Method and system for quantifying and managing steering command response delays for autonomous vehicles

Abstract

A method and system quantifies and manages a steering command response delay for an autonomous vehicle. The system enables the method to determine a lag time between issuing a control command and an angle at which the command is implemented for a plurality of predetermined vehicle speeds. For each of a plurality of predetermined vehicle speeds, a predetermined number of lag times is averaged. The average lag time is weighted, wherein a more current lag time has a higher weight than a less current lag time. The average time lag is used to improve the response of the vehicle and detect health issues of the vehicle steering system.

Description

Technical Field

[0001] This disclosure generally relates to vehicles with autonomous driving systems, and more specifically, to methods and systems for quantifying and managing steering command response delays for autonomous vehicles. Background Technology

[0002] Modern vehicles incorporate intelligent systems (also known as smart systems), such as Advanced Driver Assistance Systems (ADAS) and / or Automated Driving Systems (ADS). These reside within the intelligent vehicle and are used to enhance or automate the functions of various vehicle systems. Intelligent systems have one or more control modules that communicate with vehicle sensors (such as external, internal, and status sensors) and various vehicle systems (such as steering, acceleration, braking, and safety systems). These control modules analyze the information collected by the vehicle sensors and send instructions (also known as commands) to the various vehicle systems to achieve partial or full driving automation. Vehicles capable of partial or full automated driving are generally referred to as autonomous vehicles.

[0003] Due to various factors, there may be an inherent delay between the time it takes for the control module to issue a command to the vehicle system and the time it takes for the vehicle system to complete its response to the command. While current intelligent systems have achieved their goals, a method and system are still needed to quantify and manage the inherent delays in command responses of vehicle systems (especially steering systems) used for autonomous driving. Summary of the Invention

[0004] According to several aspects, a method is provided for quantifying and managing steering command response latency for autonomous vehicles. The method includes: autonomously driving the vehicle along a vehicle path; determining, in real time, the average latency of the steering command response for each of a plurality of predetermined vehicle speeds; determining a change in the vehicle path; determining an instantaneous speed in response to the determined change in the vehicle path; selecting a predetermined vehicle speed having the same determined average latency as the instantaneous speed; issuing a steering command to resolve the determined change in the vehicle path, wherein the steering command includes compensation for the selected determined average latency; and executing the steering command to resolve the determined change in the vehicle path.

[0005] In another aspect of this disclosure, the method further includes determining the current delay between issuing a steering command to address a determined change in the vehicle path and executing the steering command; and incorporating the determined current delay and the determined instantaneous speed into the average delay of the steering command response for each of a plurality of predetermined vehicle speeds determined in real time.

[0006] In another aspect of this disclosure, the method further includes determining that one of the determined average delays of the steering command response exceeds a predetermined threshold; and initiating a vehicle health alert in response to the determined average delay of the steering command response exceeding the predetermined threshold.

[0007] In another aspect of this disclosure, the determined average delay is a weighted average of multiple delays determined over a period of time, wherein a more currently determined delay has a higher weight than a less currently determined delay.

[0008] In another aspect of this disclosure, as more current delays are determined, more than a predetermined number of less current delays are removed.

[0009] In another aspect of this disclosure, the predetermined speed is one of a predetermined discrete speed and a predetermined speed range.

[0010] In another aspect of this disclosure, the delay in steering command response is the amount of time elapsed between the control module issuing a control command for the steering system to achieve the requested steering angle and the steering system completing the execution of the requested steering angle.

[0011] In another aspect of this disclosure, the delay in steering command response is the amount of time elapsed between the control module issuing a control command for the steering system to achieve the requested steering angle and the steering system achieving the requested steering angle.

[0012] In another aspect of this disclosure, at least one of the delays in the turn command response is determined by utilizing a cross-correlation function.

