Vehicle Sensor Operation

Abstract

A system includes a processor; and a memory storing instructions executable by the processor to perform the following operations: receiving image data from a vehicle sensor installed in a vehicle, transforming the image data into global coordinate data, estimating a fractal dimension value of the global coordinate data, and determining a calibration parameter based on the fractal dimension value to operate the vehicle sensor.

Description

Technical Field

[0001] The present invention relates to the field of vehicle sensors and, more particularly, to vehicle sensor operation. Background Art

[0002] Sensors collect data about the vehicle's surroundings. A computer in the vehicle can use the data to operate one or more vehicle components. The data can include, for example, data about the road, objects on the road and / or adjacent to the road, other vehicles, etc. The computer can use the data to build a virtual representation of the surrounding environment. Calibrating the sensors to collect the data with the desired accuracy is a problem. Summary of the invention

[0003] A system includes a processor and a memory storing instructions executable by the processor to receive image data from a vehicle sensor installed in a vehicle, transform the image data into global coordinate data, estimate a fractal dimension value of the global coordinate data, and determine calibration parameters based on the fractal dimension value to operate the vehicle sensor.

[0004] The instructions may also include instructions for estimating a fractal dimension value for each of a plurality of stored parameters used to transform the image data into the global coordinate data.

[0005] The instructions may also include instructions for determining the calibration parameters by identifying a stored parameter associated with a minimum fractal dimension value of the global coordinate data.

[0006] The parameters may include parameters of six dimensions in the global coordinate system. The instructions may also include instructions for determining a fractal dimension value for the set of parameters of the six dimensions.

[0007] The instructions may further include instructions for transforming data having parameters into sensor coordinate data and transforming sensor coordinate data having predetermined parameters into global coordinate data.

[0008] The instructions may also include instructions for transforming the sensor coordinate data having predetermined parameters into vehicle coordinate data.

[0009] The instructions may also include instructions to actuate sensors to collect data about the vehicle's surroundings.

[0010] The instructions may also include instructions to receive data from a plurality of sensors and determine calibration parameters based on estimated fractal dimension values ​​of the data from the different sensors.

[0011] The instructions may also include instructions for estimating a fractal dimension value using a cost function.

[0012] The instructions may also include instructions to direct the vehicle sensor to collect additional image data, apply calibration parameters to the collected image data to transform the additional image data into additional global coordinate data, and actuate the vehicle component based on the additional global coordinate data.

[0013] A method includes receiving image data from a vehicle sensor installed in a vehicle, transforming the image data into global coordinate data, estimating a fractal dimension value of the global coordinate data, and determining calibration parameters to operate the vehicle sensor based on the fractal dimension value.

[0014] The method may also include estimating a fractal dimension value for each of a plurality of stored parameters used to transform the image data into the global coordinate data.

[0015] The method may also include determining a calibration parameter by identifying a stored parameter associated with a minimum fractal dimension value of the global coordinate data.

[0016] In the method, the parameters may include parameters of six dimensions in a global coordinate system, and the method may further include determining a fractal dimension value for each parameter set of the six dimensions.

[0017] The method may further include transforming the data having the stored parameters into sensor coordinate data, and transforming the sensor coordinate data having the predetermined parameters into global coordinate data.

[0018] The method may also include receiving data from a plurality of sensors and determining calibration parameters based on estimated fractal dimension values ​​of the data from the different sensors.

[0019] A system includes: a sensing member for providing data; and a computer programmed to receive image data from a vehicle sensor installed in a vehicle, transform the image data into global coordinate data, estimate a fractal dimension value of the global coordinate data, and determine calibration parameters based on the fractal dimension value to operate the vehicle sensor.

[0020] The computer may also be programmed to estimate a fractal dimension value for each of a plurality of stored parameters used to transform the image data into global coordinate data.

[0021] The computer may also be programmed to determine the calibration parameters by identifying the stored parameters associated with the minimum fractal dimension value of the global coordinate data.

[0022] The computer may also be programmed to receive data from a plurality of sensors and determine calibration parameters based on estimated fractal dimension values ​​of the data from the different sensors.

