundary (at a distance from the initial road boundary greater than a preset distance threshold). The smaller the residual value, the closer the initial road boundary indicating the fit may be to the actual road boundary. Therefore, the set evaluation rule may include index 3 to consider the residual values of the data point set with respect to the initial road boundary being evaluated, and the initial road boundary having a smaller residual value may have a higher score.
Index 4: the curve length of the initial road boundary being evaluated. The actual road boundaries are generally continuous along the direction of the road centerline, so that the longer the initial road boundary is fitted, the more likely it is that the actual road boundary is approached. While noise points in the data point set often cause the fitted curve to break, becoming a short curve. Therefore, the set evaluation rule may include index 4 to consider the curve length of the initial road boundary being evaluated, and so that the initial road boundary having a longer curve length may have a higher score.
Index 5: the degree of curvature of the initial road boundary being evaluated. Generally, when a vehicle travels on a road, the direction of the vehicle body substantially coincides with the direction of the center line of the road. Therefore, an initial road boundary whose curvature is closer to the steering angle (yaw) of the ego vehicle may be closer to the real road boundary. Therefore, the set evaluation rule may include the index 5 to consider the degree of curvature of the initial road boundary being evaluated, and such that the initial road boundary whose degree of curvature is closer to the steering angle of the ego-vehicle may have a higher score.
One or more of the above-described indices 1 to 5 may be selected as an evaluation rule, and a corresponding score may be calculated for each selected index, respectively, to determine whether or not an initial road boundary is a valid road boundary.
In one embodiment, in response to the evaluation rule including a plurality of indexes, a plurality of sub-scores corresponding to the plurality of indexes may be evaluated in step S12, and respective weights of the sub-scores corresponding to the plurality of indexes may be set in advance, and the plurality of sub-scores may be weighted and combined to obtain the score of the evaluated initial road boundary. The initial road boundary whose score is higher than the threshold is then determined as the valid road boundary in step S13.
In one embodiment, one or more sub-scores corresponding to one or more metrics may be evaluated in step S12, and then a trained classification model may be used in step S13 to determine whether the evaluated initial road boundary is a valid road boundary based on the one or more sub-scores calculated in step S12. The classification model may be a binary classifier having as input one or more sub-scores corresponding to one or more criteria selected as evaluation rules and as output whether it is a valid road boundary. The binary classifier may be trained based on sub-scores corresponding to one or more of the indicators 1 to 5 (depending on which indicator or indicators are included in the set evaluation rule) and a true value (ground route), i.e., whether it is a valid road boundary.
Historical information may also be considered in order to more accurately determine valid road boundaries. Since the travel of the vehicle is continuous, the actual road boundary should have continuity in time. Therefore, it should be helpful to consider historical information.
In one embodiment, one or more valid road boundaries determined during a previous processing may be updated, for example, using kalman filtering, to obtain one or more corresponding updated road boundaries. The updated road boundary may be used as the initial road boundary, and the subsequent operations are performed on one or more initial road boundaries obtained in step S11. For example, in subsequent step S12, the sub-scores of one or more of the above-described indices 1 to 5 of the updated road boundaries are calculated using the data point sets sensed by the sensors during the present processing (instead of the data point sets collected from the sensors at the previous processing), so as to determine the validity of the updated road boundaries in step S13. The finally determined one or more valid road boundaries may or may not include updated road boundaries.
In one embodiment, before performing the curve fitting of step S11, the data point set is divided into two subsets corresponding to the left and right road boundaries, respectively, and then the operations of steps S11 to S13 described above are performed for each subset, respectively. The set of data points may be divided according to the driving trajectory of the ego-vehicle, the data points located on the left side of the driving trajectory may be divided into data subsets corresponding to the left-side road boundary, and the data points located on the right side of the driving trajectory may be divided into data subsets corresponding to the right-side road boundary. In step S11, the two subsets are used to fit the left road initial boundary and the right road initial boundary, respectively. The driving trajectory of the ego-vehicle may include a predicted driving trajectory output by the autonomous driving planning module, which embodies the driving intent of the ego-vehicle, and may be used to partition points in the set of data points that are located forward of the vehicle body. Further, the travel track may also include a historical travel track of the ego-vehicle, which may be used to segment points in the set of data points that are located behind the vehicle body.