[0013] According to several aspects, a method for quantifying and managing steering command response latency for an autonomous vehicle is provided. The method includes: a) automating the vehicle at a plurality of predetermined speeds; b) issuing a plurality of control commands to achieve a corresponding commanded steering angle at each of the plurality of predetermined speeds; c) implementing the corresponding commanded steering angle in response to the plurality of control commands; d) determining a lag time between each issuance of the plurality of control commands to achieve the corresponding commanded steering angle at each of the plurality of predetermined speeds and the achievement of the specific commanded steering angle; e) determining an average lag time at each of the plurality of predetermined speeds; and f) executing a control command to achieve the steering angle at one of the plurality of predetermined speeds, wherein the control command includes compensating for the determined average lag time corresponding to one of the plurality of predetermined speeds. Determining the lag time includes utilizing a cross-correlation function.

[0014] In another aspect of this disclosure, averaging the determined lag times of each of a plurality of predetermined speeds includes assigning weights, wherein the most currently determined lag time has a higher weight than the less currently determined lag time.

[0015] In another aspect of this disclosure, averaging the determined lag time for each of a plurality of predetermined speeds includes averaging a predetermined number of currently determined lag times.

[0016] In another aspect of this disclosure, a predetermined number of currently determined lag times are stored in a buffer, and excess determined lag times exceeding the predetermined number are removed from the buffer.

[0017] In another aspect of the invention, the method further includes: detecting a triggering condition; and initiating step be in response to the triggering condition.

[0018] According to several aspects, a computer-readable medium is provided, comprising instructions stored thereon for quantifying and managing steering command response latency of an autonomous vehicle. When executed by a processor, the instructions cause the processor to determine a triggering event; determine, in real time, the average latency of the steering command response for each of a plurality of predetermined vehicle speeds; determine a change in the vehicle path; determine an instantaneous speed in response to the determined change in the vehicle path; select a predetermined vehicle speed having the same determined average latency as the instantaneous speed; issue a steering command to address the determined change in the vehicle path, wherein the steering command includes compensation for the selected determined average latency; and execute the steering command to address the determined change in the vehicle path. The determined average latency is a weighted average of a plurality of latency determined over a period of time, wherein more currently determined lag times have higher weights than less currently determined lag times.

[0019] In another aspect of this disclosure, the computer-readable medium also includes instructions to cause the processor to determine that one of the average delays of the determined steering command responses exceeds a predetermined threshold; and to initiate a vehicle health alert in response to the determined average delay of the steering command response exceeding the predetermined threshold.

[0020] Further areas of application will become apparent from the description provided herein. It should be understood that these descriptions and specific examples are for illustrative purposes only and are not intended to limit the scope of this disclosure. Attached Figure Description

[0021] The accompanying drawings described herein are for illustrative purposes only and are not intended to limit the scope of this disclosure in any way.

[0022] Figure 1 This is a functional diagram of an intelligent vehicle having a system for quantifying and managing steering command response latency, according to an exemplary embodiment.

[0023] Figure 2 This is a plan view of an exemplary traffic scene according to an exemplary embodiment, wherein Figure 1 The intelligent vehicle shown is in autonomous driving mode.

[0024] Figure 3 This is a block diagram of a method for quantifying and managing steering command response latency according to an exemplary embodiment; and

[0025] Figure 4 An exemplary table showing the steering command delay related to a predetermined vehicle speed is provided. Detailed Implementation

[0026] The following description is merely exemplary in nature and is not intended to limit this disclosure, its application, or its uses. The illustrated embodiments are disclosed with reference to the accompanying drawings, in which the same reference numerals denote corresponding parts in multiple drawings. The drawings are not necessarily drawn to scale, and some features may be enlarged or minimized to show detail of particular features. The specific structural and functional details disclosed are not intended to be construed as limiting, but rather as a representative basis for teaching those skilled in the art how to practice the disclosed concepts.

[0027] As used herein, the terms module, component module, control module, or controller refer individually or in any combination of any hardware, software, firmware, electronic control components, processing logic, and / or processor devices, including but not limited to: application-specific integrated circuits (ASICs), electronic circuits, processors (shared, dedicated, or grouped) and memory that executes one or more software or firmware programs, combinational logic circuits, and / or other suitable components that provide the described functionality.

