Vehicle systems and related methods for autonomously increasing camera range

By adjusting the field of view and trajectory control of the sensing devices, autonomous vehicles can operate autonomously in complex environments, solving the problem of insufficient field of view and improving the driving experience.

CN117261934BActive Publication Date: 2026-11-17GM GLOBAL TECHNOLOGY OPERATIONS LLC
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
CN202211346366.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Priority Date
2022-06-15
Filing Date
2022-10-31
Publication Date
2026-11-17
Estimated Expiration
2042-10-31

AI Technical Summary

Technical Problem

When autonomous vehicles encounter complex environments such as traffic, road conditions, and obstacles, the insufficient forward field of vision of the sensing devices makes it difficult for the control system to operate autonomously, increasing the burden on the driver.

Method used

The controller on the vehicle determines the current and target values ​​of the field of view of the sensing device, adjusts the longitudinal and lateral trajectories based on the vehicle speed and distance to the CIP vehicle, adjusts the distance using back-off adjustment and lateral offset, and autonomously operates the vehicle actuators to increase the field of view.

Benefits of technology

It improves the ability of autonomous vehicles to operate in complex environments, reduces the need for driver intervention, and enhances the autonomous driving performance of vehicles.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117261934B_ABST
    Figure CN117261934B_ABST
Patent Text Reader

Abstract

Vehicles and related systems and methods for controlling a vehicle in an autonomous operating mode are provided. One method includes determining a current value of a field of view associated with sensing devices on the vehicle, determining a target value of the field of view based at least in part on the vehicle's speed, and in response to determining that the current value is less than the target value, determining a backoff adjustment distance based at least in part on the difference between the target value of the field of view and an estimated distance to the nearest (CIP) vehicle in the path ahead of the vehicle in the current driving lane, determining a longitudinal trajectory of the vehicle based at least in part on the backoff adjustment distance, and autonomously operating one or more actuators on the vehicle according to the longitudinal trajectory.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] This technical field generally relates to vehicle systems, and more particularly to the autonomous operation of vehicles to increase the forward field of view of sensing devices such as cameras or image sensors. Background Technology

[0002] An autonomous vehicle is a vehicle capable of sensing its environment and navigating with little or no user input. Autonomous vehicles use sensing devices such as radar, lidar, and image sensors to perceive their environment. Autonomous vehicle systems also use information from Global Positioning System (GPS) technology, navigation systems, vehicle-to-vehicle communication, vehicle-to-infrastructure technology, and / or drive-by-wire systems to navigate the vehicle.

[0003] Vehicle automation has been categorized into numerical levels ranging from zero to five, where zero corresponds to no automation and complete human control, and five corresponds to full automation without human control. Various automated driver assistance systems (such as cruise control, adaptive cruise control, and parking assistance systems) correspond to lower levels of automation, while truly "driverless" vehicles correspond to higher levels of automation.

[0004] Because of the numerous and varied variables present in real-world environments, autonomous vehicle control systems may encounter situations or scenarios where assistance is desired. For example, they may encounter traffic, road conditions, and other obstacles or scenarios that hinder the control system's ability to arrive at a solution regarding how to autonomously operate the vehicle within the context of lane boundaries or other restrictions or constraints for which it seeks compliance. In lower levels of automation systems (e.g., Level 3 or lower), such scenarios may require the driver or other vehicle occupants to manually control or operate the vehicle in some situations, placing a burden on the driver and somewhat contrary to the intent of automation. Therefore, it is desirable to provide vehicle control systems and methods capable of autonomously resolving scenarios where a reduced forward field of view may hinder the achievement of a satisfactory solution regarding how to autonomously operate the vehicle. Other desirable features and characteristics of the invention will become apparent from the following detailed description and appended claims, taking into account the accompanying drawings and the foregoing technical and background information. Summary of the Invention

[0005] Devices for a vehicle and related methods for controlling the vehicle in an autonomous operating mode are provided. One method for controlling a vehicle in an autonomous operating mode includes: determining a current value of a field of view associated with sensing devices on the vehicle by a controller associated with the vehicle; determining a target value of the field of view associated with the sensing devices by the controller based at least in part on the vehicle's speed; and in response to determining that the current value is less than the target value, determining a backoff adjustment distance by the controller based at least in part on the difference between the target value of the field of view and an estimated distance to the nearest (CIP) vehicle in the path ahead of the vehicle in the current driving lane; determining a longitudinal trajectory of the vehicle by the controller based at least in part on the backoff adjustment distance to increase the estimated distance to the CIP vehicle; and autonomously operating one or more actuators on the vehicle according to the longitudinal trajectory.

[0006] In one aspect, determining the target value includes obtaining the target value from a lookup table maintained in a data storage associated with the vehicle using the vehicle speed. In another aspect, the method includes a controller determining when a second difference between the current speed of the vehicle associated with the target value and the initial speed of the vehicle is greater than a threshold, and in response to determining that the second difference is greater than the threshold, the controller determines an updated target value for the field of view associated with the sensing device based at least in part on the current speed of the vehicle, determines an updated backoff adjustment distance based at least in part on the updated target value and the current estimated distance between the CIP vehicle and the vehicle, determines an updated longitudinal trajectory of the vehicle based at least in part on the updated backoff adjustment distance, and autonomously operates one or more actuators on the vehicle according to the updated longitudinal trajectory. In yet another aspect, the method includes gradually decreasing the backoff adjustment distance when the CIP vehicle is no longer in front of a vehicle in the current driving lane. In yet another aspect, the method includes gradually decreasing the backoff adjustment distance when the number of consecutive overtaking events exceeds a threshold. On the other hand, the method includes, when the width associated with the CIP vehicle is greater than a threshold, in response to determining that the current value is less than a target value, the controller determines a lateral offset adjustment distance, the controller determines the lateral trajectory of the vehicle based at least in part on the lateral offset adjustment distance to offset the vehicle relative to the centerline associated with the current driving lane, and the controller autonomously operates one or more actuators on the vehicle according to the lateral trajectory, while simultaneously operating one or more actuators on the vehicle according to the longitudinal trajectory.

[0007] In one aspect, determining the current value of the field of view includes a rolling average calculated by the controller of a first estimated visible length associated with the left boundary of the current driving lane and a second estimated visible length associated with the right boundary of the current driving lane over a previous time interval. Another aspect of the method also includes the controller determining the first estimated visible length associated with the left boundary of the current driving lane and the second estimated visible length associated with the right boundary of the current driving lane based at least in part on one or more images or sensor data captured by the sensing device.

[0008] An apparatus for a vehicle is provided, comprising a data storage for maintaining a lookup table, one or more sensors on the vehicle, one or more actuators on the vehicle, and a controller that, via a processor, determines a current value of a field of view associated with one of the sensors, determines a target value of the field of view associated with the sensors using the lookup table based at least in part on the vehicle's speed, determines a backoff adjustment distance based at least in part on the difference between the target value of the field of view and an estimated distance to the nearest (CIP) vehicle in the path ahead of the vehicle in the current driving lane when the current value is less than the target value, determines a backoff adjustment distance based at least in part on the difference between the target value of the field of view and an estimated distance to the nearest (CIP) vehicle in the path ahead of the vehicle in the current driving lane, determines a longitudinal trajectory of the vehicle based at least in part on the backoff adjustment distance to increase the estimated distance to the CIP vehicle, and autonomously operates one or more actuators on the vehicle according to the longitudinal trajectory. In one aspect, the sensors are cameras.

[0009] On the other hand, the controller determines the current value of the field of view by calculating a rolling average of a first estimated visible length associated with the left boundary of the current driving lane and a second estimated visible length associated with the right boundary of the current driving lane over a previous time interval. On another hand, the sensing device is a camera, and the controller determines the first estimated visible length associated with the left boundary of the current driving lane and the second estimated visible length associated with the right boundary of the current driving lane based at least in part on one or more images captured by the camera. On yet another hand, the controller gradually decreases the back-off adjustment distance when the CIP vehicle is no longer in front of the vehicle in the current driving lane. On yet another hand, the controller gradually decreases the back-off adjustment distance when the number of consecutive overtaking events exceeds a threshold. On yet another hand, when the width associated with the CIP vehicle exceeds a threshold, in response to determining that the current value is less than a target value, the controller determines a lateral offset adjustment distance, determines the lateral trajectory of the vehicle based at least in part on the lateral offset adjustment distance to offset the vehicle relative to the centerline associated with the current driving lane, and autonomously operates one or more actuators on the vehicle according to the lateral trajectory, while simultaneously operating one or more actuators on the vehicle according to the longitudinal trajectory.

[0010] On the other hand, there is provided an apparatus for storing on a non-transitory computer-readable medium executable instructions that, when executed by a processor, cause the processor to determine a current value of a field of view associated with a sensing device on a vehicle, determine a target value of the field of view associated with the sensing device based at least in part on the speed of the vehicle, determine a backoff adjustment distance based at least in part on the difference between the target value of the field of view and an estimated distance to the nearest (CIP) vehicle in the path ahead of the vehicle in the current driving lane, determine a longitudinal trajectory of the vehicle based at least in part on the backoff adjustment distance to increase the estimated distance to the CIP vehicle, and autonomously operate one or more actuators on the vehicle according to the longitudinal trajectory.