According to the method according to this embodiment, it is possible to eliminate the excessive computational effort placed on the detection of the road boundary irrespective of the driving intention of the ego vehicle, which is particularly significant in the case of intersections and curves. For example, for a Y-intersection as shown in fig. 2A, if the predicted travel path of the vehicle is traveling on the left road (the dashed line in the figure is illustrative of the predicted travel path of the vehicle), all data points located on the right side of the travel path are divided into data subsets of the right road boundary for calculating the right boundary of the road on which the vehicle is traveling, regardless of whether there is any right branch. For another example, for a left-turn curve scene as shown in fig. 2B, without dividing the two subsets corresponding to the left and right road boundaries, it may occur that the data points corresponding to the right road boundary are fitted to the curve representing the left road boundary, resulting in too many invalid fitted curves.
In some cases, the driving trajectory predicted by the autopilot planning module may be unreliable (e.g., the evaluation score is low), and the referrability of the driving trajectory is low at this time. Even in some cases, the autopilot planning module is not capable of outputting a predicted travel trajectory. In these cases, the data points on the left and right sides of the road may be divided according to a preset road model. In one embodiment, the road type is determined according to the distribution of the data points in the data point set, and the division is performed according to the road type. For example, some common road types (also referred to as "road models") including straight roads, slightly curved roads, sharp curves, intersections, Y-junctions, and the like may be preset. When the predicted driving track is unreliable or not output, the closest road model can be selected according to the distribution situation of the data point set, so that the data point set is divided into a left subset and a right subset according to the road model.
To further mention the efficiency and accuracy of determining valid road boundaries, after curve fitting to obtain one or more initial road boundaries, multiple initial road boundaries may be fused to obtain a more reliable road boundary curve. In one embodiment, after performing step S11 to obtain a plurality of initial road boundaries and before performing the evaluation of step S12, the plurality of initial road boundaries may be fused to obtain one or more fused initial road boundaries. Then, in the subsequent operation, the evaluation of step S12 and the determination of step S13 are performed for each of the fused initial road boundaries, respectively. Specific fusion methods are described below.
Case 1: for a plurality of curves having a continuation relation in the length direction of the road, they may be merged into a longer road boundary. For example, if the first initial road boundary and the second initial road boundary have a continuation relation in the length direction, a curve capable of embodying the continuation of the first initial road boundary and the second initial road boundary in the length direction is determined as a fused initial road boundary into which the first initial road boundary and the second initial road boundary are fused.
Case 2: for multiple curves that intersect each other, the portion of each curve that is closest to the ego-vehicle may be selected to merge the multiple curves into a road boundary. For example, as shown in fig. 2C, if a first initial road boundary (as indicated by a dotted-line-shaped broken line in the figure) intersects a second initial road boundary (as indicated by a short-line-shaped broken line in the figure), a curve (as indicated by a solid line in the figure) including a portion of one of the first initial road boundary and the second initial road boundary that is closer to the vehicle than the other initial road boundary, including an upper portion of the first initial road boundary and a lower portion of the second initial road boundary, is determined as a fused initial road boundary into which the first initial road boundary and the second initial road boundary are fused.
Case 3: for multiple road boundary curves that are parallel or substantially parallel (i.e., without intersections), only one of the boundaries closest to the ego-vehicle needs to be selected, and other road boundaries that are parallel to the ego-vehicle are deleted, i.e., not evaluated and determined to be valid. For example, if the first initial road boundary is substantially parallel to the second initial road boundary, the initial road boundary closer to the vehicle of the first initial road boundary and the second initial road boundary is determined as a fused initial road boundary into which the first initial road boundary and the second initial road boundary are fused.