[0028] This document describes embodiments of the present disclosure based on functional and / or logical block components and various processing steps. It should be understood that such block components can be implemented by any number of hardware, software, and / or firmware components configured to perform specified functions. For example, embodiments of the present disclosure may employ various integrated circuit components, such as memory elements, digital signal processing elements, logic elements, lookup tables, etc., which can perform various functions under the control of one or more microprocessors or other control devices. Furthermore, those skilled in the art will understand that embodiments of the present disclosure can be practiced in conjunction with any number of systems, and the systems described herein are merely exemplary embodiments of the present disclosure.

[0029] The connecting lines shown in the various figures contained herein are intended to illustrate example functional relationships and / or physical couplings between various components. Conventional techniques may be used for signal processing, data transmission, signaling, control, and other functional aspects of the system (as well as the various operating components of the system) may not be described in detail herein. It should be noted that many alternative or additional functional relationships or physical connections may exist in the embodiments of this disclosure.

[0030] The following disclosure provides a method and system for quantifying and managing steering command response latency in autonomous vehicles, examples of which are described below. The method and system provide real-time calculation and classification of steering latency. Variations in steering latency can be caused by a variety of factors, such as the load on steering system components (e.g., steering rack), vehicle speed, cargo load distribution, and / or occupant position within the autonomous vehicle. Failure to effectively quantify steering latency can lead to undesirable vehicle vibrations. Effective quantification of steering latency enables path planning algorithms to accurately predict and manage the trajectory of autonomous vehicles, thereby reducing vehicle oscillations and improving vehicle dynamics and occupant comfort.

[0031] Figure 1 This is a functional diagram of an autonomous vehicle 100 (also referred to as vehicle 100) having an intelligent system 102, such as an Advanced Driver Assistance System (ADAS) and / or an Automated Driving System (ADS), capable of operating from Level 0 (no driving automation) to Level 5 (fully automated driving) according to SAE J3016 driving automation levels. Vehicle 100 generally comprises a body 106, front wheels 108, and rear wheels 110. The body 106 essentially surrounds the vehicle systems and components of vehicle 100. The front wheels 108 and rear wheels 110 are each rotatably coupled to the body 106 near a corresponding corner. Although the coupled vehicle 100 is shown as a passenger car, it is foreseeable that the coupled vehicle 100 could be another type of road vehicle, such as a pickup truck, sports coupe, sport utility vehicle (SUV), recreational vehicle (RV), or motorcycle.

[0032] As shown in the figure, vehicle 100 generally includes a propulsion system 120, a transmission system 122, a steering system 124, a braking system 126, a detection system 128, a vehicle communication system 130, and various vehicle actuators 132 for operating components of vehicle systems 120, 122, 124, 126, 128, and 130. Vehicle systems 120, 122, 124, 126, 128, and 130 and actuators 132 communicate with a vehicle control module 134, which is described in detail below. Vehicle 100 may also include a health manager 133 that communicates with the control module 134 to monitor the health status of vehicle systems 120, 122, 124, 126, 128, and 130 and notify the operator of any flagged systems via a human-machine interface (HMI) 103.

[0033] The autonomous vehicle 100 includes multiple sensors 140A-140C configured to collect information and generate sensor data indicative of the collected information. Sensors 140A-140C may be detachably or fixedly mounted on the vehicle 100 and may be arranged in various configurations to provide information to the vehicle control module 134. As a non-limiting example, the multiple sensors 140A-140C include, but are not limited to, a navigation sensor 140A, which includes a Global Navigation Satellite System (GNSS) transceiver or receiver; a vehicle status sensor 140B, including a yaw rate sensor, a speed sensor, and a wheel angle sensor 140B1; and external sensors 140C, including cameras, lidar, radar, and ultrasonic sensors. The wheel angle sensor 140B1 is configured to detect changes in the degree of the wheel 108 controlled by the steering system 124. When the vehicle 100 moves forward in a straight line, the wheel 108 is at 0 degrees and can change by up to + / - 90 degrees relative to 0 degrees.