[0011] In one aspect, when the width associated with the CIP vehicle is greater than a threshold, executable instructions cause the processor to determine a lateral offset adjustment distance in response to determining that the current value is less than a target value, determine the lateral trajectory of the vehicle based at least in part on the lateral offset adjustment distance to offset the vehicle relative to the centerline associated with the current driving lane, and autonomously operate one or more actuators on the vehicle according to the lateral trajectory, while simultaneously operating one or more actuators on the vehicle according to the longitudinal trajectory. In another aspect, executable instructions cause the processor to determine a current value of the field of view by calculating a rolling average of a first estimated visible length associated with the left boundary of the current driving lane and a second estimated visible length associated with the right boundary of the current driving lane over a previous time interval. In yet another aspect, executable instructions cause the processor to determine the first estimated visible length associated with the left boundary of the current driving lane and the second estimated visible length associated with the right boundary of the current driving lane based at least in part on one or more images or sensor data captured by a sensing device. In yet another aspect, the sensing device is a camera on the vehicle, and executable instructions cause the processor to determine the first and second estimated visible lengths based at least in part on one or more images captured by the camera on the vehicle.

[0012] This invention provides the following technical solutions: 1. A method for controlling a vehicle in an autonomous operation mode, the method comprising: The current value of the field of view associated with the sensing devices on the vehicle is determined by the controller associated with the vehicle; The controller determines a target value for the field of view associated with the sensing device based at least in part on the vehicle's speed; and In response to determining that the current value is less than the target value: The controller determines the back-off adjustment distance based at least in part on the difference between the target value of the field of view and the estimated distance to the nearest (CIP) vehicle in the path ahead of the vehicle in the current driving lane; The controller determines the vehicle's longitudinal trajectory based at least in part on the back-off adjustment distance to increase the estimated distance to the CIP vehicle; and The controller autonomously operates one or more actuators on the vehicle according to the longitudinal trajectory.

[0013] According to the method of technical solution 1, determining the target value includes obtaining the target value from a lookup table maintained in a data storage associated with the vehicle using the vehicle's speed.

[0014] The method according to technical solution 1 further includes: The controller determines when a second difference between the vehicle's current speed and its initial speed, associated with the target value, exceeds a threshold; and In response to determining that the second difference is greater than the threshold: The controller determines an updated target value for the field of view associated with the sensing device, based at least in part on the vehicle's current speed; The updated backoff adjustment distance is determined by the controller based at least in part on the updated target value and the current estimated distance between the CIP vehicle and the vehicle. The updated longitudinal trajectory of the vehicle is determined by the controller based at least in part on the updated back-off adjustment distance; and The controller autonomously operates one or more actuators on the vehicle based on the updated longitudinal trajectory.

[0015] The method according to technical solution 1 further includes gradually reducing the back-off adjustment distance when the CIP vehicle is no longer in front of the vehicle in the current driving lane.

[0016] According to the method described in technical solution 1, it further includes gradually reducing the back-off adjustment distance when the number of consecutive overtaking events exceeds a threshold.

[0017] The method according to technical solution 1 further includes: When the width associated with the CIP vehicle is greater than a threshold, the controller determines the lateral offset adjustment distance in response to determining that the current value is less than the target value; The controller determines the vehicle's lateral trajectory, at least in part, based on the lateral offset adjustment distance, to offset the vehicle relative to the centerline associated with the current driving lane; and The controller autonomously operates one or more actuators on the vehicle according to a lateral trajectory, and simultaneously operates the one or more actuators on the vehicle according to a longitudinal trajectory.

[0018] According to the method of technical solution 1, determining the current value of the field of view includes calculating by the controller a rolling average of a first estimated visible length associated with the left boundary of the current driving lane and a second estimated visible length associated with the right boundary of the current driving lane over a previous time interval.

[0019] The method according to technical solution 7 further includes determining, at least in part, a first estimated visible length associated with the left boundary of the current driving lane and a second estimated visible length associated with the right boundary of the current driving lane by a controller based on one or more images or sensor data captured by the sensing device.

[0020] A vehicle comprising: Maintain the data storage for the lookup table; One or more vehicle-mounted sensing devices; One or more actuators on the vehicle; and The controller, through a processor, determines a current value of the field of view associated with one of the one or more sensing devices, determines a target value of the field of view associated with the sensing devices using a lookup table based at least in part on the vehicle's speed, determines a backoff adjustment distance based at least in part on the difference between the target value of the field of view and the estimated distance to the nearest (CIP) vehicle in the path ahead of the vehicle in the current driving lane when the current value is less than the target value, determines the longitudinal trajectory of the vehicle based at least in part on the backoff adjustment distance to increase the estimated distance to the CIP vehicle, and autonomously operates one or more actuators on the vehicle according to the longitudinal trajectory.

[0021] According to the vehicle described in technical solution 9, the sensing device includes a camera.

[0022] According to the vehicle of technical solution 9, the controller determines the current value of the field of view by calculating a rolling average of a first estimated visible length associated with the left boundary of the current driving lane and a second estimated visible length associated with the right boundary of the current driving lane over a previous time interval.

[0023] According to the vehicle described in technical solution 11, wherein: The sensing device includes a camera; and The controller determines, at least in part, a first estimated visible length associated with the left boundary of the current driving lane and a second estimated visible length associated with the right boundary of the current driving lane based on one or more images captured by the camera.

[0024] According to the vehicle described in technical solution 9, when the CIP vehicle is no longer in front of a vehicle in the current driving lane, the controller gradually reduces the back-off adjustment distance.

[0025] According to the vehicle described in technical solution 9, when the number of consecutive overtaking events exceeds a threshold, the controller gradually reduces the back-off adjustment distance.

[0026] According to the vehicle of technical solution 9, when the width associated with the CIP vehicle is greater than a threshold, in response to determining that the current value is less than a target value, the controller determines a lateral offset adjustment distance, determines the lateral trajectory of the vehicle at least in part based on the lateral offset adjustment distance, offsets the vehicle relative to the centerline associated with the current driving lane, and autonomously operates one or more actuators on the vehicle according to the lateral trajectory, while simultaneously operating one or more actuators on the vehicle according to the longitudinal trajectory.

[0027] A non-transitory computer-readable medium comprising executable instructions that, when executed by a processor, cause the processor to: Determine the current value of the field of view associated with the sensors on the vehicle; The target value of the field of view associated with the sensing device is determined at least in part based on the vehicle's speed; and In response to determining that the current value is less than the target value: The back-off adjustment distance is determined at least in part based on the difference between the target value of the field of view and the estimated distance to the nearest (CIP) vehicle in the path ahead of the vehicle in the current driving lane; The longitudinal trajectory of the vehicle is determined at least in part based on the back-off adjustment distance to increase the estimated distance to the CIP vehicle; and The vehicle autonomously operates one or more actuators according to the longitudinal trajectory.

[0028] According to the non-transitory computer-readable medium of technical solution 16, the executable instructions cause the processor to: When the width associated with the CIP vehicle is greater than a threshold, in response to determining that the current value is less than the target value, a lateral offset adjustment distance is determined; The lateral trajectory of the vehicle is determined at least in part based on the lateral offset adjustment distance to offset the vehicle relative to the centerline associated with the current driving lane; and The vehicle autonomously operates one or more actuators according to the lateral trajectory, and simultaneously operates one or more actuators according to the longitudinal trajectory.

[0029] According to the non-transitory computer-readable medium of technical solution 16, the executable instructions cause the processor to determine the current value of the field of view by calculating a rolling average of a first estimated visible length associated with the left boundary of the current driving lane and a second estimated visible length associated with the right boundary of the current driving lane over a previous time interval.

[0030] According to the non-transitory computer-readable medium of technical solution 18, the executable instructions cause the processor to determine, at least in part, a first estimated visible length associated with the left boundary of the current driving lane and a second estimated visible length associated with the right boundary of the current driving lane based on one or more image or sensor data captured by the sensing device.

[0031] According to the non-transitory computer-readable medium of technical solution 19, the sensing device includes a camera on a vehicle, and the executable instructions cause the processor to determine a first estimated visual length and a second estimated visual length based at least in part on one or more images captured by the camera on the vehicle. Attached Figure Description

[0032] Exemplary aspects will now be described in conjunction with the following figures, wherein like reference numerals denote like elements, and wherein: Figure 1 This is a block diagram illustrating an autonomous vehicle control system for a vehicle according to various embodiments; Figure 2 It is suitable for various implementation methods. Figure 1 A block diagram of the autonomous driving system (ADS) implemented by the autonomous vehicle control system of the vehicle; Figure 3 Depicting one or more aspects suitable for use by, according to the description herein. Figure 1 In autonomous vehicle control systems Figure 2 A flowchart of the scope control process implemented by ADS; Figure 4 Depicting one or more aspects suitable for use by, according to the description herein. Figure 2 ADS combination Figure 3 The flowchart of the rollback determination process implemented in the scope control process; and Figure 5 Depicting one or more aspects suitable for use by, according to the description herein. Figure 2 ADS combination Figure 3 The flowchart of the lateral adjustment process implemented in the range control process; and Figure 6-7 Depicting one or more aspects according to the description in this article Figure 3The sequence of different states in an exemplary scenario of an example implementation of the range control process. Detailed Implementation

[0033] The following detailed description is merely exemplary in nature and is not intended to limit application and use. Furthermore, it is not intended to be bound by any express or implied theory set forth in the foregoing introduction, summary of the invention, or the following detailed description. As used herein, the term "module" refers individually or in any combination of 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 memories executing one or more software or firmware programs, combinational logic circuits, and / or other suitable components providing the said functionality.