[0023] By selecting parameters for transforming raw sensor data into one or more coordinate systems based on the fractal dimension, a computer can map the raw data from the sensor to a coordinate system that allows the computer to actuate vehicle components based on objects detected by the data. The parameters can be selected to calibrate the sensor. The fractal dimension is lowest when the data deviates the least from the object from which the data was collected. That is, a low fractal dimension can correspond to a more refined reading from the sensor. Therefore, the sensor can be calibrated to collect more accurate information about objects around the vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 is a block diagram of an exemplary system for operating a vehicle.

[0025] Figure 2 is a perspective view of a vehicle having multiple sensors.

[0026] Figure 3 is a block diagram of an exemplary process for calibrating a sensor. DETAILED DESCRIPTION

[0027] Figure 1 An exemplary system 100 for operating a vehicle 101 is shown. A computer 105 in the vehicle 101 is programmed to receive data 115 from one or more sensors 110. For example, the vehicle 101 data 115 may include the location of the vehicle 101, the speed of the vehicle 101, etc. The location data may be in a known form, for example, geographic coordinates, such as well-known latitude and longitude coordinates obtained via a navigation system that uses a global positioning system (GPS). Additional examples of data 115 may include measurements of systems and components of the vehicle 101, such as the speed of the vehicle 101, the trajectory of the vehicle 101, etc.

[0028] As is well known, the computer 105 is typically programmed to communicate on a vehicle 101 network (e.g., including a communication bus). Via a network, bus, and / or other wired or wireless mechanism (e.g., a wired or wireless local area network in the vehicle 101), the computer 105 can transmit messages to and / or receive messages from various devices in the vehicle 101, such as controllers, actuators, sensors, etc., including sensor 110. Alternatively or additionally, in the event that the computer 105 actually includes multiple devices, the vehicle network can be used for communication between devices represented as the computer 105 in this disclosure. In addition, the computer 105 can be programmed to communicate with a network, which can include various wired and / or wireless networking technologies, such as cellular, Low power consumption (BLE), wired and / or wireless packet networks, etc.

[0029] Sensors 110 may include various devices. For example, as is well known, various controllers in vehicle 101 may operate as sensors 110 to provide data 115 via a network or bus of vehicle 101, such as data 115 related to vehicle speed, acceleration, position, subsystem and / or component status, etc. In addition, other sensors 110 may include cameras, motion detectors, etc., i.e., sensors 110 to provide data 115 for evaluating the location of an object, projecting the path of an object, evaluating the location of a road lane, etc. Sensors 110 may also include short-range radar, long-range radar, laser radar (LIDAR), and / or ultrasonic transducers.

[0030] Data 115 may include various data collected in vehicle 101. Examples of data 115 are provided above, and data 115 is generally collected using one or more sensors 110, and may also include data calculated therefrom in computer 105. In general, data 115 may include any data that may be collected by sensors 110 and / or calculated therefrom.

[0031] The vehicle 101 may include a plurality of vehicle components 120. As used herein, each vehicle component 120 includes one or more hardware components adapted to perform a mechanical function or operation, such as moving the vehicle, slowing or stopping the vehicle, steering the vehicle, etc. Non-limiting examples of components 120 include propulsion components (which include, for example, an internal combustion engine and / or an electric motor, etc.), transmission components, steering components (which may include, for example, one or more of a steering wheel, a steering rack, etc.), braking components, parking assist components, adaptive cruise control components, adaptive steering components, movable seats, etc.

[0032] When the computer 105 operates the vehicle 101, the vehicle 101 is an "autonomous" vehicle 101. For the purposes of this disclosure, the term "autonomous vehicle" is used to refer to a vehicle 101 operating in a fully autonomous mode. The fully autonomous mode is defined as a mode in which each of the propulsion (typically via a powertrain including an electric motor and / or an internal combustion engine), braking, and steering of the vehicle 101 is controlled by the computer 105. A semi-autonomous mode is a mode in which at least one of the propulsion (typically via a powertrain including an electric motor and / or an internal combustion engine), braking, and steering of the vehicle 101 is at least partially controlled by the computer 105, rather than a human operator. In a non-autonomous mode, i.e., a manual mode, the propulsion, braking, and steering of the vehicle 101 are controlled by a human operator.