[0034] Navigation sensor 140A is configured to detect the position and orientation of vehicle 100. External sensor 140C can have a sufficiently large detection field to detect and identify objects in front of, behind, and to the sides of autonomous vehicle 100. External sensor 140C can actively or passively scan obstacles (including other vehicles, buildings, pedestrians, etc.), roads, lane markings, signs, or signals in the vehicle environment.

[0035] The vehicle communication system 130 may include one or more communication transceivers 137 configured to wirelessly transmit information or data to and from other remote entities, such as other connected vehicles utilizing vehicle-to-vehicle (V2V) communication, infrastructure units (e.g., roadside units (RSUs) and mobile edge computing (MECs)) utilizing vehicle-to-infrastructure (V2I) communication, and / or cloud computing service providers 150 utilizing telecommunications. The communication transceivers 137 may be configured to communicate using the IEEE 802.11 standard or via a wireless local area network (WLAN) using cellular data communication. However, additional or alternative communication methods such as Dedicated Short Range Communication (DSRC) channels are also considered within the scope of this disclosure. A DSRC channel refers to a one-way or two-way short- to medium-range wireless communication channel designed specifically for automotive use, along with a set of corresponding protocols and standards.

[0036] The intelligent system 102 includes a vehicle control module 134 that communicates with one or more vehicle systems 120, 122, 124, 126, 128, 130, vehicle sensors 140A-140C, and vehicle actuators 132 via a controller area network (CAN) and / or Ethernet. The intelligent system 102 may also include a human-machine interface (HMI) 103 for communication with vehicle occupants (e.g., operators). In some embodiments that include communication with external sources via the vehicle communication system 130, the vehicle control module 134 may receive information (e.g., map data) from other intelligent vehicles, intelligent infrastructure (e.g., electronically communicated roads, traffic signals, or multi-story parking garages), or other relevant information sources. The collected data is processed by the vehicle control module 134 to generate control commands and send them to the various vehicle systems 120, 122, 124, 126, 128, 130, and actuators 132 for partial or fully autonomous operation of the vehicle 100. Control commands may include instructions to quantify and manage delays in command responses in certain vehicle systems (particularly steering system 124).

[0037] The control module 134 includes at least one processor 144 and a non-transitory computer-readable storage device or medium 146. The non-transitory computer-readable storage device or medium 146 includes machine-readable instructions that, when executed by the processor 144, cause the processor 144 to perform method 300 and control the vehicle 100 in a partially or fully automated driving mode. The processor 144 may be a custom or commercially available processor, a central processing unit (CPU), a graphics processing unit (GPU), an auxiliary processor among a plurality of processors associated with the control module 134, a semiconductor-based microprocessor (in the form of a microchip or chipset), a macroprocessor, a combination thereof, or generally a device for executing instructions. The vehicle computer-readable storage device or medium 146 may include volatile and non-volatile storage devices such as read-only memory (ROM), random access memory (RAM), and keep-alive memory (KAM). KAM is persistent or non-volatile memory that can be used to store various operational variables when the processor 144 is powered off. The vehicle computer-readable storage device or medium 146 of the control module 134 may be implemented using multiple storage devices, such as a programmable read-only memory (PROM), an electrical PROM (EPROM), an electrically erasable PROM (EEPROM), flash memory, or other electrical, magnetic, optical, or combined storage devices capable of storing data, some of which represents executable instructions used by the control module 134 when controlling the autonomous vehicle 100. The control module 134 may also include a buffer 147 configured for temporary data storage.

[0038] Figure 2This is a non-limiting example illustration of a traffic scenario where vehicle 100 autonomously drives on road 202, which includes various directional changes such as twists 204 and turns 206. Control module 134 receives data from various vehicle sensors 140A-140C and processes this data to generate control commands for the vehicle system to autonomously resolve directional changes defined by road 202. Control module 134 may also receive map data and other information from external sources to supplement the sensor data for generating control commands to resolve road 202.

[0039] Figure 3 This is a block diagram of a method (method 300) for quantifying and managing the response delay of steering commands for an autonomous vehicle 100. Delay refers to the lag time between the control module 134 issuing a control command (i.e., request) to the steering system to achieve a requested steering angle and the steering system completing the execution of the requested steering angle. The executed steering angle is also called the response steering angle, response angle, or command angle. Method 300 dynamically calculates the delay between the control command to achieve the steering angle and the completion of the execution of the requested steering angle in real time, where the real-time calculated delay is a function of the vehicle speed. The calculated delay can also be weighted to take into account the latest vehicle operating conditions. Method 300 provides real-time continuous updates to the vehicle control module 134 for more accurate path planning.

[0040] At box 302, vehicle 100 is operating autonomously on a route (also referred to as a vehicle path), defined by road 202 detected by vehicle sensors 140A-140C or by map data stored on the vehicle's computer-readable storage device 146. Autonomous driving means that vehicle 100 is operating in either partially or fully automated driving mode. Map data can be provided by a remote external source via communication system 130. The route can also be defined by an operator entering waypoints on HMI 103 (e.g., an interactive map displayed on a touchscreen monitor).

[0041] At block 304, in response to a control command issued by control module 134 to achieve the requested steering angle, control module 134 monitors vehicle systems 120, 122, 124, 126, 128, and 130 to detect triggering conditions, such as a steering angle change greater than a predetermined threshold (+ / - 45 degrees or greater, as a non-limiting example) within a recent time period (3 seconds, for example). When a triggering condition is detected, control module 134 records the instantaneous speed (v) of vehicle 200 and determines the delay (t) of steering system 124 in achieving the commanded steering angle. The control module calculates the cross-correlation between the command signal and the response signal and determines the delay (t) between the signals by finding the offset with the highest cross-correlation. The delay is determined for each instance where a triggering condition is detected. If no triggering condition is detected, such as when the vehicle is traveling in a straight line (e.g., the wheels are not turning), no delay is needed or cannot be determined because the steering angle response will always match the control command, which is a 0-degree change. Block 304 is repeated continuously. The currently determined minimum delay exceeding the predetermined threshold is ignored or deleted from memory.

[0042] At box 306, determined delays with the same instantaneous speed are categorized or grouped together to provide a correlation between vehicle speed and delay. In a non-limiting example, a predetermined number of determined delays (t0–t3) and their corresponding instantaneous vehicle speeds (v0–v3) are listed in Table 402. For each corresponding speed (v0–v3), the determined delays are categorized in order from the most currently determined delay (t0) to the least currently determined delay (t3). A predetermined number of recorded delays and corresponding speeds can be stored in memory buffer 147. Less currently determined delays exceeding the predetermined number can be deleted or ignored from memory buffer 147.

[0043] At box 308, for each corresponding velocity (v0-v) n The determined lag time (t0–t) n The average lag time (μ) can be calculated. j The weighted average is calculated as follows: the more current lag time (e.g., t0) is weighted more than the least current lag time (e.g., t). nThe lag time values ​​are given greater weight. In a non-limiting example, Table 402 shows a predetermined number of lag time values ​​from t0 to t3, and the selected vehicle speeds (v0-v3) are 0 km / h (kph), 10 kph, 30 kph, and 60 km / h, respectively. In the example shown, the selected vehicle speeds are discrete speeds. It should be understood that, as a non-limiting example, the selected vehicle speeds (v0-v3) can be, for example, speed ranges of 0 to 10 kph, 11-20 kph, 31-40 kph, and 41-60 kph, respectively. Referring to Table 404, as more currently determined delays are entered at t0, earlier determined delays (t1-t3) are moved one column until the least currently determined delay is removed from the table or memory buffer 147.