It should be noted that the execution subject of the method 100 may be a module loaded on a vehicle or a remote module. For example, the method 100 may be implemented by a processor onboard a vehicle executing program instructions. The method 100 may also be implemented by a processor in a cloud server executing a program instruction, where the cloud server may send the finally determined effective road boundary to the vehicle so that the vehicle may determine the driving track by itself, and the cloud server may also send the driving track planned based on the finally determined effective road boundary to the vehicle so that the vehicle directly controls driving according to the driving track. The road, as referred to in this disclosure, may include one or more lanes (lanes). That is, the road referred to in this disclosure may be understood as a lane on which the vehicle is driving or is about to drive, where the road boundary refers to the boundary of the lane. Further, references to a road in this disclosure may be understood to include a road that includes lanes on which vehicles are traveling or are about to travel, where a road boundary refers to a boundary of the road.
Fig. 3 is an exemplary block diagram schematically illustrating a generic hardware system 300 applicable to the present disclosure, according to an embodiment of the present disclosure. A system 300, which is an example of a hardware device that may be applied to aspects of the present disclosure, will now be described with reference to fig. 3. System 300 may be any machine configured to perform processing and/or computing, and may be, but is not limited to, a workstation, a server, a desktop computer, a laptop computer, a tablet computer, a personal data assistant, a smart phone, a vehicle computer, or any combination thereof. The above-described system 200 for determining a roadway boundary for a vehicle according to an embodiment of the present disclosure may be implemented in whole or at least in part by the system 300 or a similar device or system.
The system 300 may also include a non-transitory storage device 310 or be connected to a non-transitory storage device 310. The non-transitory storage device 310 may be any storage device that is non-transitory and that can enable storage of data, and may include, but is not limited to, a disk drive, an optical storage device, solid state memory, a floppy disk, a hard disk, a magnetic tape, or any other magnetic medium, an optical disk, or any other optical medium, a ROM (read only memory), a RAM (random access memory), a cache memory, and/or any other memory chip/chip set, and/or any other medium from which a computer can read data, instructions, and/or code. The non-transitory storage device 310 may be removable from the interface. The non-transitory storage device 310 may have data/instructions/code for implementing the methods, steps, and processes described above. For example, the HD MAP 211 described above may be stored, at least in part, in the non-transitory storage device 310.
The system 300 may also include a communication device 312. The communication device 312 may be any type of device or system capable of communicating with external devices and/or with a network and may include, but is not limited to, a modem, a network card, an infrared communication device, a wireless communication device, and/or a chipset, such as a bluetooth device, 1302.11 device, a WiFi device, a WiMax device, a cellular communication device, a satellite communication device, and/or the like.
When the system 300 is used as an on-board device, it may also be connected to external devices, such as a GPS receiver, sensors for sensing different environmental data, such as acceleration sensors, wheel speed sensors, gyroscopes, and so on. In this manner, the system 300 may, for example, receive location data and sensor data indicative of a driving condition of the vehicle. When the system 300 is used as an on-board device, it may also be connected to other facilities of the vehicle (e.g., an engine system, wiper blades, an anti-lock brake system, etc.) to control the operation and manipulation of the vehicle.
In addition, the non-transitory storage device 310 may have map information and software elements so that the processor 304 may perform route guidance processing. In addition, the output device 308 may include a display for displaying a map, a position marker of the vehicle, and an image indicating the running condition of the vehicle. The output device 308 may also include a speaker or an interface with headphones for audio guidance.
The bus 302 may include, but is not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MCA) bus, an Enhanced ISA (EISA) bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus. In particular, for on-board devices, the bus 302 may also include a Controller Area Network (CAN) bus or other architecture designed for application on a vehicle.
Software elements may be located in working memory 314 including, but not limited to, an operating system 316, one or more application programs 318, drivers, and/or other data and code. Instructions for performing the methods and steps described above may be included in one or more application programs 318. Executable code or source code for the instructions of the software elements may be stored in a non-transitory computer-readable storage medium, such as storage device 310 described above, and may be read into working memory 314 by compilation and/or installation. Executable or source code for the instructions of the software elements may also be downloaded from a remote location.