[0033] Figure 21 is a perspective view of a vehicle 101 having a sensor 110. The sensor 110 may be positioned on a roof of the vehicle 101 to collect data 115 from around the vehicle 101. The computer 105 may use the data 115 from the sensor 110 to actuate one or more vehicle components 120. The computer 105 may calibrate the sensor 110 based on the data 115 collected by the sensor 110.

[0034] The computer 105 can collect data 115 from the sensor 110 in up to six dimensions (three spatial dimensions X, Y, Z and three rotational dimensions θ, φ, ψ). The sensor 110 can be, for example, a camera, a lidar, an infrared transmitter, etc., and therefore the data 115 can be image data 115, i.e., a set of numerical arrays representing an image captured by the sensor 110. As used herein, "dimension" has the conventional meaning of a direction in a coordinate system along which the data 115 can be measured. The "spatial" dimensions are the orthogonal axes in a three-dimensional coordinate system, and the "rotational" dimensions are the angular coordinates around each spatial dimension. The rotational dimension θ is positive in the counterclockwise direction around the axis extending in the positive X direction. The rotational dimension φ is positive in the counterclockwise direction around the axis extending in the positive Y direction. The rotational dimension ψ is positive in the counterclockwise direction around the axis extending in the positive Z direction. The sensors 110 may collect data 115 of the environment and / or movement of the vehicle 101 in six dimensions X, Y, Z, θ, φ, ψ.

[0035] Computer 105 may determine the fractal dimension of data 115. As used herein, "fractal dimension" is a measure of a curve, such as a non-integer Hausdorff dimension, Minkowski dimension, etc., that describes the variation in detail of the curve due to variations in the measurement resolution of the curve. For example, the fractal dimension of a Sierpinski triangle is The computer 105 may determine the fractal dimension using a conventional algorithm, such as a box counting algorithm or other space filling function. In a box counting algorithm, an image from the data 115 is divided into a plurality of boxes having a specified side length ε. The size of ε may be based on the measurement resolution of the sensor 110. The computer 105 may determine the number N of boxes in the image having a value above an image value threshold determined by the computer 105 to indicate detection of an object using the data 115. The image value threshold may be determined based on a minimum predetermined image value indicating the presence of an object. The computer 105 may then reduce the value of ε, thereby dividing the image into more boxes having smaller side lengths, and determine another number N of boxes to detect objects in the image. The computer 105 may determine a set of values ​​N for a plurality of box sizes S and determine the fractal dimension d of the image, as described in Equation 1:

[0036]

[0037] The computer 105 can use known techniques (e.g., linear regression) to approximate the limit of the fractal dimension d from the number of boxes N for multiple side lengths ε. Alternatively, the computer 105 can use another method to determine the fractal dimension d, such as a cost function that generates a value of the fractal dimension d when minimized.

[0038] The computer 105 may determine a plurality of values ​​of a fractal dimension d of the data 115. The computer 105 may transform the raw data 115 from the sensor 110 into a sensor coordinate system. The sensor coordinate system may have a sensor coordinate dimension X s , Y s , Z s ,θ s ,φ s , ψ s and an origin at one of the sensors 110, such as Figure 2 The computer 105 may transform the sensor coordinate data 115 into a vehicle coordinate system. The vehicle coordinate system may have a vehicle coordinate dimension X v , Y v , Z v ,θ v ,φ v , ψ v and an origin on the vehicle 101 (e.g., at the leftmost point on the front bumper). The computer 105 may transform the vehicle coordinate data 115 into a global coordinate system. The global coordinate system may have coordinate dimensions X g , Y g , Z g ,θ g ,φ g , ψ g and an origin at a predetermined geographical location, for example, at the starting point of the driving route of the vehicle 101. The coordinate dimension X in the positive direction g Can be aligned with the cardinal north direction and have the coordinate dimension X in the positive direction g Can be aligned to cardinal east.