[0044] A defined delay (t0-t3) can be assigned a weighted value, such as Figure 4 As shown in Table 406, the most currently determined delay t0 is given a higher weight value, while the least currently determined delay is given a lower weight value. In a non-restrictive example, referring back to Table 402, t0 is given a weight value of 0.35, t1 is given a weight value of 0.30, t2 is given a weight value of 0.20, and t3 is given a weight value of 0.15. The resulting average weighted lag time (μ) corresponding to a vehicle speed of 10 kph is 74.3 milliseconds (ms).

[0045] At box 310, control module 134 determines the average weighted lag time (μ) corresponding to a specific vehicle speed. j Does the system consistently exceed a predetermined lag time threshold? If so, the control module 134 sends a flag to the vehicle health manager 133 and / or HMI 103 to warn the operator that vehicle performance may be degraded and may require maintenance.

[0046] At block 312, control module 134 continues to guide vehicle 100 on road 202 and issues control commands to various vehicle systems 120, 122, 124, 126, 128, and 130, including steering control commands for changes in the current direction of the steering system to perform steering angle changes to address the zigzag changes of road 202. To navigate these features, control module 134 determines the vehicle's current speed when issuing the steering control command and considers the calculated average weighted lag time (μ) corresponding to the vehicle's current speed when issuing the steering control command. The steering control commands are calibrated in real time based on the calculated average weighted lag time (μ) corresponding to the vehicle's instantaneous speed to ensure the vehicle travels along a predetermined route. The magnitude, rate, and timing of the control commands are calculated based on the average weighted lag time (μ) corresponding to a predetermined speed. For example, if the lag time is significantly higher than usual, control module 134 will compensate for the tag time by commanding the steering system to execute the steering control command earlier than it would normally execute. Conversely, if the lag is shorter than usual, control module 134 will compensate by delaying the steering control command.

[0047] The description in this disclosure is merely exemplary in nature, and changes that do not depart from the general meaning of this disclosure are intended to fall within its scope. These changes should not be considered as departing from the spirit and scope of this disclosure.

Claims

1. A method of quantifying and managing steering command response latency for an autonomous vehicle, comprising: autonomously driving a vehicle along a vehicle path; determining in real-time an average latency of a steering command response for each of a plurality of predetermined vehicle speeds; determining a change in the vehicle path; determining an instantaneous speed in response to the determined change in the vehicle path; selecting a determined average latency having a predetermined vehicle speed that is the same as the instantaneous speed; issuing a direction change steering command to address the determined change in the vehicle path, wherein the direction change steering command includes compensation for the selected determined average latency; and executing the direction change steering command to address the determined change in the vehicle path.

2. The method of claim 1, further comprising: determining a current latency between issuing the direction change steering command to address the determined change in the vehicle path and executing the direction change steering command; and incorporating the determined current latency and the determined instantaneous speed in determining in real-time the average latency of the steering command response for each of the plurality of predetermined vehicle speeds.

3. The method of claim 1, further comprising: determining that one of the determined average latencies of the steering command response exceeds a predetermined value threshold; and initiating a vehicle health alert in response to the determined average latency of the steering command response exceeding the predetermined value threshold. the determined average latency is a weighted average of a plurality of latencies determined over a period of time, wherein more recently determined latencies are included with higher weights than less recently determined latencies. more recently determined latencies are deleted above a predetermined number. the plurality of predetermined vehicle speeds are predetermined discrete speeds.

4. The method of claim 1, wherein, the plurality of predetermined vehicle speeds are predetermined speed ranges.

5. The method of claim 4, wherein, the latency of a steering command response is an amount of time elapsed between a control module issuing a control command for a steering system to achieve a requested steering angle and the steering system completing implementation of the requested steering angle.

6. The method of claim 1, wherein, the latency of a steering command response is an amount of time elapsed between a control module issuing a control command for a steering system to achieve a requested steering angle and the steering system achieving the requested steering angle.

7. The method of claim 1, wherein, at least one of the latencies of the steering command response is determined by utilizing a cross-correlation function.

8. The method of claim 1, wherein, ​ 9. The method of claim 1, wherein, ​ 10. The method of claim 1, wherein, ​

Images