[0034] Now for reference Figure 1 According to one or more embodiments, the illustrated autonomous vehicle control system 100 determines a plan for autonomously operating the vehicle 10 along a route in a manner that takes into account objects or obstacles detected by the onboard sensors 28, 40, as described in more detail below. In this regard, the control modules on the vehicle 10 calibrate different types of onboard sensors 28, 40 relative to each other and / or the vehicle 10, thereby allowing data from those different types of onboard sensors 28, 40 to be spatially correlated or otherwise correlated with each other based on calibrations used for object detection, object classification, and the final autonomous operation of the vehicle 10.

[0035] like Figure 1 The vehicle 10 depicted typically includes a chassis, a body 14, and front wheels 16 and rear wheels 18, which are rotatably connected to the chassis near corresponding corners of the body 14. The body 14 is mounted on the chassis and substantially surrounds the components of the vehicle 10, and the body 14 and the chassis can together form a frame.

[0036] In an exemplary embodiment, vehicle 10 is an autonomous vehicle or otherwise configured to support one or more autonomous operating modes, and control system 100 is integrated into vehicle 10 (hereinafter referred to as vehicle 10). Vehicle 10 is depicted as a passenger vehicle in the illustrated embodiment; however, it should be understood that any other means of transportation, including motorcycles, trucks, SUVs, RVs, boats, aircraft, etc., may also be used. In an exemplary embodiment, vehicle 10 is a so-called Level 2 automation system. Level 2 system means "partial driving automation," referring to an automated driving system that controls specific performance of steering, acceleration, and braking in specific scenarios, while the driver remains alert and actively supervises the automated driving system and can provide driver support to control the primary driving tasks.

[0037] As shown in the figure, vehicle 10 typically includes a propulsion system 20, a transmission system 22, a steering system 24, a braking system 26, a sensor system 28, an actuator system 30, at least one data storage device 32, at least one controller 34, and a communication system 36. In various embodiments, the propulsion system 20 may include an internal combustion engine, an electric motor such as a traction motor, and / or a fuel cell propulsion system. The transmission system 22 is configured to transmit power from the propulsion system 20 to the wheels 16, 18 according to a selectable speed ratio. According to various embodiments, the transmission system 22 may include a stepped automatic transmission, a continuously variable transmission (CVT), or other suitable transmission. The braking system 26 is configured to provide braking torque to the wheels 16, 18. In various embodiments, the braking system 26 may include friction brakes, brake-by-wire brakes, regenerative braking systems such as electric motors, and / or other suitable braking systems. The steering system 24 affects the position of the wheels 16, 18. Although depicted as including a steering wheel for illustrative purposes, in some embodiments contemplated within the scope of this disclosure, the steering system 24 may not include a steering wheel.

[0038] Sensor system 28 includes one or more sensing devices 40a-40n that sense observable conditions of the external and / or internal environment of vehicle 10. Sensing devices 40a-40n may include, but are not limited to, radar, lidar, GPS, optical cameras, thermal cameras, ultrasonic sensors, and / or other sensors. Actuator system 30 includes one or more actuator devices 42a-42n that control one or more vehicle features, such as, but not limited to, propulsion system 20, transmission system 22, steering system 24, and braking system 26. In various embodiments, vehicle features may further include internal and / or external vehicle features, such as, but not limited to, doors, trunk, and cabin features, such as air, music, lighting, etc. (not numbered).

[0039] Data storage device 32 stores data for automatically controlling vehicle 10. In various embodiments, data storage device 32 stores a defined map of the navigable environment. In various embodiments, the defined map may be predefined by and obtained from a remote system. For example, the defined map may be assembled by a remote system and transmitted to vehicle 10 (wirelessly and / or via wired means) and stored in data storage device 32. As will be understood, data storage device 32 may be part of controller 34, separate from controller 34, or part of controller 34 and a separate system.

[0040] The controller 34 includes at least one processor 44 and a computer-readable storage device or medium 46. The processor 44 can be any custom or commercially available processor, central processing unit (CPU), graphics processing unit (GPU), auxiliary processor among several processors associated with the controller 34, semiconductor-based microprocessor (in the form of a microchip or chipset), macroprocessor, any combination thereof, or any means generally used for executing instructions. The computer-readable storage device or medium 46 can include volatile and non-volatile storage, such as read-only memory (ROM), random access memory (RAM), and keep-alive memory (KAM). KAM is a permanent or non-volatile memory that can be used to store various operational variables when the processor 44 is powered off. The computer-readable storage device or medium 46 can be implemented using any of a variety of known storage devices, such as PROM (programmable read-only memory), EPROM (electrical PROM), EEPROM (electrically erasable PROM), flash memory, or any other electrical, magnetic, optical, or combined memory device capable of storing data, some of which represent executable instructions used by the controller 34 when controlling the vehicle 10.

[0041] The instructions may include one or more separate programs, each including an ordered list of executable instructions for implementing logical functions. When executed by processor 44, the instructions receive and process signals from sensor system 28, execute logic, calculations, methods, and / or algorithms for automatically controlling components of vehicle 10, and generate control signals for actuator system 30 to automatically control components of vehicle 10 based on logic, calculations, methods, and / or algorithms. Although in Figure 1 Only one controller 34 is shown, but embodiments of vehicle 10 may include any number of controllers 34 that communicate via any suitable communication medium or combination of communication media and cooperate to process sensor signals, perform logic, calculations, methods and / or algorithms, and generate control signals to automatically control the features of vehicle 10.

[0042] In various embodiments, one or more instructions of controller 34 are contained in control system 100 (e.g., in data storage element 46) and, when executed by processor 44, cause processor 44 to obtain data captured or generated from imaging and ranging device 40 and use the captured environmental data to determine commands for autonomous operation of vehicle 10, as described in more detail below. In one or more exemplary embodiments, data storage element 46 maintains a lookup table of lateral planning information, which can be used to determine corresponding lateral reference trajectories for lateral maneuvers into adjacent lanes. When a normal vehicle guidance or control scheme supported by processor 44 encounters a time-sensitive lateral maneuver deadline or other time constraints, processor 44 uses or otherwise references the lateral planning information and the resulting reference lateral trajectory to determine commands for autonomous operation of vehicle 10 to avoid having to solve for the vehicle path of the command within a limited time period.

[0043] Still referencing Figure 1 In an exemplary embodiment, communication system 36 is configured to wirelessly transmit information to and from other entities 48 via a communication network, such as, but not limited to, other vehicles (“V2V” communication), infrastructure (“V2I” communication), remote systems, and / or personal devices. In an exemplary embodiment, communication system 36 is a wireless communication system 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 specifically designed for automotive applications, and a corresponding set of protocols and standards.

[0044] The communication network utilized by communication system 36 may include a wireless carrier system, such as a cellular telephone system comprising multiple cell towers (not shown), one or more mobile switching centers (MSCs) (not shown), and any other networking components required to connect the wireless carrier system to the terrestrial communication system. The wireless carrier system may implement any suitable communication technology, including, for example, digital technologies such as CDMA (e.g., CDMA2000), LTE (e.g., 4G LTE or 5G LTE), GSM / GPRS, or other current or emerging wireless technologies. Additionally or alternatively, a second wireless carrier system in the form of a satellite communication system may be used to provide one-way or two-way communication using one or more communication satellites (not shown) and uplink transmitting stations (not shown), including but not limited to satellite radio services, satellite telephone services, and / or similar services. Some implementations may utilize terrestrial communication systems, such as conventional terrestrial-based telecommunications networks, including the Public Switched Telephone Network (PSTN) for providing hard-wired telephone, packet-switched data communications, and Internet infrastructure. One or more segments of a terrestrial communication system may be implemented using standard wired networks, fiber optic or other optical networks, cable networks, power lines (such as wireless local area networks (WLANs) or other wireless networks that provide broadband wireless access (BWA), or any combination thereof.

[0045] Now for reference Figure 2 According to various embodiments, the controller 34 implements an autonomous driving system (ADS) 70. That is, suitable software and / or hardware components of the controller 34 (e.g., processor 44 and computer-readable storage device 46) are used to provide an autonomous driving system 70 for use in conjunction with the vehicle 10, for example, to automatically control various actuators 30, and thereby control the vehicle's acceleration, steering and braking respectively, without human intervention.

[0046] In various implementations, the instructions of the autonomous driving system 70 can be organized by function or system. For example, such as Figure 2 As shown, the autonomous driving system 70 may include a sensor fusion system 74, a positioning system 76, a guidance system 78, and a vehicle control system 80. As will be appreciated, in various embodiments, instructions may be organized into any number of systems (e.g., combined, further divided, etc.), as this disclosure is not limited to the present example.

