Automated vehicle control during final assembly and dispatch

Abstract

The invention provides automated vehicle control during final assembly and dispatch. A method of controlling an autonomously operating vehicle along a test lane includes: extracting a frequency characteristic of the vehicle; determining one or more driving profiles based on the frequency characteristics and a deep learning model; causing the vehicle to select at least one of the one or more driving profiles based on at least one of the plurality of lane segments along the test lane; and control movement of the vehicle along the test lane based on the vehicle selecting at least one of the one or more driving profiles and at least one of the plurality of lane segments.

Description

Technical Field

[0001] The present disclosure relates to the automated marshalling of one or more vehicles along a test lane. More specifically, the present disclosure relates to the generation of one or more unique driving profiles associated with each of the test lanes. Background Art

[0002] The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.

[0003] Vehicle manufacturing companies marshal vehicles along a test lane to obtain audio and / or vibration associated feedback to determine whether such feedback exceeds an acceptable threshold. The marshalling of these vehicles along the test lane is done via manual operation, which requires hiring many human operators and requires these operators to work countless hours to ensure that each vehicle is properly tested. Additionally, since the marshalling of these vehicles is done via manual operation, whether the audio and / or vibration associated feedback exceeds the acceptable threshold is a subjective determination based on the judgment of the operator of a particular vehicle.

[0004] The present disclosure addresses these and other problems associated with marshalling vehicles. Summary of the Invention

[0005] This section provides an overview of the present disclosure and is not a full disclosure of its entire scope or all of its features.

[0006] The present disclosure provides a method for controlling an autonomously operating vehicle along a test lane, the method comprising: extracting frequency characteristics associated with the vehicle; determining one or more driving profiles based on the frequency characteristics and a deep learning model; causing the vehicle to select at least one of the one or more driving profiles based on at least one of a plurality of lane segments along the test lane; and controlling the movement of the vehicle along the test lane based on at least one of the plurality of lane segments and the vehicle selecting at least one of the one or more driving profiles; wherein causing the vehicle to select at least one of the one or more driving profiles further comprises: determining, based on one or more vision sensors and a positioning system, the time it will take for the vehicle to reach a starting point associated with a lane segment of the plurality of lane segments, wherein the time is a function of the distance of the vehicle from the starting point associated with the lane segment and the speed of the vehicle's travel; wherein causing the vehicle to select at least one of the one or more driving profiles is based on the determined time; the method further comprising: identifying a sound level or a vibration level that exceeds a threshold when the vehicle is moving along the test lane; and comparing the sound level or the vibration level with a baseline sound level or a baseline vibration level; the method further comprising: determining a friction level associated with a lane segment of the plurality of lane segments based on the traction between one or more wheels of the vehicle and the lane segment of the plurality of lane segments and one or more vision sensors; and causing the vehicle to apply an estimated level of torque that will equalize the effect of the determined friction level based on the determined friction level associated with the lane segment of the plurality of lane segments; wherein determining one or more driving profiles includes: generating each of the one or more driving profiles based on the frequency characteristics, wherein the frequency characteristics include one or more of the following: the speed of the vehicle, the acceleration of the vehicle, the deceleration of the vehicle, the steering of the vehicle, or a combination thereof; and wherein each of the one or more driving profiles uniquely corresponds to a respective lane segment of the plurality of lane segments.

[0007] A platooning system for controlling a vehicle operating autonomously along a test lane, the platooning system comprising: a server configured to: extract frequency characteristics associated with the vehicle; determine one or more driving profiles based on the frequency characteristics and a deep learning model; cause the vehicle to select at least one of the one or more driving profiles based on at least one of a plurality of road segments along the test lane; and control the movement of the vehicle along the test lane based on at least one of a plurality of lane segments and the vehicle selecting at least one of the one or more driving profiles; and a vehicle configured to automatically select at least one of the one or more driving profiles; wherein the server is configured to cause the vehicle to select at least one of the one or more driving profiles and is further configured to: determine, based on one or more vision sensors and a positioning system, the time it will take for the vehicle to reach a starting point associated with one of the plurality of road segments, wherein the time is a function of the distance of the vehicle from the starting point associated with the road segment and the speed at which the vehicle is traveling; wherein causing the vehicle to select at least one of the one or more driving profiles is based on the determined time; wherein the server is further configured to: identify a sound level or a vibration level that exceeds a threshold when the vehicle is moving along the test lane; and compare the sound level or the vibration level with a baseline sound level or a baseline vibration level; wherein the server is further configured to: determine a friction level associated with a road segment of the plurality of road segments based on the traction between one or more wheels of the vehicle and the road segment of the plurality of road segments and one or more vision sensors; and cause the vehicle to apply an estimated level of torque that will equalize the effect of the determined friction level based on the determined friction level associated with the road segment of the plurality of road segments; wherein the server is configured to determine one or more driving profiles and is further configured to: generate each of the one or more driving profiles based on the frequency characteristics, wherein the frequency characteristics include one or more of the following: the speed of the vehicle, the acceleration of the vehicle, the deceleration of the vehicle, the steering of the vehicle, or a combination thereof; and wherein each of the one or more driving profiles uniquely corresponds to a respective one of the plurality of road segments.

[0008] One or more non - transitory computer - readable media store processor - executable instructions that, when executed by at least one processor, cause the at least one processor to: extract frequency characteristics associated with a vehicle; determine one or more driving profiles based on the frequency characteristics and a deep - learning model; cause the vehicle to select at least one of the one or more driving profiles based on at least one of a plurality of roadway segments along a test lane; and control the movement of the vehicle along the test lane based on at least one of the plurality of roadway segments and the vehicle's selection of at least one of the one or more driving profiles; wherein the processor - executable instructions that, when executed by at least one processor, cause the vehicle to select at least one of the one or more driving profiles further cause the at least one processor to: determine the time it will take for the vehicle to reach the starting point associated with the roadway segment of the plurality of roadway segments based on one or more vision sensors and a positioning system, where the time is a function of the distance of the vehicle from the starting point associated with the roadway segment and the speed of the vehicle's travel; wherein it further causes the at least one processor to: when the vehicle is moving along the test lane, identify a sound level or a vibration level that exceeds a threshold; and compare the sound level or the vibration level with a baseline sound level or a baseline vibration level; wherein it further causes the at least one processor to: determine a friction level associated with the roadway segment of the plurality of roadway segments based on the traction between one or more wheels of the vehicle and the roadway segment of the plurality of roadway segments and one or more vision sensors; and cause the vehicle to apply an estimated level of torque that will equalize the effect of the determined friction level based on the determined friction level associated with the roadway segment of the plurality of roadway segments; wherein determining the one or more driving profiles further includes: generating each of the one or more driving profiles based on the frequency characteristics, where the frequency characteristics include one or more of the following: the speed of the vehicle, the acceleration of the vehicle, the deceleration of the vehicle, the steering of the vehicle, or a combination thereof; and wherein each of the one or more driving profiles uniquely corresponds to the corresponding roadway segment of the plurality of roadway segments.