It is also to be understood that variations may be made in accordance with specific requirements. For example, customized hardware might also be used and/or particular elements might be implemented in hardware, software, firmware, middleware, microcode, hardware description languages, or any combination thereof. In addition, connections to other computing devices, such as network input/output devices, may be employed. For example, some or all of the methods or apparatus according to embodiments of the present disclosure may be implemented by programming hardware (e.g., programmable logic circuitry including Field Programmable Gate Arrays (FPGAs) and/or Programmable Logic Arrays (PLAs)) in assembly or hardware programming languages (e.g., VERILOG, VHDL, C + +) using logic and algorithms according to the present disclosure.
It should also be understood that the components of system 300 may be distributed across a network. For example, some processes may be performed using one processor, while other processes may be performed by another processor that is remote from the one processor. Other components of the system 300 may also be similarly distributed. As such, system 300 may be construed as a distributed computing system performing processing at multiple locations.
Although the various aspects of the present disclosure have been described so far with reference to the accompanying drawings, the above-described methods, systems and apparatuses are merely exemplary examples, and the scope of the present disclosure is not limited by these aspects, but is only limited by the following aspects: the appended claims and their equivalents. Various elements may be omitted or equivalent elements may be substituted. In addition, the steps may be performed in a different order than described in the present disclosure. Further, the various elements may be combined in various ways. It is also important that as technology develops, many of the elements described can be replaced by equivalent elements which appear after the present disclosure.
Claims (15)
1. A method for determining a road boundary for a vehicle, comprising:
obtaining one or more initial road boundaries by curve fitting a set of data points from sensors onboard the vehicle;
evaluating the score of each initial road boundary according to a set evaluation rule; and
determining whether each initial road boundary is a valid road boundary according to the score of each initial road boundary,
wherein the evaluation rules comprise one or more of the following indicators:
the distance between the estimated initial road boundary and the vehicle;
the number of support points for the evaluated initial road boundary in the data point set;
residual values of the set of data points with respect to the initial road boundary being evaluated;
a curve length of the initial road boundary being evaluated; and
the degree of curvature of the initial road boundary being evaluated.
2. The method of claim 1, wherein the residual value comprises a mean of residuals of respective data points in the set of data points, excluding the disturbance point, to the initial road boundary being evaluated.
3. The method of claim 1, wherein in response to the evaluation rule comprising a plurality of metrics, the evaluating comprises:
respectively evaluating a plurality of sub-scores corresponding to the plurality of indexes; and
the multiple sub-scores are combined in a weighted manner to obtain the score of the initial road boundary to be evaluated.
4. The method of claim 1, wherein the first and second light sources are selected from the group consisting of,
wherein the evaluating comprises:
one or more sub-scores corresponding to the one or more indicators are evaluated,
wherein the method further comprises:
determining, using the trained classification model, whether the initial road boundary being evaluated is a valid road boundary based on the one or more sub-scores.
5. The method of claim 1, further comprising:
and updating the historical effective road boundary to obtain the one or more initial road boundaries.
6. The method of claim 5, wherein the historical valid road boundaries are one or more valid road boundaries that were previously determined.
7. The method of claim 5, wherein the updating is based on Kalman filtering.
8. The method of claim 1, further comprising:
before the curve fitting is carried out, dividing a data point set into two subsets respectively corresponding to a left road boundary and a right road boundary; and
the curve fitting, the evaluating, and the determining are performed separately for each subset.
9. The method according to claim 8, wherein the partitioning is performed according to a historical travel trajectory and/or a predicted travel trajectory of the vehicle.
10. The method of claim 8, wherein the road type is determined according to a distribution of data points in the data point set, and the division is performed according to the road type.
11. The method of claim 1, further comprising:
after obtaining a plurality of initial road boundaries and before performing the evaluation, fusing the plurality of initial road boundaries to obtain one or more fused initial road boundaries; and
and performing the evaluation and the determination on each fused initial road boundary respectively.