[0047] In various embodiments, sensor fusion system 74 synthesizes and processes sensor data and predicts the presence, location, classification, and / or path of objects and features in the environment of vehicle 10. In various embodiments, sensor fusion system 74 may combine information from multiple sensors, including but not limited to cameras, lidar, radar, and / or any number of other types of sensors. In one or more exemplary embodiments described herein, sensor fusion system 74 associates image data with lidar point cloud data, vehicle reference coordinates, or some other reference coordinate system using calibration transformation parameter values ​​associated with a pair of corresponding cameras and reference coordinate systems to associate lidar points with pixel locations, assign depth to image data, identify objects in one or more image and lidar data sets, or otherwise synthesize associated image and lidar data. In other words, sensor outputs from sensor fusion system 74 provided to vehicle control system 80 (e.g., labels of detected objects and / or their locations relative to vehicle 10) reflect, or are otherwise influenced by, calibrations and associations between camera images, lidar point cloud data, etc.

[0048] The positioning system 76 processes sensor data and other data to determine the vehicle's position relative to its environment (e.g., local position relative to a map, precise position relative to a road lane, vehicle direction of travel, speed, etc.). Given the current sensor data and vehicle attitude, the guidance system 78 processes the sensor data and other data to determine the path that the vehicle 10 should follow. The vehicle control system 80 then generates control signals for controlling the vehicle 10 based on the determined path. In various embodiments, the controller 34 implements machine learning techniques to assist its functions, such as feature detection / classification, obstacle mitigation, route traversal, mapping, sensor integration, and ground condition determination.

[0049] In one or more embodiments, the guidance system 78 includes a motion planning module that generates motion plans for controlling the vehicle as it traverses a route. The motion planning module includes a longitudinal solver module that generates a longitudinal motion planning output for controlling the vehicle's movement along the route in its general direction of travel, for example, by accelerating or decelerating the vehicle at one or more points along the route in the future to maintain a desired speed or rate. The motion planning module also includes a lateral solver module that generates a lateral motion planning output for controlling the vehicle's lateral movement along the route to change the general direction of travel, for example, by turning the vehicle at one or more points along the route in the future (e.g., keeping the vehicle centered in a lane, changing lanes, etc.). The longitudinal and lateral planning outputs correspond to command (or planned) path outputs provided to the vehicle control system 80 for controlling the vehicle actuators 30 to achieve movement of the vehicle 10 along the routes corresponding to the longitudinal and lateral plans.

[0050] During normal operation, the longitudinal solver module attempts to optimize the vehicle speed (or rate) in the direction of travel, the vehicle acceleration in the direction of travel, and the derivative of the vehicle acceleration in the direction of travel (hereinafter referred to as the vehicle's longitudinal jerk), while the lateral solver module attempts to optimize one or more of the steering angle, the rate of change of the steering angle, and the acceleration or second derivative of the steering angle (hereinafter referred to as the vehicle's lateral jerk). At this point, the steering angle may be related to the curvature of the path or route, and any one of the steering angle, the rate of change of the steering angle, and the acceleration or second derivative of the steering angle can be optimized individually or in combination by the lateral solver module.

[0051] In an exemplary embodiment, the longitudinal solver module receives or otherwise obtains the vehicle's current or instantaneous attitude, including the vehicle's current position or location, current orientation, current speed or rate, and current acceleration. Using the vehicle's current position or location, the longitudinal solver module also retrieves or otherwise obtains route information, including information about the route the vehicle is traveling along given its current attitude and some additional buffer distance or time period (e.g., the next 12 seconds), such as, for example, current and future road slope or spacing, current and future road curvature, current and future lane information (e.g., lane type, boundaries, or other constraints or limitations), and other constraints or limitations associated with the road (e.g., minimum and maximum speed limits, height or weight limits, etc.). The route information can be obtained from, for example, onboard data storage element 32, an online database, or other entities. In one or more embodiments, lateral route information may include a lateral path planning command output by the lateral solver module, wherein the longitudinal and lateral solver modules iteratively derive the optimal driving plan along the route.

[0052] The longitudinal solver module also receives or otherwise obtains current obstacle data relating to the route and the vehicle's current attitude, which may include, for example, the location or position, size, orientation or direction of travel, velocity, acceleration, and other characteristics of objects or obstacles near the vehicle or in the future route. The longitudinal solver module also receives or otherwise obtains longitudinal vehicle constraint data that characterizes or otherwise defines the kinematic or physical capabilities of the vehicle's longitudinal motion, such as, for example, maximum acceleration and maximum longitudinal jerk, maximum deceleration, etc. The longitudinal vehicle constraint data may be vehicle-specific and may be obtained from onboard data storage element 32 or from a networked database or other entities 48, 52, 54. In some embodiments, the longitudinal vehicle constraint data 416 may be dynamically or substantially in real-time calculated or otherwise determined based on the vehicle's current mass, current onboard fuel level, historical or recent performance of the vehicle, and / or other potential factors. In one or more embodiments, the longitudinal vehicle constraint data is calculated or determined relative to the lateral path, lateral vehicle constraint data, and / or determinations made by the lateral solver module. For example, by calculating the maximum longitudinal speed as a function of path curvature and maximum lateral acceleration (which itself can be constrained by driver preference or vehicle dynamics), the maximum longitudinal speed can be constrained by path curvature and maximum lateral acceleration at specific locations. At this point, at locations with relatively high path curvature (e.g., sharp turns), the maximum longitudinal speed can be correspondingly limited to maintain comfortable or achievable lateral acceleration along the curve.

[0053] Using various inputs to the longitudinal solver module, the longitudinal solver module calculates or otherwise determines a longitudinal plan (e.g., speed, acceleration, and jerk values ​​as a function of time) for traveling along the route within a predicted line of sight (e.g., 12 seconds) by changing the vehicle's speed or rate from the current posture and by optimizing some longitudinal cost variables or combinations thereof (e.g., minimizing travel time, minimizing fuel consumption, minimizing jerk, etc.) to ensure that the vehicle conforms to longitudinal riding preference information to the greatest extent possible, while also adhering to lane boundaries or other route constraints and avoiding collisions with objects or obstacles. At this point, under many conditions, the resulting longitudinal plan generated by the longitudinal solver module does not violate the maximum vehicle speed, maximum vehicle acceleration, maximum deceleration, and maximum longitudinal jerk settings associated with the user, while also adhering to the following distance or buffer associated with the user. That is, in some scenarios, violating one or more longitudinal riding preference settings may be necessary to avoid collisions, obey traffic signals, etc., in which case the longitudinal solver module may attempt to maintain as many user-specific longitudinal riding preference settings as possible. Therefore, the resulting longitudinal plan generally conforms to the user's longitudinal riding preference information, but not necessarily so strictly.

[0054] In a similar manner, the lateral solver module receives or otherwise obtains current vehicle attitude and relevant route information, as well as obstacle data, to determine a lateral driving planning solution within the predicted line of sight. The lateral solver module also receives or otherwise obtains lateral vehicle constraint data, which characterizes or otherwise defines the vehicle's kinematic or physical capabilities for lateral movement, such as, for example, maximum steering angle or steering angle range, minimum turning radius, maximum rate of change of steering angle, etc. Lateral vehicle constraint data can also be specific to each particular vehicle and can be obtained from onboard data storage element 32 or from a networked database or other entities 48, 52, 54. The lateral solver module can also receive or otherwise obtain user-specific lateral riding preference information, including, for example, user-specific steering rate values ​​or settings (e.g., maximum rate of change of steering angle, maximum acceleration of steering angle, etc.), lateral jerk, etc. Lateral riding preference information may also include user-specific distances or buffers, such as, for example, minimum and / or maximum distances from lane boundaries, minimum lateral buffers or lateral separation distances between objects or obstacles, etc., and potential other user-specific lane preferences (e.g., preferred driving lanes).

[0055] Using various inputs to the lateral solver module, the lateral solver module calculates or otherwise determines lateral planning for driving along the route at future locations within the predicted line of sight by changing the steering angle or wheel angle, by optimizing some lateral cost variables or combinations thereof (e.g., minimizing deviation from the road center, minimizing the curvature of the path, minimizing lateral jerk, etc.), in a manner that ensures the vehicle adheres to lateral driving preference information to the extent possible, while also complying with lane boundaries or other route constraints, and avoiding collisions with objects or obstacles.

[0056] During normal operation, the lateral solver module utilizes the longitudinal driving plan from the longitudinal solver module, along with route information and obstacle data, to determine how to steer the vehicle from its current posture within the predicted line of sight, while attempting to conform to lateral riding preference information. At this point, the final longitudinal and lateral driving plans output by the motion planning module conform to as many user riding preferences as possible, while optimizing cost variables and avoiding collisions by altering one or more of the vehicle's rate, acceleration / deceleration (longitudinal and / or lateral), jerk (longitudinal and / or lateral), steering angle, and rate of change of steering angle. The longitudinal driving plan output by the motion planning module includes a sequence of planned rate and acceleration commands relative to time for maneuvering the vehicle within the longitudinal predicted line of sight (e.g., rate planning for the next 12 seconds), and similarly, the lateral driving plan output by the motion planning module includes a sequence of planned steering angle and steering rate relative to distance or position for steer the vehicle within the lateral predicted line of sight when operating according to the longitudinal driving plan (e.g., steering planning for the next 50 meters). The longitudinal and lateral planning outputs are provided to the vehicle control system 80, which can use the vehicle positioning information and adopt its own control scheme to generate control outputs. These control outputs adjust the vehicle positioning information to longitudinal and lateral planning by changing the speed and steering commands provided to the actuator 30, thereby changing the speed and steering of the vehicle 10 to simulate or otherwise realize longitudinal and lateral planning.