[0039] The computer 105 may transform the raw data 115 to the sensor coordinate system by applying a plurality of predetermined parameters to the raw data 115. The parameters are values ​​that transform the data 115 to one of the sensor coordinate system, the vehicle coordinate system, and the global coordinate system when applied to the data 115. For example, the parameters may be a coordinate transformation matrix that maps the raw data 115 to coordinates in one of the sensor coordinate system, the vehicle coordinate system, and the global coordinate system. The parameters may map each raw data 115 input to a six-dimensional array of numbers in one of the sensor coordinate system, the vehicle coordinate system, and the global coordinate system. The following equation 2 shows exemplary parameters:

[0040]

[0041] where a X , a Y , a Z , a θ , a φ， a ψ It converts the data in coordinates X, Y, Z, θ, φ, ψ to different coordinate systems X a , Y a , Z a ,θ a ,φ a , ψ a Parameters of the data in .

[0042] In another example, the sensor 110 may receive raw data 115 in the rotation dimensions θ, φ, ψ, and the computer 105 may transform the data 115 into spatial coordinates X in the sensor coordinate system, for example, according to Equation 3. s , Y s , Z s :

[0043]

[0044] Where b1, b2, b3, b4, b5, b6 are parameters for transforming the raw data 115 into the sensor coordinate system. That is, one of the sensors 110 may receive the raw data 115 in units relative to the sensor 110, such as azimuth, elevation, distance from the sensor 110, intensity of light received by the sensor 110, etc. The computer 105 may apply the parameters to transform the data 115 into the sensor coordinate system. The computer 105 may use additional equations (not shown) depending on the specific type of sensor 110 and the type of data 115 collected to convert the data 115 into the sensor coordinate system, the vehicle coordinate system, and the global coordinate system.

[0045] The computer 105 may determine a fractal dimension d of an image generated based on the data 115, wherein each parameter set of the six dimensions X, Y, Z, θ, φ, ψ is applied to the data 115, for example, using a transformation such as shown in Equations 2 to 3. The computer 105 may store an initial parameter set and determine the fractal dimension d of the image based on the initial parameter set applied to the data 115. The initial parameter set may be determined, for example, by a manufacturer, and may be a value determined from empirical data during diagnostic testing of the sensor 110. Alternatively, the initial parameter set may each have a value of 0. The computer 105 may generate new parameters, for example, by incrementing the initial parameter set by a fixed value (e.g., 0.01), by interpolating with a known method (e.g., Newton's method), etc., and determine multiple values ​​of the fractal dimension d based on the new parameter set. That is, each generated parameter set of the dimensions X, Y, Z, θ, φ, ψ may have an associated fractal dimension d determined by constructing an image from the data 115 using the parameter set applied to the data 115. The computer 105 may continue with the new parameters until a parameter endpoint, for example, until an upper parameter limit predetermined by the manufacturer, or until the difference between the value of the fractal dimension d from the latest parameter set and the value of the fractal dimension d from the previous factor set is below a predetermined difference threshold.

[0046] Computer 105 may store the parameter set associated with the lowest fractal dimension value as the calibration parameter set. Using the calibration parameters, computer 105 may operate sensor 110 to collect data 115 and analyze data 115 more accurately.

[0047] Figure 3 An exemplary process 300 is shown for calibrating a sensor 110 in a vehicle 101 and operating the vehicle 101 using the calibrated sensor 110. The process 300 begins in block 305, where the computer 105 actuates the sensor 110 to collect data 115 from the environment around the vehicle 101. As described above, the computer 105 may actuate the sensor 110, such as a lidar 110, to collect data 115 from an area within a distance radius from the sensor 110. The data 115 may include data 115 in three spatial dimensions X, Y, Z and three rotational dimensions θ, φ, ψ.

[0048] Next, in block 310, the computer 105 determines parameters to apply to the data 115. Parameters are numerical values ​​that, when applied to the data 115, transform the data 115 into one of the sensor coordinate system, the vehicle coordinate system, or the global coordinate system. As described above, the computer 105 may apply parameters to transform the raw data 115 from the sensor 110 into one of the coordinate systems.

[0049] Next, in block 315, the computer 105 transforms the data 115 into a set of sensor coordinate data 115. As described above, the sensor coordinate data 115 may be values ​​in a sensor coordinate system. The sensor coordinate system may be a spatial coordinate system with a point on the sensor 110 as an origin. The computer 105 may apply a set of parameters to transform the raw data 115 into the sensor coordinate data 115. For example, as shown in Equation 3, the computer 105 may use parameters to convert the raw data 115 to the sensor coordinate system.