[0009] Based on the description provided herein, additional applicable fields will become apparent. It should be understood that the description and specific examples are for illustrative purposes only and are not intended to limit the scope of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] For a better understanding of the present disclosure, various forms of the present disclosure will now be described by way of example with reference to the accompanying drawings, in which:

[0011] Figure 1 An overall vehicle automated platooning system according to various embodiments is shown;

[0012] Figure 2 Shows according to various embodiments of the Figure 1An example system associated with the automated vehicle platooning system shown;

[0013] Figure 3 Shows a plurality of example test lanes according to various embodiments;

[0014] Figure 4 Shows according to various embodiments by Figure 1 and Figure 2 The example vehicles platooned by the system shown;

[0015] Figure 5 Shows according to various embodiments along the example vehicle via Figure 1 and Figure 2 The example route of the test lane through which the automated platooning is performed by the system shown;

[0016] Figure 6 Shows a flowchart illustrating an example method for automatically switching between one or more driving profiles associated with a vehicle; and

[0017] Figure 7 Shows a flowchart illustrating another example method for automatically switching between one or more driving profiles associated with a vehicle.

[0018] The drawings described herein are for illustrative purposes only and are not intended to limit the scope of the present disclosure in any way. Detailed Description

[0019] The following description is merely exemplary in nature and is not intended to limit the present disclosure, application, or uses. It should be understood that throughout the drawings, corresponding reference numerals indicate the same or corresponding parts and features.

[0020] The present disclosure provides for the automated platooning of one or more vehicles along a plurality of test lanes by generating one or more unique driving profiles associated with respective test lanes of the plurality of test lanes. For example, the use of vision sensors, wheel speed sensors, real-time kinematic (RTK) global positioning system (GPS), or combinations thereof is used to ensure the deployment of accurate control parameters in the positioning of one or more vehicles. The use of vision sensors, wheel speed sensors, RTK GPS, or combinations thereof also provides accurate positioning of one or more vehicles on any of the plurality of test lanes with any degree of accuracy. For example, the use of vision sensors, wheel speed sensors, RTK GPS, or combinations thereof ensures that any wheel slippage is taken into account during the passage of one or more vehicles through any of the plurality of test lanes.

[0021] In various examples, implementations of GPS and / or Global Navigation Satellite System (GNSS) and RTK positioning correction eliminate the need for time-consuming, tedious, and / or manual operations on each of one or more vehicles as the one or more vehicles pass through the production squeak and rattle test phase. By implementing GPS and / or GNSS and RTK position correction, the one or more vehicles can each traverse the production squeak and rattle test phase in a fully automated manner, which significantly reduces the financial consequences associated with having numerous manual operators work numerous hours to manually operate each of the one or more vehicles as the vehicles pass through the production squeak and rattle test phase. Additionally, by implementing a fully automated system and / or method for traversing the production squeak and rattle test phase, numerous production hours are saved because the production squeak and rattle test phase will be completed more quickly than when performed manually. Further, because the present disclosure provides an automated marshalling solution to optimize the production squeak and rattle test phase of vehicle production, feedback associated with audio and / or vibration that exceeds an acceptable threshold is objectively determined based on, for example, training of a deep learning model. As an example, when a vehicle traverses any of a plurality of test lanes, the feedback associated with audio and / or vibration can be associated with audio and / or vibration related to squeaks and / or rattles.

[0022] Figure 1 System 100 is shown illustrating wireless communication relationships between several various entities. More specifically, the entities of System 100 generally include one or more infrastructure sensors 102, one or more marshalling servers 104, data network cloud 106, base station 108, vehicle 110, and GPS / GNSS satellites 112.

[0023] In various examples, data network cloud 106 is configured as the central entity of System 100, the central entity facilitating data exchange between other entities included within System 100. For example, one or more infrastructure sensors 102 are disposed within the infrastructure at different frequencies (e.g., at different locations or physical positions or physical intervals within a manufacturing facility). For example, one or more infrastructure sensors 102 can be disposed at intervals of 10 meters throughout the infrastructure. One or more infrastructure sensors 102 are configured to monitor paths that vehicle 110 can traverse. One or more infrastructure sensors 102 are also configured to send sensor data to data network cloud 106. For example, in a case where vehicle 110 enters the field of view of any of the one or more infrastructure sensors 102 (e.g., within the sensing range), the one or more infrastructure sensors 102 transmit the sensor data to data network cloud 106.

[0024] One or more marshaling servers 104 are configured to send one or more marshaling commands to the data network cloud 106. The one or more marshaling servers 104 are also configured to receive sensor data and / or one or more vehicle updates from the data network cloud 106. For example, the one or more vehicle updates may include ranging-related information, the attitude of the vehicle, or a combination thereof. It should be understood that the one or more vehicle updates may include any vehicle-related information. Although multiple marshaling servers (e.g., one or more marshaling servers 104) are discussed, it should be understood that a single marshaling server may be implemented within the system 100.

[0025] The base station 108 is configured to communicate with both the data network cloud 106 and / or the GPS / GNSS satellites 112. The base station 108 is configured to receive GPS / GNSS position data from the GPS / GNSS satellites 112. For example, the accuracy of the GPS / GNSS satellites 112 is dynamic, such that while the default accuracy may be within three to six meters, the GPS / GNSS satellites 112 can be even more precise. It should be understood that the default accuracy of the GPS / GNSS satellites 112 may be within any range. As another example, position errors associated with the accuracy of the GPS / GNSS satellites 112 may be introduced into the system 100 due to multipath errors, clock errors, delays caused by the upper atmosphere, or a combination thereof.