[0057] As described in more detail below, in an exemplary embodiment, the guidance system 78 supports a hands-free autonomous operation mode that controls steering, acceleration, and braking. This mode is enabled and operates using current sensor data (or obstacle data) provided by the sensor fusion system 74 and the current vehicle attitude provided by the positioning system 76 to provide lane centering while attempting to maintain the driver-selected speed and / or following distance (or gap time) relative to other vehicles. In the autonomous operation mode, the guidance system 78 detects, identifies, or otherwise determines when the forward field of view of the sensing device 40 (such as a camera or other image sensor) is less than a target value corresponding to a desired minimum forward field of view threshold, for example, due to obstacles or other objects in the line of sight of the sensing device 40, guidance system 78, or other vehicles. When the forward field of view is less than the threshold, the guidance system 78 automatically increases the following distance (or gap time) and / or adjusts the lateral position of the vehicle 10 relative to the lane boundary (or lane centerline) for a temporary period to increase the forward field of view while attempting to maintain the driver-selected speed and avoid further exacerbation of situations that may occur due to driver intervention or insufficient forward field of view. For example, vehicles ahead of the main vehicle 10 (or, alternatively, referred to herein as closest in path (CIP) vehicles) within the line of sight of the camera or other sensing device 40 can reduce the ability of the sensor fusion system 74 and / or the positioning system 76 to detect or identify lane boundaries beyond CIP vehicles. Furthermore, in heavy traffic, the guidance system 78 must consider vehicles in adjacent lanes as well as curbs or road edges, which limit the main vehicle 10's ability to move laterally or change lanes to navigate around CIP vehicles.

[0058] In the exemplary embodiments described herein, when the current forward field of view of sensing device 40 is less than a target value corresponding to a desired minimum forward field of view threshold, guidance system 78 may automatically increase the following distance (or gap time) by a backoff distance to increase the total separation distance between the primary vehicle 10 and the CIP vehicle over a temporary time period, thereby increasing the length or amount of lane boundary or lane line visible to sensing device 40 at primary vehicle 10. Additionally or alternatively, guidance system 78 may also automatically adjust the lateral position of primary vehicle 10 by a slight offset relative to the lane centerline to assist lane line detection while avoiding road edges, adjacent vehicles, or other potential lateral intrusions. Due to the backoff distance and lateral offset, the subject matter described herein allows guidance system 78 at primary vehicle 10 to maintain reliable lane centering control and avoid driver intervention or other exacerbations when primary vehicle 10 encounters a CIP vehicle, which would otherwise limit the ability of sensor device 40 to capture the desired length of lane boundary and / or lane centerline.

[0059] Figure 3An exemplary implementation of a range control process 300 is depicted, which is suitable for implementation by a control module on a vehicle (e.g., a guidance system 78 of an ADS 70 supported by a controller 34 in vehicle 10) to temporarily reverse and / or laterally adjust the vehicle in response to a detected obstacle, object, or other event that diminishes the forward range of a camera, image sensor, or other sensing device (e.g., sensing device 40) on the vehicle. For illustrative purposes, the following description may be referenced in conjunction with the above. Figure 1-2 The components mentioned. Although the various parts of the range control process 300 can be executed by different components of the vehicle system, for illustrative purposes, the subject matter herein can be described primarily in the context that the range control process 300 is executed primarily by the guidance system 78 of the ADS 70, which is implemented by the controller 34 associated with the vehicle 10. In one or more exemplary aspects, the range control process 300 is combined with the components mentioned below. Figure 4 The rollback determination process is described in more detail in the context of 400 and / or below. Figure 5 The lateral adjustment process 500 is performed in more detail in the context of this process.

[0060] In an exemplary embodiment, at 302, the range control process 300 identifies or otherwise determines the current forward field of view of the sensing device. In one or more embodiments, the current forward field of view is calculated as a rolling average of the estimated visible lane boundary lengths over previous time intervals or a previous number of samples. For example, the sensor fusion system 74 may output the estimated visible lengths of the left lane boundary and the right lane boundary of the current driving lane while the vehicle 10 is in motion, wherein the estimated visible lengths of the lane boundaries are determined by the sensor fusion system 74 based at least in part on images or other sensor data captured and output by the sensing device. The guidance system 78 may periodically sample the output of the sensor fusion system 74 (e.g., during each iteration or update of the control scheme associated with the guidance system 78) to obtain the current estimated visible lengths of the left and right lane boundaries. For each iteration, the guidance system 78 may select or otherwise identify the maximum of the estimated visible lengths of the left lane boundary and the right lane boundary as the estimated forward field of view of the sensing device associated with the corresponding iteration. Subsequently, the guidance system 78 dynamically calculates or otherwise determines the rolling average of the estimated forward field of view values ​​(corresponding to the maximum of the estimated visible lengths of the left lane boundary and the right lane boundary) in previous iterations.

[0061] At 304, the range control process 300 continues by monitoring the current forward field of view to detect or otherwise identify when the current forward field of view falls below a target value for the forward field of view at 304. In an exemplary embodiment, the target value for the forward field of view is identified or otherwise determined based on the current speed or rate of the master vehicle 10, for example, by using a lookup table to identify a desired minimum threshold forward field of view for the input vehicle speed or rate. At this point, the guidance system 78 obtains the vehicle's current speed (e.g., from the positioning system 76), utilizes a lookup table to identify a target minimum threshold forward field of view for the current vehicle speed, and detects when the current forward field of view (e.g., a rolling average of estimated forward field of view values) is less than the target minimum threshold forward field of view for the current vehicle speed. When the current forward field of view is greater than the target minimum threshold forward field of view for the current vehicle speed, the loop defined by 302 and 304 is repeated during each iteration or update of the guidance system 78 implementing the range control process 300. As a non-limiting example, the target minimum threshold forward field of view can be the larger of a fixed minimum (e.g., 5 meters) or a function of the current vehicle speed multiplied by a calibration factor (e.g., 1.2).

[0062] When the current forward field of view is less than the target minimum threshold forward field of view for the current vehicle speed, the range control process 300 determines at 306 whether to initiate a reversal of the vehicle's longitudinal position before determining a reversal adjustment at 308. At this point, before initiating the reversal adjustment, the range control process 300 verifies or confirms that one or more reversal criteria are met. In an exemplary embodiment, the guidance system 78 verifies that the target minimum threshold forward field of view for the current vehicle speed is greater than the estimated distance between the current longitudinal position of the master vehicle 10 and the current longitudinal position of the CIP vehicle in front of the master vehicle 10. At this point, when the estimated distance to the CIP vehicle is greater than the target minimum threshold forward field of view, the range control process 300 determines that the CIP vehicle is not the cause of the current forward field of view limitation and determines that a reversal adjustment to increase the total following distance between the CIP vehicle and the master vehicle 10 is not suitable to increase the current forward field of view. In some embodiments, the sensor fusion system 74 outputs or otherwise provides a marker for the CIP vehicle and a corresponding estimate of the distance (or range) between the master vehicle 10 and the CIP vehicle. In some implementations, before initiating the rollback, the guidance system 78 may also verify or otherwise confirm that the current vehicle speed is within the desired vehicle speed range for which the rollback is initiated, that the autonomous lane centering control mode is effective, and that the number of consecutive vehicle overtaking maneuvers maintained by a counter (described in more detail below) is equal to zero. For example, as follows: Figure 4In a more detailed description within the context of this context, in some embodiments, the range control process 300 implements a counter to track or otherwise monitor the number of times vehicles other than CIP vehicles overtake the master vehicle 10, while performing backoff adjustment, and disables or otherwise terminates backoff adjustment when the counter value exceeds a threshold number (e.g., 2 consecutive overtakings) to limit the number of consecutive overtaking events. In one or more embodiments, in response to the number of consecutive overtakings exceeding the threshold, the range control process 300 starts a timer and waits for the threshold duration (e.g., 300 seconds) before re-enabling backoff adjustment at 306.

[0063] When applicable backoff criteria are met, the range control process 300 calculates or otherwise determines the backoff adjustment distance, as follows: Figure 4 The backoff determination process 400 is described in more detail in the context of this process. The backoff adjustment distance is provided as input to the longitudinal solver module to increase or otherwise amplify the following distance (or gap time) between the CIP vehicle and the master vehicle 10, thereby causing the longitudinal solver module to generate a longitudinal motion planning output that increases the distance between the CIP vehicle and the master vehicle 10 to correspondingly increase the forward field of view.

[0064] Still referencing Figure 3 At 310, before determining lateral offset adjustment at 312, the range control process 300 determines whether to initiate lateral adjustment of the vehicle within the current driving lane. At this point, before initiating lateral offset adjustment, the range control process 300 verifies or otherwise confirms that one or more lateral offset criteria are met. In an exemplary embodiment, the guidance system 78 verifies that the estimated width of the CIP vehicle is greater than a threshold width (e.g., 1.5 meters). At this point, when the estimated width of the CIP vehicle is less than the threshold width, the range control process 300 determines that the width of the CIP vehicle is not a cause of limiting the current forward field of vision, and that lateral adjustment is not suitable to increase the current forward field of vision. In some embodiments, before initiating lateral adjustment, the guidance system 78 may also verify or otherwise confirm that the current vehicle speed is within the desired vehicle speed range for which lateral adjustment is enabled, that the autonomous lane centering control mode is effective, and that the road curvature at or within a threshold distance from the current vehicle location is less than a threshold (e.g., 0.0005 / m). In this respect, in addition to estimating lane line length, sensor fusion system 74 can output the estimated curvature of each of the left lane boundary (or left lane line) and the right lane boundary (or right lane line) of the currently driving lane.

[0065] When applicable lateral adjustment criteria are met, the range control process 300 calculates or otherwise determines the lateral offset distance and lateral adjustment direction, as follows: Figure 5The lateral adjustment process 500 is described in more detail in the context of the lateral adjustment process. The lateral offset distance is provided as input to the lateral solver module to laterally offset the lateral position of the vehicle relative to the centerline of the current driving lane in a determined lateral adjustment direction, thereby causing the lateral solver module to generate a lateral motion planning output that laterally maneuvers the master vehicle 10 in the current driving lane away from the centerline to laterally offset the position of the master vehicle 10 relative to the CIP vehicle, reducing the obstruction of the CIP vehicle and increasing the forward field of vision.

[0066] Still referencing Figure 3 At 314, the range control process 300 updates the trajectory planning of the master vehicle to incorporate backoff adjustment and / or lateral offset adjustment. At this point, as described above, the effective backoff adjustment distance increases or otherwise amplifies the following distance (or gap time) utilized by the longitudinal solver when generating the longitudinal motion planning output to alter or otherwise update the longitudinal trajectory of the master vehicle 10 to increase the distance between the CIP vehicle and the master vehicle 10 (e.g., by decelerating the master vehicle 10 at one or more locations along the route in the future, so that the total distance to the CIP vehicle equals the sum of the default or normal following distance and the backoff adjustment distance). Simultaneously, the lateral solver module utilizes any effective lateral offset distance and direction when generating the lateral motion planning output to alter or otherwise update the lateral trajectory of the master vehicle 10 within the current driving lane to at least temporarily deviate from the centerline of the current driving lane (e.g., by steering the vehicle 10 at one or more locations along the route in the future, so that the vehicle 10 deviates from the lane centerline in the desired direction through desired offset adjustment).

[0067] At 316, the range control process 300 determines whether any applicable exit criteria are met or whether an exit condition for terminating adjustment exists. For example, the range control process 300 may verify or otherwise confirm that the autonomous lane centering control mode remains effective, the CIP vehicle is still ahead of the master vehicle 10, the current vehicle speed is within the desired speed range, and / or similar conditions. In the absence of an exit condition, the range control process 300 repeats the loop defined by 306, 308, 310, 312, and 314 to dynamically change the back-off adjustment distance and / or lateral offset adjustment distance as the master vehicle 10 moves (e.g., taking into account changes in the speed of the master vehicle 10, changes in the speed or lateral position of the CIP vehicle, etc.). When the exit criteria are met or an exit condition exists in another manner, at 318, the range control process 300 gradually reduces the back-off adjustment and / or lateral offset adjustment to zero. In this respect, when the CIP vehicle changes lanes and no longer has or obstructs the forward field of vision, any currently effective backoff adjustment and / or lateral offset adjustment can be gradually reduced or ramped down to avoid sudden changes in vehicle position and to maintain passenger comfort when returning to the normal configuration of autonomous lane centering control mode.

[0068] Figure 4 An exemplary embodiment of a back-up determination process 400 is described, which is adapted to be used in conjunction with a range control process 300 at 308 to determine a back-up distance to increase the following distance (or gap time) relative to a CIP vehicle ahead of the master vehicle, thereby improving the forward field of view of cameras or other forward-looking sensing devices on the master vehicle. For illustrative purposes, the following description may refer to the above in conjunction with... Figure 1-2 The components mentioned. Although parts of the rollback determination process 400 can be performed by different components of the vehicle system, for the purposes of explanation, the subject matter can be described primarily in the context that the rollback determination process 400 is performed mainly by the guidance system 78 of the ADS 70, which is implemented by the controller 34 associated with the vehicle 10.

[0069] At 402, the backoff determination process 400 calculates or otherwise determines the distance difference between the target forward field of view of the sensing device and the estimated distance between the CIP vehicle and the host vehicle, and then at 404 multiplies this difference by a calibrable gain factor to calculate the maximum backoff distance adjustment. At this point, the maximum backoff distance is a function of the difference between the current position of the CIP vehicle relative to the host vehicle 10 and the position of the host vehicle 10 relative to the CIP vehicle to ensure that the target forward field of view can be achieved when the CIP vehicle is present. Subsequently, at 406, the backoff determination process 400 increments or gradually increases the value of the backoff adjustment distance, which is provided to the longitudinal solver module or otherwise used to increase the following distance from zero (or another initial value) until the calculated maximum backoff distance adjustment is reached. At this point, for each iteration or update of the longitudinal motion planning, the backoff adjustment distance can be gradually increased or ramped up until the value of the maximum backoff distance adjustment is achieved, without any offset exit condition (e.g., at 316, the CIP vehicle no longer exists). In some implementations, the back-off adjustment distance may be incremented by a fixed calibrable value (in some implementations, this value may vary depending on the current vehicle speed, or may be calculated as a function of the current vehicle speed), while in other implementations, the back-off adjustment distance may be incremented as a percentage or fraction of the maximum back-off distance.

[0070] In the illustrated embodiment, while increasing and / or maintaining the backoff distance adjustment, the backoff determination process 400 monitors vehicle overtaking events at 408 and detects or otherwise identifies at 410 when the number of vehicle overtaking events exceeds a threshold. At this point, as described above, the guidance system 78 may implement a counter or similar feature to monitor the output of the sensor fusion system 74 to detect or otherwise identify each different vehicle from the previous CIP vehicle overtaking in front of the master vehicle 10, while implementing backoff adjustment to terminate the backoff adjustment when the number of consecutive overtaking events exceeds a threshold number of permissible consecutive overtaking events. When the observed number of overtaking events is less than the maximum permissible threshold amount, the backoff determination process 400 monitors the speed (or rate) of the master vehicle at 412 to verify that the current vehicle speed is within a threshold used to calculate the initial reference vehicle speed for the maximum backoff distance adjustment at 402.

[0071] When the current vehicle speed is within a threshold of the initial vehicle speed at the start of the rollback determination process 400, the rollback determination process 400 continues to incrementally increase the rollback adjustment distance, while monitoring overtaking events at 406, 408, and 410. At this point, once the initially calculated maximum rollback distance adjustment is achieved, the rollback determination process 400 monitors the speed (or rate) of the primary vehicle at 412 to dynamically adjust the rollback distance adjustment in response to changes in the primary vehicle's speed exceeding a threshold amount (e.g., exceeding 15 mph). For example, as described above, the target forward field of view can be determined as a function of the current vehicle speed at the time of initiating rollback adjustment using a lookup table to identify the target minimum threshold forward field of view. Subsequently, at 412, when the backoff determination process 400 determines that the current vehicle speed deviates from the initial reference vehicle speed used to determine the initial target forward field of view at 402 by more than a threshold, the backoff determination process 400 dynamically calculates or otherwise determines the minimum threshold forward field of view of the current vehicle speed (e.g., obtained from a lookup table using the new current vehicle speed as input) and the current estimated distance between the CIP vehicle and the master vehicle, and then at 404 calculates or otherwise determines the adjusted maximum backoff distance adjustment as a function of the updated difference.

[0072] For example, in one implementation, the adjusted maximum back-off distance adjustment is calculated by multiplying the previously calculated maximum back-off distance adjustment and the updated difference using the same gain factor used at 402 to calculate the maximum back-off distance adjustment amount. Thereafter, the back-off determination process 400 incrementally increases or decreases the back-off distance until the adjusted maximum back-off distance adjustment is achieved at 406. At this point, as the main vehicle accelerates, a larger forward field of view is expected, which in turn causes the back-off determination process 400 to dynamically increase the back-off distance substantially in real time. On the other hand, when the main vehicle 10 decelerates, a shorter minimum threshold forward field of view is expected, in which case the back-off determination process 400 can dynamically decrease the back-off distance to account for the reduced vehicle speed and reduce the likelihood of overtaking events.

[0073] Still referencing Figure 4At 410, when the backoff determination process 400 determines that the number of consecutive overtaking events exceeds the threshold number of permissible overtaking events, the backoff determination process 400 incrementally reduces the backoff distance adjustment to zero at 414. In this way, the guidance system 78 can gradually decrease or reduce the backoff adjustment distance provided to the longitudinal solver module or otherwise used to increase the following distance from the current value until the backoff distance adjustment reaches zero. As a result, for each iteration or update of the longitudinal motion planning, the backoff adjustment distance can be gradually reduced, thereby causing the longitudinal motion planning to gradually reduce the total following distance between the CIP vehicle and the master vehicle 10 in a corresponding manner. In a similar manner to the above, depending on the implementation, the backoff adjustment distance can be reduced incrementally by a fixed calibrable value, while in other implementations, the backoff adjustment distance can be reduced incrementally by a percentage or fraction of the maximum backoff distance.

[0074] Figure 5 An exemplary embodiment of a lateral adjustment process 500 is depicted, which is suitable for use in conjunction with a range control process 300 at 312 to determine the lateral offset direction and lateral offset distance for steering the host vehicle relative to the CIP vehicle while keeping the host vehicle in its current driving lane, thereby improving the forward field of view of cameras or other forward-looking sensing devices on the host vehicle. For illustrative purposes, the following description may be referenced to the above in conjunction with... Figure 1-2 The components mentioned. Although parts of the lateral adjustment process 500 can be performed by different components of the vehicle system, for the purposes of explanation, the subject matter can be described primarily in the context of the lateral adjustment process 500, which is mainly performed by the guidance system 78 of the ADS 70 implemented by the controller 34 associated with the vehicle 10.

[0075] The lateral adjustment process 500 begins at 502 by calculating or otherwise determining assessment scores for the two lane boundaries of the current driving lane during an assessment window, and then determining the lateral offset direction based on the lane boundary assessment scores at 504. For example, as described above, the sensor fusion system 74 may output or otherwise provide markers of the estimated visible lengths of the left and right lane boundaries of the current driving lane. Additionally, the sensor fusion system 74 may output or otherwise provide confidence values ​​or other quality markers associated with the respective lane boundaries. In this respect, the quality markers provided by the sensor fusion system 74 may be affected by adjacent traffic, curbs, or other environmental factors that may impair the ability of the sensor fusion system 74 to detect, distinguish, or otherwise identify lane boundaries. For each lane boundary, the guidance system 78 may calculate or otherwise determine the assessment score associated with the corresponding lane boundary as the sum of a first product of the estimated visible length of the corresponding lane boundary and a first gain coefficient (or weighting factor) and a second product of the estimated quality and a second gain coefficient (or weighting factor) associated with the corresponding lane boundary. To determine the direction of offset, guidance system 78 implements a counter associated with each corresponding lane boundary, and during each update or iteration of guidance system 78, guidance system 78 increments the value of the counter associated with the lane boundary that has the highest evaluation score calculated for that iteration. After the evaluation time window has passed, guidance system 78 identifies the side associated with the corresponding lane boundary with the highest counter value as the direction in which lateral offset should occur (e.g., by laterally maneuvering the master vehicle 10 closer to the lane boundary with a higher evaluation score that has a more consistent performance).

[0076] In an exemplary embodiment, the lateral adjustment process 500 verifies or otherwise confirms that there is no risk of another vehicle, obstacle, or other object intruding from the lateral offset direction determined at 506. In this regard, the guidance system 78 analyzes the output provided by the sensor fusion system 74 to verify or otherwise confirm that there is no adjacent traffic or potential other intruding objects from the determined offset direction in adjacent lanes in the determined offset direction before enabling lateral offset adjustment. For example, if the determined lateral offset direction is to the left, and there is another vehicle traveling alongside the main vehicle 10 in the next lane adjacent to the current driving lane to the left of the current driving lane, the lateral adjustment process 500 may determine that there is a potential intrusion risk and exit without performing lateral offset adjustment. On the other hand, if the determined lateral offset direction is to the left, and no vehicle is traveling within a threshold distance of the main vehicle 10 in the next lane adjacent to the current driving lane to the left of the current driving lane, the lateral adjustment process 500 may determine that there is no intrusion risk in the lateral offset direction and continue to implement lateral offset adjustment.

[0077] At point 508, after determining the direction of the forward range-based lateral offset adjustment and verifying that the lateral offset adjustment does not increase the risk of intrusion, the lateral adjustment process 500 continues by gradually or incrementally increasing the range-based lateral offset amount in the determined lateral offset direction until the maximum permissible amount of range-based lateral offset is reached. In a manner similar to that described above in the context of rollback adjustment, the guidance system 78 gradually increases the magnitude of the range-based lateral offset adjustment from an initial zero value in the determined direction relative to the lane centerline until the maximum permissible value of the range-based lateral offset adjustment is reached. At this point, the maximum permissible value of the range-based lateral offset adjustment can be configured to limit or otherwise prevent the primary vehicle 10 from deviating from the lane centerline by a fixed amount. This ensures a sufficient buffer distance between the primary vehicle 10 and the nearest lane boundary and reduces the likelihood of driver intervention in response to lateral offset (e.g., due to the perceived lane centering autonomous control mode not operating correctly). Therefore, for each iteration or update of the lateral motion planning, when range-based lateral offset adjustment is enabled, the lateral offset adjustment distance can be gradually increased or ramped up until the maximum range-based lateral offset adjustment value is achieved without any offset exit conditions (e.g., the 316 CIP vehicle no longer exists). In an exemplary implementation, the lateral offset adjustment distance increases incrementally by a fixed calibrable value (in some implementations, this calibrable value may vary depending on the current value of the vehicle speed or other factors).

[0078] In one or more exemplary embodiments, to implement lateral offset adjustment, the lateral adjustment process 500 mixes or otherwise combines a range-based lateral offset with any other valid lateral offset to obtain a total lateral offset adjustment that will be used for lateral motion planning at 510. For example, depending on the embodiment, the guidance system 78 and / or ADS 70 may independently calculate or otherwise determine one or more lateral offset adjustments to be applied based on road conditions such as whether oncoming traffic is separated, road curvature, intruding vehicles, etc. When the range-based lateral offset is in the opposite direction to the cumulative net of other lateral offsets, the lateral adjustment process 500 adds or otherwise combines the value of the range-based lateral offset with the net lateral offset value to arrive at a value for the total lateral offset adjustment that the lateral motion planner will utilize. For example, if the range-based lateral offset value is 10 cm (-10 cm) to the left, and the net of other lateral offsets is 20 cm (+20 cm) to the right, the lateral adjustment process 500 adds these values ​​to arrive at a total lateral offset adjustment of 10 cm (+10 cm) to the right.

[0079] On the other hand, when the range-based lateral offset is in the same direction as the net other lateral offsets, the lateral adjustment process 500 selects the offset with the largest amount of lateral offset adjustment distance to be implemented. For example, if the range-based lateral offset value is 10 cm (-10 cm) to the left, and the net amount of the other lateral offsets is 5 cm (-5 cm) to the left, then the lateral adjustment process 500 selects or otherwise identifies the value of the range-based lateral offset value to be used as the total lateral offset adjustment distance (10 cm) and the lateral offset direction (negative or left) as values ​​to be provided as input to the lateral solver module. At this point, when the range-based lateral offset value increases in the same direction as other effective offsets (e.g., at 508), the range-based lateral offset value can increase the magnitude of the lateral offset to increase the forward field of vision by taking into account the presence and / or width of the CIP vehicle plus other road conditions, thereby making the lateral offset in that direction desirable. As described above, the lateral solver module uses total lateral offset adjustment in autonomous lane centering control mode to generate lateral motion planning output, which is used to control the lateral movement of vehicle 10 in the current driving lane by maneuvering vehicle 10 at one or more locations along the route in the future, so as to maintain the lateral position of the vehicle at an input lateral offset distance from the lane centerline in a determined lateral offset direction.

[0080] Figure 6-7 An exemplary scene sequence is depicted, showing the scene at vehicle 602. Figure 3 In the range control process 300, vehicle 602 can be an instance of vehicle 10. Figure 6 The initial state 600 of vehicle 602 is depicted, which is traveling along a route within a first lane 620 behind another vehicle 604, while operating in a secondary autonomous operation mode that attempts to keep vehicle 602 substantially centered within the current lane 620 traveling along the lane centerline 622 at a user-defined rate, and subject to other user-defined or user-configurable constraints (e.g., distance from other vehicles, etc.). Figure 6 A CIP vehicle 604 is depicted in the current lane 620, positioned in front of the main vehicle 602 at a distance 606 smaller than the target forward field of view 608 corresponding to the current speed of the main vehicle 602. This obstructs the camera or other forward-looking sensing device on the main vehicle 602 from achieving the target forward field of view 608. Furthermore, the width of the CIP vehicle 604 is greater than the width of the main vehicle 602, potentially hindering the ability of the camera or other sensing device on the main vehicle 602 to achieve the target forward field of view 608 at the lane boundary of the current lane 620.

[0081] Figure 7The updated state 700 of vehicle 602 is depicted after the execution of range control process 300 to perform backoff adjustment according to backoff determination process 400, thereby increasing the separation distance 606 utilized by the longitudinal solver module by a backoff adjustment distance 706. This backoff adjustment distance 706 temporarily increases the distance between the main vehicle 602 and the CIP vehicle 604 to help achieve the target forward visibility range 608 of the lane boundary of the current lane 620. As described above, the backoff adjustment distance 706 can be calculated based on the difference between the target forward visibility range 608 and the estimated distance 606 to the CIP vehicle 604 (e.g., by subtracting the estimated distance 606 from the target distance 608 and multiplying the result by a gain factor). Additionally, Figure 7 A scenario is described in which the range control process 300 also depends on Figure 5 The lateral adjustment process 500 performs lateral offset adjustment to laterally deviate from the lane centerline 622 by a lateral offset adjustment distance 708 to the right of the lane centerline 622. For example, the presence of another vehicle 610 in the adjacent lane 630 to the left of the current lane 620 may reduce the quality or accuracy of the lane boundary associated with the left side of the current lane 620 determined by the sensor fusion system 74, consistent with the presence of a potential intruding vehicle 610 in the adjacent lane 630. This causes the lateral adjustment process 500 to determine the desired lateral offset direction to the right and accordingly provide a lateral offset adjustment marker to the lateral solver module to maneuver the main vehicle 602 to the right, thereby further improving the visibility of the lane boundary associated with the current lane 620.

[0082] As described above, in the exemplary embodiment, between the initial state 600 and the subsequent state 700, the forward visibility adjustment distance ranges 706 and 708 gradually increase from zero in the initial state 600 to the values ​​depicted in the subsequent state 700. Thereafter, when the CIP vehicle 604 is no longer present or some other exit condition is met (e.g., at 316), the forward visibility adjustment distance ranges 706 and 708 may gradually decrease back to zero (e.g., at 318). For example, when one or more vehicles 610 from the adjacent left lane 630 enter the current lane 620 between the main vehicle 602 and the previous CIP vehicle 604, causing the number of overtaking events to exceed the permissible threshold number of consecutive overtaking events (e.g., at 410), the backoff adjustment distance 706 may gradually decrease back to zero to reduce the likelihood of additional overtaking events. Similarly, if another vehicle 610, with a width less than or equal to the threshold width used to perform lateral offset adjustment, overtakes the master vehicle 602 and becomes the updated CIP vehicle, the range control process 300 may determine that lateral offset adjustment is no longer necessary or desirable (e.g., at 310), and gradually reduce the lateral offset adjustment distance 708 back to zero when the CIP vehicle is no longer wider than the lateral offset adjustment enabling threshold. At this point, it should be understood that in practice, the forward vision adjustment distance ranges 706, 708 may depend on the current speed dynamics of the master vehicle 602, or reflect changes in the behavior of other vehicles 604, 610 and / or road conditions observed while the master vehicle 602 is driving. In this way, a target forward vision range can be achieved for the camera or other forward-looking sensing device on the master vehicle 602, thereby maintaining autonomous lane centering control in a manner that minimizes driver intervention or passenger discomfort.

[0083] While at least one exemplary aspect has been presented in the foregoing detailed description, it should be understood that numerous variations exist. It should also be understood that the one or more exemplary aspects are merely examples and are not intended to limit the scope, applicability, or configuration of this disclosure in any way. Rather, the foregoing detailed description will provide those skilled in the art with a convenient roadmap for implementing one or more exemplary aspects. It should be understood that various changes can be made to the function and arrangement of the elements without departing from the scope of this disclosure as set forth in the appended claims and their legal equivalents.

Claims

1. A method for controlling a vehicle in an autonomous operation mode, the method comprising: The controller associated with the vehicle determines the current value of the forward field of view associated with the sensing devices on the vehicle; The controller determines the target value of the forward field of view associated with the sensing device based at least in part on the speed of the vehicle; as well as In response to determining that the current value is less than the target value: The controller determines the back-off adjustment distance based at least in part on the difference between the target value of the forward field of view and the estimated distance to the nearest vehicle in the path ahead of the vehicle in the current driving lane. The controller determines the vehicle's longitudinal trajectory based at least in part on the back-off adjustment distance to increase the estimated distance to the nearest vehicle in the path; When the width associated with the nearest vehicle in the path is greater than a threshold, the controller determines the lateral offset adjustment distance; The controller determines the vehicle's lateral trajectory based at least in part on the lateral offset adjustment distance to offset the vehicle relative to the centerline associated with the current driving lane; as well as The controller autonomously operates one or more actuators on the vehicle based on a longitudinal trajectory, and simultaneously operates the one or more actuators based on a lateral trajectory, in order to increase the forward field of view. The determination of the current value of the forward field of view range includes a rolling average of a first estimated visible length associated with the left boundary of the current driving lane and a second estimated visible length associated with the right boundary of the current driving lane, calculated by the controller over a previous time interval.

2. The method according to claim 1, wherein, Determining the target value involves using the vehicle's speed to obtain the target value from a lookup table maintained in the data storage associated with the vehicle.

3. The method according to claim 1, further comprising: The controller determines when a second difference between the vehicle's current speed and its initial speed, which are associated with the target value, is greater than a threshold. and In response to determining that the second difference is greater than the threshold: The controller determines the updated target value of the forward field of view associated with the sensing device based at least in part on the vehicle's current speed; The updated backoff adjustment distance is determined by the controller based at least in part on the updated target value and the current estimated distance between the nearest vehicle in the path and the vehicle. The updated longitudinal trajectory of the vehicle is determined by the controller based at least in part on the updated backoff adjustment distance; and The controller autonomously operates one or more actuators on the vehicle based on the updated longitudinal trajectory.

4. The method according to claim 1 further includes gradually reducing the back-off adjustment distance when the nearest vehicle in the path is no longer in front of the vehicle in the current driving lane.

5. The method according to claim 1 further includes gradually reducing the backoff adjustment distance when the number of consecutive overtaking events exceeds a threshold.

6. The method of claim 1, further comprising determining, at least in part, a first estimated visible length associated with the left boundary of the current driving lane and a second estimated visible length associated with the right boundary of the current driving lane based by the controller on one or more images or sensor data captured by the sensing device.

7. A vehicle comprising: Maintain the data storage for the lookup table; One or more vehicle-mounted sensing devices; One or more actuators on a vehicle; and The controller, which is controlled by the processor: Determine the current value of the forward field of view associated with one or more of the sensing devices. The target value for the forward field of view associated with the sensing device is determined using a lookup table, at least in part, based on the vehicle's speed. When the current value is less than the target value: The back-off adjustment distance is determined at least in part based on the difference between the target value of the forward field of view and the estimated distance to the nearest vehicle in the path ahead of the vehicle in the current driving lane. The longitudinal trajectory of the vehicle is determined, at least in part, based on the back-off adjustment distance to increase the estimated distance to the nearest vehicle in the path. When the width associated with the nearest vehicle in the path is greater than a threshold, determine the lateral offset adjustment distance. The lateral trajectory of the vehicle is determined at least in part based on the lateral offset adjustment distance to offset the vehicle relative to the centerline associated with the current driving lane, and The vehicle autonomously operates one or more actuators based on a longitudinal trajectory, and simultaneously operates the same one or more actuators based on a lateral trajectory, thereby increasing the forward field of view. The determination of the current value of the forward field of view range includes a rolling average of a first estimated visible length associated with the left boundary of the current driving lane and a second estimated visible length associated with the right boundary of the current driving lane, calculated by the controller over a previous time interval.

8. The vehicle according to claim 7, wherein, The sensing device includes a camera.

9. The vehicle according to claim 7, wherein: The sensing device includes a camera; and The controller determines, at least in part, a first estimated visible length associated with the left boundary of the current driving lane and a second estimated visible length associated with the right boundary of the current driving lane based on one or more images captured by the camera.

10. The vehicle according to claim 7, wherein, When the nearest vehicle in the path is no longer in front of the vehicle in the current driving lane, the controller gradually reduces the back-off adjustment distance.

11. The vehicle according to claim 7, wherein, When the number of consecutive overtaking events exceeds a threshold, the controller gradually reduces the backoff adjustment distance.

12. A non-transitory computer-readable medium comprising executable instructions, said executable instructions causing the processor, when executed by a processor, to: Determine the current value of the forward field of view associated with the sensors on the vehicle; The target value of the forward field of view associated with the sensing device is determined at least in part based on the vehicle's speed; and In response to determining that the current value is less than the target value: The back-off adjustment distance is determined at least in part based on the difference between the target value of the forward field of vision and the estimated distance to the nearest vehicle in the path ahead of the vehicle in the current driving lane. The longitudinal trajectory of the vehicle is determined at least in part based on the back-off adjustment distance to increase the estimated distance to the nearest vehicle in the path; When the width associated with the nearest vehicle in the path is greater than a threshold, a lateral offset adjustment distance is determined; The lateral trajectory of the vehicle is determined at least in part based on the lateral offset adjustment distance to offset the vehicle relative to the centerline associated with the current driving lane; and The vehicle autonomously operates one or more actuators according to the longitudinal trajectory, and simultaneously operates the one or more actuators according to the lateral trajectory, in order to increase the forward field of view. Determining the current value of the forward field of view range includes calculating a rolling average of a first estimated visible length associated with the left boundary of the current driving lane and a second estimated visible length associated with the right boundary of the current driving lane over a previous time interval.

13. The non-transitory computer-readable medium according to claim 12, wherein, The executable instructions cause the processor to determine, at least in part, a first estimated visible length associated with the left boundary of the current driving lane and a second estimated visible length associated with the right boundary of the current driving lane, based on one or more images or sensor data captured by the sensing device.

14. The non-transitory computer-readable medium according to claim 13, wherein, The sensing device includes a camera on the vehicle, and the executable instructions cause the processor to determine a first estimated visual length and a second estimated visual length based at least in part on one or more images captured by the camera on the vehicle.

Citation Information

Patent Citations

  • System and method for improving sensor visibility of vehicle in autonomous driving mode

    CN104044587A

  • Method for longitudinal control of e.g. electrical vehicle, involves implementing brake intervention to maintain preset minimum distance to vehicle, and introducing intervention only when brake- or accelerator pedal is actuated

    DE102011116773A1

  • Positioning quality filter for the V2X technologies

    US20180045832A1

  • Trajectory generation and optimization using closed-form numerical integration in route-relative coordinates

    US20210109539A1

  • Vision-based follow the leader lateral controller

    WO2021076705A2