[0050] Next, in block 320, the computer 105 transforms the sensor coordinate data 115 into a set of vehicle coordinate data 115. As described above, the vehicle coordinate data 115 may be values ​​in a vehicle coordinate system. The vehicle coordinate system may be a spatial coordinate system in which points on the vehicle 101 (e.g., the edge of the front bumper) are at an origin. The computer 105 may apply a set of parameters to transform the sensor coordinate data 115 into the vehicle coordinate data 115.

[0051] Next, in block 325, the computer 105 transforms the vehicle coordinate data 115 into a set of global coordinate data 115. As described above, the global coordinate data 115 may be values ​​in a global coordinate system. The global coordinate system may be a spatial coordinate system with a predetermined point as an origin. The computer 105 may apply a parameter set to transform the vehicle coordinate data 115 into the global coordinate data 115.

[0052] Next, in box 330, the computer 105 determines the fractal dimension of the data 115. As described above, the fractal dimension is a measure of the curve, such as a non-integer Hausdorff dimension, a Minkowski dimension, etc., which describes the change in the details of the curve caused by the change in the measurement resolution of the curve. The computer 105 can determine the fractal dimension using, for example, a box counting algorithm, a space filling function, a cost function, etc., as shown in Equation 1 above. The computer 105 can apply the parameter set to the data 115 to generate an image. The computer 105 can determine the fractal dimension by applying, for example, the box counting algorithm of Equation 1 to the image.

[0053] Next, in block 335, the computer 105 determines whether to continue process 300. The computer 105 may determine to continue process 300 to generate new parameters to apply to the data 115 and determine the fractal dimension of the new parameters. If the computer 105 determines to continue, the process 300 continues in block 340. Otherwise, the process 300 continues in block 345.

[0054] In block 340, the computer 105 generates new parameters to apply to the data 115. The computer 105 may generate the new parameters, for example, by incrementing previously used parameters by a fixed value (e.g., 0.01), decrementing previously used parameters by a fixed value (e.g., 0.01), interpolating previously used parameters using a fixed equation (e.g., using Newton's method), etc. The process 300 then returns to block 310 using the new parameters.

[0055] In block 345, the computer 105 determines the parameter set corresponding to the lowest fractal dimension in each coordinate system and stores the parameters. The computer 105 applies the parameter set corresponding to the lowest fractal dimension to calibrate the sensor 110. Thus, using the determined parameters, the computer 105 can collect finer data 115 from the sensor 110, i.e., data 115 with a smaller and more precise resolution. The finer data 115 allows the computer 105 to operate the component 120 with greater precision, thereby improving the operation of the component 120 and the vehicle 101. The computer 105 can determine the parameter set with the lowest fractal dimension for the dimensions X, Y, Z, θ, φ, ψ of each of the sensor coordinate system, the vehicle coordinate system, and the global coordinate system.

[0056] Next, in box 350, the computer 105 applies the calibration parameters to the raw sensor data 115 to generate calibration data 115. The calibration parameters can transform the data 115 into one of the above-mentioned coordinate systems, thereby producing a virtual representation of the environment around the vehicle 101, which the computer 105 can use to actuate the components 120. Using the calibration data 115, the computer 105 can actuate one or more vehicle components 120 more accurately.

[0057] Next, in block 355, the computer 105 actuates one or more vehicle components 120 based on the calibration data 115. Using the calibration data 115, the computer 105 may actuate the one or more components 120 to, for example, manipulate the vehicle 101 within a virtual environment represented by the calibration data 115. After block 355, the process 300 ends.

[0058] As used herein, the adverb "substantially" modifying an adjective means that the shape, structure, measurement results, value, calculation results, etc. may deviate from the precisely described geometry, distance, measurement results, value, calculation results, etc. due to imperfections in materials, processing, manufacturing, data collector measurements, calculations, processing time, communication time, etc.

[0059] The computers 105 typically each include instructions that can be executed by one or more computing devices (such as those noted above) and for performing the blocks or steps of the processes described above. The computer-executable instructions can be compiled or interpreted from a computer program created using a variety of programming languages ​​and / or technologies, including but not limited to, alone or in combination, Java, TM , C, C++, Visual Basic, Java Script, Perl, HTML, etc. Typically, a processor (e.g., a microprocessor) receives instructions, such as from a memory, a computer-readable medium, etc., and executes these instructions to perform one or more processes, including one or more processes described herein. Various computer-readable media can be used to store and transmit such instructions and other data. Files in computer 105 are typically collections of data stored on computer-readable media (such as storage media, random access memory, etc.).

[0060] Computer readable media include any media that participate in providing data (e.g., instructions) that can be read by a computer. Such media can take many forms, including but not limited to non-volatile media, volatile media, etc. Non-volatile media include, for example, optical disks or disks and other permanent memories. Volatile media include dynamic random access memory (DRAM), which usually constitutes main memory. Common forms of computer readable media include, for example, floppy disks, floppy disks, hard disks, magnetic tapes, any other magnetic media, CD ROMs, DVDs, any other optical media, punch cards, paper tapes, any other physical media with hole patterns, RAMs, PROMs, EPROMs, FLASH EEPROMs, any other memory chips or cassettes, or any other media that a computer can read.

[0061] With respect to the media, processes, systems, methods, etc. described herein, it should be understood that although the steps of these processes, etc. have been described as occurring according to a certain ordered sequence, these processes can be practiced with the steps performed in an order other than that described herein. It should also be understood that certain steps can be performed simultaneously, other steps can be added, or certain steps described herein can be omitted. For example, in process 300, one or more steps can be omitted, or can be performed in a different order than that described herein. Figure 3 In other words, the descriptions of systems and / or processes herein are provided for the purpose of illustrating certain embodiments and should in no way be construed as limiting the disclosed subject matter.

[0062] Therefore, it should be understood that the present disclosure, including the above description and the accompanying drawings and the appended claims, is intended to be illustrative and not restrictive. After reading the above description, many embodiments and applications other than the examples provided will be apparent to those skilled in the art. The scope of the present invention should not be determined with reference to the above description, but should be determined with reference to the claims attached hereto and / or included in the non-provisional patent application based thereon and the entire range of equivalents to which these claims are entitled. It is expected and hoped that future developments will occur in the technology discussed herein, and the disclosed systems and methods will be incorporated into such future embodiments. In short, it should be understood that the disclosed subject matter is capable of modification and change.

[0063] Unless otherwise specified, or the context requires otherwise, the articles "a" and "an" modifying a noun are to be construed as meaning one or more. The phrase "based on" includes partially or entirely based on.

[0064] According to the present invention, a system is provided, which has a processor; and a memory storing instructions executable by the processor to perform the following operations: receiving image data from a vehicle sensor installed in a vehicle; converting the image data into global coordinate data; estimating a fractal dimension value of the global coordinate data; and determining calibration parameters based on the fractal dimension value to operate the vehicle sensor.

[0065] According to one embodiment, the instructions further include instructions for estimating a fractal dimension value for each of a plurality of stored parameters used to transform the image data into global coordinate data.

[0066] According to one embodiment, the instructions further include instructions for determining the calibration parameters by identifying a stored parameter associated with a minimum fractal dimension value of the global coordinate data.

[0067] According to one embodiment, the invention is further characterized in that the parameters include parameters of six dimensions in a global coordinate system, and wherein the instructions further include instructions for determining a fractal dimension value for the set of parameters in the six dimensions.

[0068] According to one embodiment, the instructions further include instructions for transforming the data with the parameters into sensor coordinate data and transforming the sensor coordinate data with the parameters into global coordinate data.

[0069] According to one embodiment, the instructions further include instructions for transforming the sensor coordinate data having the parameters into vehicle coordinate data.

[0070] According to one embodiment, the instructions further include instructions to actuate sensors to collect data about the vehicle's surroundings.

[0071] According to one embodiment, the instructions further include instructions to receive data from a plurality of sensors and determine calibration parameters based on estimated fractal dimension values ​​of the data from the different sensors.

[0072] According to one embodiment, the instructions further include instructions for estimating a fractal dimension value using a cost function.

[0073] According to one embodiment, the instructions further include instructions to direct the vehicle sensor to collect additional image data, apply calibration parameters to the collected image data to transform the additional image data into additional global coordinate data, and actuate the vehicle component based on the additional global coordinate data.

[0074] According to the present invention, a method is provided, which has the following aspects: receiving image data from a vehicle sensor installed in a vehicle; transforming the image data into global coordinate data; estimating a fractal dimension value of the global coordinate data; and determining calibration parameters based on the fractal dimension value to operate the vehicle sensor.

[0075] According to one embodiment, the above invention is further characterized by estimating a fractal dimension value for each of a plurality of stored parameters used to transform the image data into global coordinate data.

[0076] According to one embodiment, the above invention is further characterized by determining the calibration parameters by identifying the stored parameters associated with the minimum fractal dimension value of the global coordinate data.

[0077] According to one embodiment, the above invention is further characterized in that the parameters include parameters of six dimensions in a global coordinate system, and wherein the method further comprises determining a fractal dimension value for each parameter set of the six dimensions.

[0078] According to one embodiment, the above invention is further characterized by transforming the data with parameters into sensor coordinate data, and transforming the sensor coordinate data with parameters into global coordinate data.

[0079] According to one embodiment, the above invention is further characterized by receiving data from a plurality of sensors and determining calibration parameters based on estimated fractal dimension values ​​of the data from the different sensors.

[0080] According to the present invention, a system is provided, which has a sensing member for providing data; and a computer, which is programmed to: receive image data from a vehicle sensor installed in a vehicle; transform the image data into global coordinate data; estimate a fractal dimension value of the global coordinate data; and determine calibration parameters based on the fractal dimension value to operate the vehicle sensor.

[0081] According to one embodiment, the computer is further programmed to estimate a fractal dimension value for each of a plurality of stored parameters used to transform the image data into global coordinate data.

[0082] According to one embodiment, the computer is further programmed to determine the calibration parameters by identifying the stored parameters associated with the minimum fractal dimension value of the global coordinate data.

[0083] According to one embodiment, the computer is further programmed to receive data from a plurality of sensors and determine calibration parameters based on estimated fractal dimension values ​​of the data from the different sensors.

Claims

1. A method for calibrating a vehicle sensor, comprising: receiving image data from a vehicle sensor installed in the vehicle; transforming the image data into global coordinate data; estimating a fractal dimension value of the global coordinate data; as well as Calibration parameters are determined based on the fractal dimension values ​​to operate the vehicle sensors.

2. The method according to claim 1, further comprising: A fractal dimension value is estimated for each of a plurality of stored parameters used to transform the image data into the global coordinate data.

3. The method according to claim 2, further comprising: The calibration parameters are determined by identifying the stored parameters associated with a minimum fractal dimension value of the global coordinate data.

4. The method of claim 1, wherein the parameters include parameters of six dimensions in a global coordinate system, and wherein the method further comprises determining a fractal dimension value for the set of parameters of the six dimensions.

5. The method according to claim 1, further comprising: The data with the parameters are transformed into sensor coordinate data, and the sensor coordinate data with the parameters are transformed into the global coordinate data.

6. The method according to claim 5, further comprising: The sensor coordinate data having the parameters is transformed into vehicle coordinate data.

7. The method according to claim 1, further comprising: The sensors are actuated to collect data about the vehicle's surroundings.

8. The method according to claim 1, further comprising: Data is received from a plurality of sensors, and the calibration parameters are determined based on the estimated fractal dimension values ​​of the data from the different sensors.

9. The method according to claim 1, further comprising: The fractal dimension value is estimated using a cost function.

10. The method according to claim 1, further comprising: The vehicle sensor is directed to collect additional image data, the calibration parameters are applied to the collected image data to transform the additional image data into additional global coordinate data, and actuate a vehicle component based on the additional global coordinate data.

11. The method according to any one of claims 2 to 9, further comprising: The vehicle sensor is directed to collect additional image data, the calibration parameters are applied to the collected image data to transform the additional image data into additional global coordinate data, and actuate a vehicle component based on the additional global coordinate data.

12. The method according to any one of claims 3 to 10, further comprising: A fractal dimension value is estimated for each of a plurality of stored parameters used to transform the image data into the global coordinate data.

13. A computer programmed to perform the method according to any one of claims 1 to 10.

14. A vehicle comprising a computer according to claim 13.

15. A computer program product comprising a computer readable medium storing instructions executable by a computer processor to perform the method according to any one of claims 1 to 10.

Images