[0026] The base station 108 is also configured to send RTK corrections to the data network cloud 106. For example, RTK corrections can correct delays and / or clock issues by tracking the phase of the carrier of the GPS / GNSS satellites 112 to obtain precise timing and distances. As another example, RTK corrections can correct GPS / GNSS errors that are differently correlated within a geographic area, such that if the base station 108 is at a known location, the base station 108 can broadcast the corrections it has calculated to a mobile receiver, thereby making the typical position accuracy highly precise (e.g., one to two centimeters). However, it should be understood that the position accuracy may be within any range. Additionally, differential GPS (DGPS) can be implemented to compare the measurements at one mobile GPS / GNSS receiver (e.g., a rover (not shown)) with those at another fixed GPS / GNSS receiver (e.g., the base station 108). Although the position of the base station 108 is known, the rover position is calculated with different levels of accuracy relative to that point. It should be understood that the combination of the rover and the GPS / GNSS receiver can be used with GPS / GNSS positioning with RTK corrections or as an alternative to GPS / GNSS positioning with RTK corrections.

[0027] The GPS / GNSS satellite 112 is configured to communicate with both the base station 108 and the vehicle 110. The GPS / GNSS satellite 112 is configured to send GPS / GNSS position data to the base station 108. The GPS / GNSS satellite 112 is further configured to send GPS / GNSS position data to the vehicle 110. The vehicle 110 is configured to communicate with both the GPS / GNSS satellite 112 and the data network cloud 106. The vehicle 110 is configured to receive GPS / GNSS position data from the GPS / GNSS satellite 112. The vehicle 110 is further configured to send one or more vehicle updates to the data network cloud 106. Additionally, the vehicle 110 is configured to receive one or more commands and / or RTK corrections from the data network cloud 106.

[0028] Figure 2 A schematic block diagram illustration of the system 200 is shown. In one or more examples, the system 200 facilitates marshalling of one or more vehicles traveling at low speeds. However, it should be understood that the system 200 may marshal one or more vehicles traveling at any speed. It should also be understood that the system 200 may marshal semi-autonomous vehicles and / or fully autonomous vehicles.

[0029] The system 200 generally includes a data network cloud 106, a base station 108, a vehicle 110, and a vehicle marshalling cloud 214. The data network cloud 106 operates as a central component of the system 200, the central component being configured to manage and / or facilitate the marshalling process associated with the guided transportation of the vehicle 110. For example, the vehicle 110 is configured to exchange (e.g., send and / or receive) data with the data network cloud 106.

[0030] Vehicle 110 includes or implements an Automated Vehicle Maneuvering (AVM) algorithm 216, a wireless transmission module 218, a vehicle central gateway module 220, a vehicle infotainment system 222, one or more vehicle sensors 224, a vehicle battery 226, a vehicle GNSS 228, a vehicle navigation map 230, vehicle exterior lights 232, and a Controller Area Network (CAN) vehicle bus 233. The wireless transmission module 218 may be a Transmission Control Unit (TCU). The wireless transmission module 218 includes one or more sensors configured to collect data and send signals to other components of the vehicle 110. The one or more sensors of the wireless transmission module 218 may include a vehicle speed sensor (not shown) configured to determine the current speed of the vehicle 110; a wheel speed sensor (not shown) configured to determine whether the vehicle 110 is traveling uphill or downhill; a throttle position sensor (not shown) configured to determine whether a downshift or upshift of one or more gears associated with the vehicle 110 is required in the current state of the vehicle 110; and / or a turbine speed sensor (not shown) configured to send data associated with the rotational speed of the torque converter of the vehicle 110. The wireless transmission module 218 transmits the information collected by the one or more sensors to the AVM algorithm 216. In one embodiment, the AVM algorithm 216 may be provided as a component within the wireless transmission module 118. For example, the vehicle 110 utilizes the AVM algorithm 216 to process the information collected by the one or more sensors and send the information to the data network cloud 106. As another example, the vehicle 110 utilizes the AVM algorithm 216 to process the information collected by the one or more sensors and send the information directly to the user device 242. The AVM algorithm 216 is configured to transmit the information and / or instructions received from the data network cloud 106 and / or the user device 242 to the wireless transmission module 218.

[0031] The vehicle central gateway module 220 operates as an interface between various vehicle domain bus systems, such as an engine compartment bus (not shown), an interior bus (not shown), an optical bus for multimedia (not shown), a diagnostic bus for maintenance (not shown), or a vehicle CAN bus 233. The vehicle central gateway module 220 is configured to distribute data transmitted by each of the various domain bus systems to the vehicle central gateway module 220 to other components of the vehicle 110. The vehicle central gateway module 220 is also configured to distribute information received from the AVM algorithm 216 to the various domain bus systems. The vehicle central gateway module 220 is further configured to send information received from the various domain bus systems to the AVM algorithm 216. For example, the vehicle 110 utilizes the AVM algorithm 216 to process information received from the vehicle central gateway module 220 and send the information to the data network cloud 106. As another example, the vehicle 110 utilizes the AVM algorithm 216 to process information received from the vehicle central gateway module 220 and send the information directly to the user device 242. The AVM algorithm 216 is configured to transmit information and / or instructions received from the data network cloud 106 and / or the user device 242 to the vehicle central gateway module 220.

[0032] The vehicle infotainment system 222 is a system that delivers a combination of information and entertainment content and / or services to the user 244 of the vehicle 110. It should also be understood that the vehicle infotainment system 222 can deliver information services to anyone associated with the vehicle 110 (e.g., a passenger such as in the vehicle 110). As an example, the vehicle infotainment system 222 includes an in-vehicle computer that combines one or more functions, such as a digital radio, an in-vehicle camera, and / or a television. The vehicle infotainment system 222 transmits information associated with the in-vehicle computer or processor to the AVM algorithm 216. For example, the vehicle 110 utilizes the AVM algorithm 216 to process information received from the vehicle infotainment system 222 and send the information to the data network cloud 106. As another example, the vehicle 110 utilizes the AVM algorithm 216 to process information received from the vehicle infotainment system 222 and send the information directly to the user device 242. The AVM algorithm 216 is configured to transmit information and / or instructions received from the data network cloud 106 and / or the user device 242 to the vehicle infotainment system 222.

[0033] One or more vehicle sensors 224 can be, for example, one or more of a camera, lidar, radar, and / or ultrasonic device. For example, an ultrasonic device used as one or more vehicle sensors 224 emits high-frequency sound waves that strike an object (e.g., a wall or another vehicle) and then are reflected back to the vehicle 110. Based on the amount of time it takes for the sound waves to return to the vehicle 110, the vehicle 110 can determine the distance between one or more vehicle sensors 224 and the object. As another example, a camera device used as one or more vehicle sensors 224 provides a visual indication of the space around the vehicle 110. As an additional example, a radar device used as one or more vehicle sensors 224 emits an electromagnetic wave signal that strikes an object and then is reflected to the vehicle 110. Based on the amount of time it takes for the electromagnetic wave to return to the vehicle 110, the vehicle 110 can determine the range, speed, and angle of the vehicle 110 relative to the object.

[0034] One or more vehicle sensors 224 transmit information associated with the position and / or distance of the vehicle 110 relative to an object to the AVM algorithm 216. For example, the vehicle 110 uses the AVM algorithm 216 to process the information received from one or more vehicle sensors 224 and send the information to the data network cloud 106. As another example, the vehicle 110 uses the AVM algorithm 216 to process the information received from one or more vehicle sensors 224 and send the information directly to the user device 242. The AVM algorithm 216 is configured to transmit information and / or instructions received from the data network cloud 106 and / or the user device 242 to one or more vehicle sensors 224.

[0035] The vehicle battery 226 is controlled by a battery management system (not shown) that provides instructions to the vehicle battery 226. For example, the battery management system provides instructions to the vehicle battery 226 based on the temperature of the vehicle battery 226. However, it should be understood that the battery management system may provide instructions to the vehicle battery 226 based on any measure associated with the vehicle battery 226. The battery management system ensures that the current mode of the vehicle battery 226 is acceptable. For example, an acceptable current mode prevents overvoltage, overcharging, and / or overheating of the vehicle battery 226. As another example, the temperature of the vehicle battery 226 indicates to the battery management system whether any of the acceptable current modes are within an acceptable temperature range. The battery management system associated with the vehicle battery 226 transmits information associated with the temperature of the vehicle battery 226 to the AVM algorithm 216. For example, the vehicle 110 utilizes the AVM algorithm 216 to process the received information about the vehicle battery 226 and send the information to the data network cloud 106. As another example, the vehicle 110 utilizes the AVM algorithm 216 to process the information about the vehicle battery 226 and send the information directly to the user device 242. The AVM algorithm 216 is configured to transmit information and / or instructions received from the data network cloud 106 and / or the user device 242 to the vehicle battery 226.

[0036] The vehicle GNSS 228 is configured to communicate with GPS / GNSS satellites 112 such that the vehicle 110 can determine the specific location of the vehicle 110. The vehicle navigation map 230 can display the specific location of the vehicle 110 to the user 244 via a display screen (not shown). The vehicle GNSS 228 transmits the geographical information associated with the vehicle 110 to the AVM algorithm 216. For example, the vehicle 110 utilizes the AVM algorithm 216 to process the information received from the vehicle GNSS 228 and send the information to the data network cloud 106. As another example, the vehicle 110 utilizes the AVM algorithm 216 to process the information from the vehicle GNSS 228 and send the information directly to the user device 242. The AVM algorithm 216 is configured to transmit information and / or instructions received from the data network cloud 106 and / or the user device 242 to the vehicle GNSS 228. As another example, the vehicle 110 utilizes the AVM algorithm 216 to process the information associated with the vehicle navigation map 230 and send the information to the data network cloud 106. As another example, the vehicle 110 utilizes the AVM algorithm 216 to process the information from the vehicle navigation map 230 and send the information directly to the user device 242. The AVM algorithm 216 is configured to transmit information and / or instructions received from the data network cloud 106 and / or the user device 242 to the vehicle navigation map 230.

[0037] The vehicle exterior lights 232 may include one or more lights embedded around the perimeter of the vehicle 110. For example, the vehicle exterior lights 232 include, but are not limited to, low beam headlights, high beam headlights, parking lights, daytime running lights, fog lights, signal lights, side marker lights, cab lights, tail lights, brake lights, center high-mounted stop lights, and / or reverse lights. In some examples, the vehicle exterior lights 232 are configured to turn on and off in a pattern to provide a visual notification or message, such as an indication of one or more faults. For example, one or more faults may be an unplanned disconnection of the vehicle 110 from the system 200 (e.g., infrastructure (not shown) within the system 200), which may be associated with (but is not limited to) onboarding, offboarding, and / or re-onboarding of the vehicle 110 to the infrastructure. The vehicle 110 transmits one or more instructions to the vehicle exterior lights 232 based on the AVM algorithm 216. For example, the vehicle 110 transmits one or more instructions received from the data network cloud 106 to the vehicle exterior lights 232. As another example, the vehicle 110 transmits one or more instructions received directly from the user device 242 to the vehicle exterior lights 232.

[0038] The vehicle platooning cloud 214 communicates wirelessly (e.g., receives and / or sends instructions and / or messages) with a vehicle customer network portal account 236 accessible via the user device 242. For example, the vehicle platooning cloud 214 is configured to guide the vehicle 110 along a particular test lane among a plurality of test lanes 300, as Figure 3 shown. The vehicle platooning cloud 214 communicates wirelessly with the user device 242 (such as a mobile device, a display panel, and / or a computer). The vehicle 110 is also configured to communicate wirelessly directly with the user device 242. For example, the user 244 engages and / or interacts with the user device 242 via an application that organizes any information and / or instructions received from the vehicle customer website portal account 236 and / or the vehicle 110. As another example, the user 244 may send one or more instructions to the vehicle customer website portal account 236, such as selecting a particular test lane among a plurality of test lanes for the vehicle 110 to traverse.

[0039] Although multiple test lanes 300 are typically used to test the squeak and rattle effects of test vehicle 110 passing through any of the multiple test lanes 300, the multiple test lanes 300 can be used for any purpose as desired or needed. Additionally, it should be understood that the multiple test lanes 300 are not an exhaustive list of test lanes, and any type of test lane can be envisioned. For example, a test lane can be used to test a vehicle based on the terrain unique to a particular part of the world. As a further example, vehicles in North America can be tested on different test lanes than vehicles in South America. Test vehicle 110 can pass through each of the multiple test lanes 300 (e.g., test lanes 302a through 302n). Each of the multiple test lanes 300 includes a smooth section 304a and a textured section 306. Each of the multiple test lanes 300 begins with an initial smooth section 304b. However, it should be understood that each of the multiple test lanes 300 can also begin with a textured section 306 or with some other section.

[0040] Now referring to Figure 4 , in various forms, test vehicle 110 can be powered in various ways (e.g., using an electric motor and / or an internal combustion engine). As a non-limiting example, test vehicle 110 can be any type of vehicle powered by an electric motor and / or an internal combustion engine, such as a car, a truck, a robot, an airplane, and / or a boat. Test vehicle 110 includes a vehicle controller 400, one or more actuators 402, a plurality of on-vehicle sensors 404, and a human-machine interface (HMI) 406. Test vehicle 110 has a reference point 408, i.e., a designated point within the space defined by the vehicle body, e.g., the geometric center point where the respective longitudinal and lateral center axes of test vehicle 110 intersect. Reference point 408 identifies the position of test vehicle 110, e.g., the point where test vehicle 110 is located when test vehicle 110 is navigating towards a waypoint.

[0041] In some examples, the vehicle controller 400 is configured or programmed to control the operation of one or more of vehicle braking, propulsion (e.g., controlling the acceleration of vehicle 110 by controlling one or more of an internal combustion engine, an electric motor, a hybrid engine, etc.), steering, climate control, interior and / or exterior lighting, etc., and to determine whether and when the vehicle controller 400 (as opposed to a human operator) controls such operations. Additionally, the vehicle controller 400 is programmed to determine whether and when a human operator controls such operations. It should be understood that any operation associated with vehicle 110 may be facilitated via an automated, semi-automated, or manual mode. For example, the automated mode may facilitate any operation being controlled entirely by the vehicle controller 400 without user assistance. As another example, the semi-automated mode may facilitate any operation being controlled at least in part by the vehicle controller 400 and / or the user. As a further example, the manual mode may facilitate any operation being controlled entirely by the user.

[0042] The vehicle controller 400 includes one or more processors or is communicatively coupled (e.g., via a vehicle communication bus) to one or more processors, such as, for example, controllers included in vehicle 110 for monitoring and / or controlling various vehicle controllers, such as a powertrain controller, a brake controller, a steering controller, etc. The vehicle controller 400 is generally arranged to communicate on a vehicle communication network, which may include a bus in vehicle 110 (such as a controller area network (CAN), etc.), and / or other wired and / or wireless mechanisms.

[0043] The vehicle controller 400 transmits messages to and / or receives messages from various devices in vehicle 110 via the vehicle network (e.g., one or more actuators 402, HMI 406, etc.). Alternatively or additionally, in the case where the vehicle controller 400 includes multiple devices, the vehicle communication network is used for communication between the devices represented as the vehicle controller 400 in the present disclosure. Additionally, as discussed below, various other controllers and / or sensors provide data to the vehicle controller 400 via the vehicle communication network.

[0044] Additionally, the vehicle controller 400 is configured to communicate with other traffic objects (e.g., vehicles, infrastructure, pedestrians, etc.) via a vehicle-to-vehicle communication network through a wireless vehicle communication interface, such as. The vehicle controller 400 is also configured to communicate via a communication network, e.g., communicate with an infrastructure controller. The vehicle communication network represents one or more mechanisms through which the vehicle controller 400 of the vehicle 110 communicates with other traffic objects and can be one or more of wireless communication mechanisms, which include any desired combination of wireless (e.g., cellular, wireless, satellite, microwave, and radio frequency) communication mechanisms and any desired network topology (or multiple topologies when multiple communication mechanisms are used). Examples of vehicle communication networks include cellular, IEEE 802.11, dedicated short-range communication (DSRC), and / or wide area network (WAN) (including the Internet), etc.

[0045] The vehicle actuator 402 is implemented via circuits, chips, or other electronic and / or mechanical components that can actuate various vehicle subsystems according to appropriate control signals. The actuator 402 can be used to control the braking, acceleration, and / or steering of the vehicle 110. The vehicle controller 400 can be programmed to actuate the vehicle actuator 402 based on the planned acceleration or deceleration of the vehicle 110, including propulsion, steering, and / or braking.

[0046] The multiple on-vehicle sensors 404 include a variety of devices for providing data to the vehicle controller 400. For example, the multiple on-vehicle sensors 404 can include object detection sensors, such as lidar sensors disposed on or in the vehicle 110, which provide the relative positions, sizes, and shapes of one or more targets (e.g., additional vehicles, bicycles, pedestrians, robots, drones, etc.) traveling beside, in front of, and / or behind the vehicle 110. As another example, one or more of the sensors can be radar sensors fixed to one or more bumpers of the vehicle 110, which can provide the position of the target relative to the position of the vehicle 110.

[0047] The object detection sensor can include a camera sensor, e.g., to provide a front view, side view, rear view, etc., and the sensor provides images from the area around the vehicle 110. For example, the vehicle controller 400 can be programmed to receive sensor data from the camera sensor and implement image processing techniques to detect roads, infrastructure elements, etc. The vehicle controller 400 can also be programmed to determine the current vehicle position based on position coordinates (e.g., GPS coordinates) indicating the position of the vehicle 110 received from the vehicle 110 and from a GPS sensor.

[0048] The HMI 406 is configured to receive information from a user, such as a human operator, during operation of the vehicle 110. Additionally, the HMI 406 is configured to present information to a user, such as an occupant of the vehicle 110. In some variations, the vehicle controller 400 is programmed to receive destination data, such as location coordinates, from the HMI 406.

[0049] In various examples, a combination of GPS / GNSS satellites 112, base stations 108, and / or vehicle GNSS 228 can be used to autonomously guide the vehicle 110 towards a waypoint. Route selection can be performed using vehicle position, travel distance, queuing for vehicle platooning, etc. Other vehicles (not shown) with a destination of a specific waypoint operate and / or are controlled in the same manner such that the movement of the entire vehicle fleet can be coordinated. The movement of the entire vehicle fleet is coordinated by a central vehicle fleet management system that guides all traffic and logistics from the assembly plant to the waypoint. For example, the entire vehicle fleet can be organized in a pre-sorted order.

[0050] In various examples, the centralized vehicle fleet management application has complete knowledge of the vehicles under its control (e.g., current location, destination, special instructions, etc.), which increases the responsibility and traceability of the assignment process. Vehicle fleet management is coordinated within and across sites to optimize the timing associated with the platooning of each vehicle to the waypoint. For example, the waypoint can be the starting point of any of the test lanes in a plurality of test lanes. Although GPS / GNSS capabilities can be relied upon to facilitate the platooning of the vehicle 110, several other logistics applications can be used. Thus, the vehicle fleet management application queues the vehicles based on unique characteristics (e.g., how far the vehicle needs to travel, traffic conditions along the route, when the vehicle needs to arrive there to queue in the correct order, etc.).

[0051] Figure 5 An example related to the vehicle 110 passing through the test lane 500 among a plurality of test lanes 300 is shown. The vehicle 110 can pass through any of the plurality of test lanes 300 in a segmented manner. For example, in this particular example, the vehicle 110 can switch between at least three driving profiles: a first driving profile when the vehicle 110 passes through the smooth sections 504a, 504b of the test lane 500, a second driving profile when the vehicle 110 passes through the first textured section 506a of the test lane 500, and a third driving profile when the vehicle 110 passes through the second textured section 506b of the test lane 500. In some examples, the first textured section 506a and the second textured section 506b are different in at least some aspects. In other examples, the first textured section 506a and the second textured section 506b are different in all aspects.

[0052] It should be understood that any test lane among the multiple test lanes 300 may include any number of road segments, where each road segment has similar or different characteristics and / or properties. It should also be understood that when the vehicle 110 traverses any test lane among the multiple test lanes 300, any number of driving profiles may be utilized. In cases where more test segments than the smooth segments 504a, initial smooth segments 504b, and textured segments 506a, 506b exist as part of the test lane 500 among the multiple test lanes 300, additional driving profiles 500-n are implemented, and each of the additional driving profiles may require a unique calibration of the vehicle control strategy, such as activating a steering mode that continues to be modulated. For example, any test lane among the multiple test lanes 300 may require the vehicle 110 to utilize a first driving profile when the vehicle 110 traverses the smooth segments 304a, 304b, a second driving profile when the vehicle 110 traverses the textured segment 306, and different driving profiles when the vehicle 110 traverses different textured segments along the same test lane. For example, the test lane 302l has four different road segments (e.g., 304a, 304b, and 306a - 306c), which requires the vehicle 110 to utilize at least four driving profiles. As an example, the vehicle 110 may utilize a first driving profile when the vehicle 110 traverses the smooth segments 304a, 304b, a second driving profile when the vehicle 110 traverses the textured segment 306a, a third driving profile when the vehicle 110 traverses the textured segment 306b, and a fourth driving profile when the vehicle 110 traverses the textured segment 306c. However, it should be understood that the vehicle 110 may utilize a general driving profile that can be applicable to more than one type of road segment. In some examples, more than one driving profile may be used for multiple road segments. In some examples, more than one driving profile may be used for a single road segment (e.g., different portions along a single road segment).

[0053] When the vehicle traverses the test lane 500, the steering mode is modulated between positive steering and negative steering. For example, the steering mode is based on the conditions of the test lane 500 associated with each specific road segment of the test lane 500. The steering amount, steering rate, and / or steering direction are functions of the lane surface modulation (e.g., the steering mode). Additionally, the speed of the vehicle 110, as well as the acceleration and / or deceleration of the vehicle 110, are tuned to the respective positions of the vehicle 110 along a specific road lane segment of the test lane 500. When the vehicle 110 traverses a specific road lane segment of the test lane 500, the vehicle 110 is caused to be positioned by the GPS / GNSS satellites 112 based on signals from the wheel speed of the vehicle 110, the speed of the vehicle 110 itself, or a combination thereof.

[0054] Vehicle 110 includes a positioning module (e.g., vehicle GNSS 228), which in combination with the vision sensors of vehicle 110 (e.g., vehicle sensors 224 and / or multiple in-vehicle sensors 404) triggers a switch between the driving profiles of the vehicle. The switch of the driving profile of vehicle 110 is based on the distance of vehicle 110 from the starting point of the next road segment of test lane 500 (e.g., Δx) and / or the time it will take for vehicle 110 to approach the starting point of the next road segment of test lane 500 (e.g., Δn). It should be understood that in some examples, the distance is determined at least based on the vision sensors of vehicle 110, and the time is determined at least based on the wheel speed of vehicle 110.

[0055] In various examples, vehicle 110 employs a deep learning model trained based on data obtained from previous vehicles passing through multiple test lanes 300. The deep learning model is dynamic because the model continuously enhances the pre-calibrated values of the control parameters associated with vehicle 110, and the control parameters are used to indicate how vehicle 110 passes through a specific test lane. The pre-calibrated values are stored within vehicle 110 (e.g., in vehicle controller 400). When vehicle 110 approaches the starting point of any specific road segment of test lane 500, vehicle 110 looks up the stored control parameters from a calibration table (not shown).

[0056] Figure 6 Method 600 for generating a driving profile via a trained deep learning model is depicted. It should be understood that method 600 can generate any number of driving profiles via the trained deep learning model. For example, each of the driving profiles is associated with a specific test lane and / or road segment from multiple test lanes 300. However, it should be understood that one or more general driving profiles applicable to more than one type of road segment and / or test lane among multiple test lanes 300 can be generated.

[0057] Generally, a prediction model and / or a computer vision model are used to train the deep learning model, so that for road segments where a constant vehicle speed may not be achievable and periodic acceleration, braking, and / or steering may be required, feedback (e.g., driving data 602) regarding the desired vehicle speed is provided to vehicle controller 400. The driving data 602 is processed by vehicle controller 400. More specifically, vehicle controller 400 can use algorithms to process the driving data 602. The driving data 602 includes frequency characteristics associated with vehicle 110. The frequency characteristics at least include data associated with speed, acceleration, braking, steering, or a combination thereof.

[0058] The vehicle controller 400 is configured to extract the frequency characteristics collected when the vehicle 110 traverses any of the plurality of test lanes 300. The vehicle controller 400 is further configured to use the extracted frequency characteristics and / or a friction estimator (not shown) to train a deep learning model to ultimately extract the driving profile of each of the plurality of test lanes 300 traversed by the vehicle 110. For example, the vehicle controller 400 is further configured to use the extracted frequency characteristics and / or a friction estimator to train a deep learning model to ultimately extract the driving profile of each individual road segment of a particular test lane (e.g., operation 604). For example, the driving profile can uniquely correspond to the respective individual road segments of a particular test lane. As another example, the driving profile provides the vehicle 110 with certain parameters and / or instructions on how to traverse a particular road segment of a particular test lane.

[0059] The friction estimator is configured to estimate the friction level between the road and the vehicle wheels associated with a particular road segment of any one of the plurality of test lanes 300. For example, the friction estimator estimates the friction level of the road associated with a particular road segment of any one of the plurality of test lanes 300 based on a measure of the traction force between the vehicle wheels and the road and / or one or more vision sensors of the vehicle 110 (e.g., vehicle sensor 224 and / or the plurality of on-vehicle sensors 404). The friction estimator is further configured to provide a desired torque to the vehicle wheels such that the vehicle 110 can overcome the road segments of any one of the test lanes in which the vehicle wheels have a high probability of slipping. For example, the desired torque is any measure of the torque necessary to provide the vehicle wheels with sufficient power to alleviate any level of slipping associated with the vehicle 110.

[0060] Generate one or more driving profiles (e.g., operation 606) based on the extracted frequency characteristics and / or training of a deep learning model. The driving profile includes operating settings that facilitate specific speed, acceleration / braking, and / or steering capabilities of the vehicle when the vehicle 110 traverses a specific lane segment and / or test lane among multiple test lanes 300. When generating one or more driving profiles, store the driving profiles in the wireless transmission module 218 of the vehicle 110. When the vehicle 110 is grouped towards a waypoint associated with the start of a specific lane segment of the multiple test lanes 300, one or more vision sensors of the vehicle 110, in combination with the vehicle GNSS 228 and / or wheel speed sensor signals, detect changes in the lane segment. For example, the change can be a determination of distance (e.g., Δx) and / or a determination of time (e.g., Δt). Based on the change in the lane segment, the wireless transmission module 218 of the vehicle 110 automatically requests the vehicle controller 400 to follow the stored driving profile parameters from a pre-trained model specific to the specific lane segment among the multiple test lanes. Although the vehicle 110 is configured to utilize one or more driving profiles generated by a deep learning model, the vehicle 110 is also configured to utilize a pre-calibrated driving profile based on a specific lane segment of a specific test lane. For example, when the vehicle 110 can traverse a specific lane segment of a specific test lane at a fixed vehicle speed, a pre-calibrated driving profile is used. In either scenario, it should be understood that the switching of the driver profile (e.g., operation 608) is done automatically. However, it should be understood that the driving profile can also be switched manually.

[0061] Figure 7 is a flowchart showing an example method 700 for autonomous operation of a vehicle (e.g., vehicle 110) grouped along a test lane (e.g., among multiple test lanes 300). At operation 702, extract the frequency characteristics associated with the vehicle 110. For example, the frequency characteristics include one or more of the speed of the vehicle 110, the acceleration of the vehicle 110, the deceleration of the vehicle 110, the steering of the vehicle 110, or a combination thereof.

[0062] At operation 704, determine one or more driving profiles. For example, determine one or more driving profiles based on the frequency characteristics and / or a deep learning model. As another example, each of the one or more driving profiles uniquely corresponds to a respective lane segment among multiple lane segments. In an embodiment, generate one or more driving profiles based on the frequency characteristics.

[0063] At operation 706, cause vehicle 110 to select at least one of one or more driving profiles. For example, cause vehicle 110 to select at least one of one or more driving profiles based on at least one of a plurality of lane segments along a test lane. In an embodiment, determine the time it will take for vehicle 110 to reach the starting point associated with the lane segment of the plurality of lane segments. For example, determining the time it will take for vehicle 110 to reach the starting point associated with the lane segment of the plurality of lane segments is based on one or more vision sensors (e.g., vehicle sensor 224 and / or a plurality of on-vehicle sensors 404) and / or a positioning system (e.g., vehicle GNSS 228). As another example, the time is a function of the distance of vehicle 110 from the starting point of the lane segment and / or the speed at which the vehicle is traveling. As a further example, cause vehicle 110 to select at least one of one or more driving profiles based on the determined time.

[0064] At operation 708, control the movement of vehicle 110 along the test lane. For example, the movement of vehicle 110 along the test lane is controlled based on at least one of a plurality of lane segments and / or vehicle 110 selecting at least one of one or more driving profiles. In an embodiment, when vehicle 110 traverses the test lane, identify the sound level and / or vibration level. Compare the sound level and / or vibration level with a baseline sound level and / or baseline vibration level to determine whether the level exceeds a threshold. It should be understood that in cases where the sound level and / or vibration level exceeds the threshold, vehicle 110 may need to be repaired. In another embodiment, determine the friction level associated with the lane segment of the plurality of lane segments. For example, determine the friction level associated with the lane segment of the plurality of lane segments based on the traction between one or more wheels of vehicle 110 and one lane segment of the plurality of lane segments and / or one or more vision sensors. Further cause the vehicle to apply an estimated level of torque that will equalize the effect of the determined friction level. For example, also cause the vehicle to apply an estimated torque level that will equalize the effect of the determined friction level based on the determined friction level associated with the lane segment of the plurality of lane segments.

[0065] Accordingly, one or more examples provide the generation of one or more driving profiles based on a vehicle-based deep learning model that can be trained to ultimately control the movement of a vehicle along varying lane segments of a corresponding test lane.

[0066] Unless expressly indicated otherwise herein, all numerical values indicating mechanical / thermal properties, percentage compositions, dimensions, and / or tolerances or other characteristics should be understood to be modified by the word "about" or "approximately" when describing the scope of the present disclosure. This modification is desired for various reasons, including: industrial practice; material, manufacturing, and assembly tolerances; and test capabilities.

[0067] As used herein, the phrase "at least one of A, B, and C" shall be construed to represent the logic (A or B or C) using non-exclusive logic "or", and shall not be construed to mean "at least one of A, at least one of B, and at least one of C".

[0068] In this application, the terms "controller" and / or "module" may refer to, be part of, or include the following: application specific integrated circuit (ASIC); digital, analog, or mixed analog / digital discrete circuits; digital, analog, or mixed analog / digital integrated circuits; combinational logic circuits; field programmable gate array (FPGA); processor circuits (shared, dedicated, or grouped) that execute code; memory circuits (shared, dedicated, or grouped) that store code executed by the processor circuits; other suitable hardware components that provide the described functionality (e.g., operational amplifier circuit integrators as part of a heat flux data module); or a combination of some or all of the above, such as in a system-on-chip.

[0069] The term memory is a subset of the term computer-readable medium. The term computer-readable medium as used herein does not cover transient electrical or electromagnetic signals propagated through a medium (such as on a carrier wave); thus, the term computer-readable medium can be considered tangible and non-transitory. Non-limiting examples of non-transitory tangible computer-readable media are non-volatile memory circuits (such as flash memory circuits, erasable programmable read-only memory circuits, or mask read-only circuits), volatile memory circuits (such as static random access memory circuits or dynamic random access memory circuits), magnetic storage media (such as analog or digital magnetic tape or hard disk drives), and optical storage media (such as CDs, DVDs, or Blu-ray discs).

[0070] The devices and methods described in this application may be implemented in part or in whole by a special purpose computer created by configuring a general purpose computer to execute one or more specific functions embodied in a computer program. Functional blocks, flowchart components, and other elements described above serve as software specifications that can be translated into a computer program by routine work of a technician or programmer.

[0071] The description of the present disclosure is merely exemplary in nature, and thus, variations that do not depart from the essence of the present disclosure are intended to be within the scope of the present disclosure. Such variations should not be regarded as departing from the spirit and scope of the present disclosure.

[0072] According to the present invention, one or more non - transitory computer - readable media store processor - executable instructions that, when executed by at least one processor, cause the at least one processor to: extract frequency characteristics associated with a vehicle; determine one or more driving profiles based on the frequency characteristics and a deep - learning model; cause the vehicle to select at least one of the one or more driving profiles based on at least one of a plurality of roadway segments along a test lane; and control the movement of the vehicle along the test track based on at least one of the plurality of roadway segments and the vehicle's selection of at least one of the one or more driving profiles.

[0073] According to an embodiment, the processor - executable instructions that, when executed by at least one processor, cause the vehicle to select at least one of the one or more driving profiles further cause the at least one processor to: determine, based on one or more vision sensors and a positioning system, the time it will take for the vehicle to reach the starting point associated with the roadway segment of the plurality of roadway segments, where the time is a function of the distance of the vehicle from the starting point associated with the roadway segment and the speed at which the vehicle is traveling.

[0074] According to an embodiment, it further causes the at least one processor to: when the vehicle is moving along the test lane, identify a sound level or a vibration level that exceeds a threshold; and compare the sound level or the vibration level with a baseline sound level or a baseline vibration level.

[0075] According to an embodiment, it further causes the at least one processor to: determine a friction level associated with the roadway segment of the plurality of roadway segments based on the traction between one or more wheels of the vehicle and the roadway segment of the plurality of roadway segments and one or more vision sensors; and cause the vehicle to apply a torque at an estimated level that will equalize the effect of the determined friction level based on the determined friction level associated with the roadway segment of the plurality of roadway segments.

[0076] According to an embodiment, determining one or more driving profiles further includes: generating each of the one or more driving profiles based on the frequency characteristics, where the frequency characteristics include one or more of the vehicle's speed, the vehicle's acceleration, the vehicle's deceleration, the vehicle's steering, or a combination thereof.

[0077] According to an embodiment, each of the one or more driving profiles uniquely corresponds to a respective roadway segment of the plurality of roadway segments.

Claims

1. A method for controlling a vehicle operating autonomously along a test lane, the method comprising: Extracting frequency characteristics associated with the vehicle; Determining one or more driving profiles based on the frequency characteristics and a deep learning model; Causing the vehicle to select at least one of the one or more driving profiles based on at least one of a plurality of road segments along the test lane; And Controlling the movement of the vehicle along the test lane based on the at least one of the plurality of road segments and the vehicle's selection of the at least one of the one or more driving profiles.

2. The method according to claim 1, wherein causing the vehicle to select the at least one of the one or more driving profiles further comprises: Determining the time it will take for the vehicle to reach a starting point associated with a road segment of the plurality of road segments based on one or more vision sensors and a positioning system.

3. The method according to claim 2, wherein the time is a function of the distance of the vehicle from the starting point associated with the road segment and the speed at which the vehicle is traveling.

4. The method according to claim 2, wherein causing the vehicle to select the at least one of the one or more driving profiles is based on the determined time.

5. The method according to claim 1, further comprising: Identifying a sound level or a vibration level that exceeds a threshold when the vehicle is moving along the test lane; And Comparing the sound level or the vibration level with a baseline sound level or a baseline vibration level.

6. The method according to claim 1, further comprising: Determining a friction level associated with a road segment of the plurality of road segments based on the traction between one or more wheels of the vehicle and the road segment and one or more vision sensors; And Causing the vehicle to apply an estimated torque level that will equalize the effect of the determined friction level based on the determined friction level associated with the road segment of the plurality of road segments.

7. The method according to claim 1, wherein determining the one or more driving profiles comprises: Generating each of the one or more driving profiles based on the frequency characteristics, wherein the frequency characteristics include one or more of the speed of the vehicle, the acceleration of the vehicle, the deceleration of the vehicle, the steering of the vehicle, or a combination thereof.

8. The method according to claim 1, wherein each of the one or more driving profiles uniquely corresponds to a respective road segment of the plurality of road segments.

9. A platooning system for controlling a vehicle operating autonomously along a test lane, the platooning system comprising: A server configured to: Extract frequency characteristics associated with the vehicle, Determine one or more driving profiles based on the frequency characteristics and a deep learning model, Cause the vehicle to select at least one of the one or more driving profiles based on at least one of a plurality of road segments along the test lane, and Controlling the movement of the vehicle along the test lane by selecting at least one of the one or more driving profiles based on the at least one of the plurality of roadway segments and the vehicle; And The vehicle, which is configured to automatically select at least one of the one or more driving profiles.

10. The platooning system according to claim 9, wherein the server is configured to cause the vehicle to select at least one of the one or more driving profiles and is further configured to: Based on one or more vision sensors and a positioning system, determine the time it will take for the vehicle to reach a starting point associated with a roadway segment among the plurality of roadway segments, where the time is a function of the distance of the vehicle from the starting point associated with the roadway segment and the speed at which the vehicle is traveling.

11. The platooning system according to claim 10, wherein causing the vehicle to select at least one of the one or more driving profiles is based on the determined time.

12. The platooning system according to claim 9, wherein the server is further configured to: When the vehicle is moving along the test lane, identify a sound level or a vibration level that exceeds a threshold; and Compare the sound level or the vibration level with a baseline sound level or a baseline vibration level.

13. The platooning system according to claim 9, wherein the server is further configured to: Based on the traction force between one or more wheels of the vehicle and a roadway segment among the plurality of roadway segments and one or more vision sensors, determine the friction level associated with the roadway segment among the plurality of roadway segments; and Based on the determined friction level associated with the roadway segment among the plurality of roadway segments, cause the vehicle to apply an estimated level of torque that will equalize the effect of the determined friction level.

14. The platooning system according to claim 9, wherein the server is configured to determine the one or more driving profiles and is further configured to: Generate each of the one or more driving profiles based on the frequency characteristics, where the frequency characteristics include one or more of the speed of the vehicle, the acceleration of the vehicle, the deceleration of the vehicle, the steering of the vehicle, or a combination thereof.

15. The platooning system according to claim 9, wherein each of the one or more driving profiles uniquely corresponds to a respective roadway segment among the plurality of roadway segments.

Images