12. The method of claim 11, wherein the plurality of initial road boundaries includes a first initial road boundary and a second initial road boundary, the fusing including one or more of:
in response to the fact that the first initial road boundary and the second initial road boundary have a continuation relation in the length direction, determining a curve capable of representing the continuation of the first initial road boundary and the second initial road boundary in the length direction as a fused initial road boundary formed by fusing the first initial road boundary and the second initial road boundary;
in response to the first initial road boundary crossing the second initial road boundary, determining a curve including a portion of one of the first initial road boundary and the second initial road boundary that is closer to the vehicle than the other initial road boundary as a fused initial road boundary into which the first initial road boundary and the second initial road boundary are fused; and
in response to the first initial road boundary being substantially parallel to the second initial road boundary, an initial road boundary of the first initial road boundary and the second initial road boundary that is closer to the vehicle is determined as a fused initial road boundary into which the first initial road boundary and the second initial road boundary are fused.
13. The method of claim 1, wherein the sensor is multiple and the set of data points is based on a fusion of data sensed by the multiple sensors.
14. An apparatus for determining a roadway boundary for a vehicle, comprising:
one or more processors; and
one or more memories configured to store a series of computer-executable instructions,
wherein the series of computer-executable instructions, when executed by the one or more processors, cause the one or more processors to perform the method of any one of claims 1-13.
15. A non-transitory computer-readable storage medium having stored thereon a series of computer-executable instructions that, when executed by one or more computing devices, cause the one or more computing devices to perform the method of any of claims 1-13.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110353245.2A CN115187937A (en) | 2021-04-01 | 2021-04-01 | Method and device for determining a road boundary for a vehicle |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110353245.2A CN115187937A (en) | 2021-04-01 | 2021-04-01 | Method and device for determining a road boundary for a vehicle |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115187937A true CN115187937A (en) | 2022-10-14 |
Family
ID=83511568
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110353245.2A Pending CN115187937A (en) | 2021-04-01 | 2021-04-01 | Method and device for determining a road boundary for a vehicle |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115187937A (en) |
-
2021
- 2021-04-01 CN CN202110353245.2A patent/CN115187937A/en active Pending
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109213134B (en) | Method and device for generating automatic driving strategy | |
EP3699048B1 (en) | Travelling track prediction method and device for vehicle | |
US10824153B2 (en) | Cost design for path selection in autonomous driving technology | |
US11231294B2 (en) | Enabling alert messages in a vehicle | |
JP7098883B2 (en) | Vehicle control methods and equipment | |
CN110998691B (en) | Driving assistance method and driving assistance device | |
CN109760675B (en) | Method, device, storage medium and terminal equipment for predicting vehicle track | |
EP3321757A1 (en) | Planning feedback based decision improvement system for autonomous driving vehicle | |
US8265869B2 (en) | Vehicle navigation apparatus and vehicle navigation program | |
JP7186241B2 (en) | Vehicle driving support method, vehicle driving support device, and automatic driving system | |
CN113928340B (en) | Obstacle avoidance method and device applied to vehicle, electronic equipment and storage medium | |
US12036980B2 (en) | Course prediction device, computer readable medium, and course prediction method | |
US12080076B2 (en) | Control system for a vehicle display of indication of road traffic sign | |
CN111413973A (en) | Lane change decision method and device for vehicle, electronic equipment and storage medium | |
JP2021140367A (en) | Communication device, vehicle, program, and communication method | |
CN117195065A (en) | Driving assistance method, driving assistance device, vehicle, electronic device and storage medium | |
US20220406179A1 (en) | Control apparatus, movable object, control method, and computer readable storage medium | |
KR102427810B1 (en) | Method and apparatus for determining the lane's centerline network | |
CN116086477A (en) | Local path information generation method, device, equipment and computer readable medium | |
CN115187937A (en) | Method and device for determining a road boundary for a vehicle | |
JP2012137362A (en) | Travel road estimation device, method, and program | |
JP2009229149A (en) | Warning device for turning on blinker and program for the same | |
US12080171B2 (en) | Alert control device, mobile object, alert controlling method and computer-readable storage medium | |
JP7313240B2 (en) | Traveling trajectory estimation method, vehicle control method, and traveling trajectory estimation device | |
WO2021117464A1 (en) | Driving assistance device and driving assistance system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |