Vehicle path assessment for detecting and reacting to untrusted driver steering inputs
By determining the vehicle's actual and apparent trajectories, and using obstacle grids to identify potential collisions and issue warnings or brakes, the potential collision risk caused by unreliable steering inputs is addressed, thus improving vehicle safety.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- GM GLOBAL TECHNOLOGY OPERATIONS LLC
- Filing Date
- 2024-12-20
- Publication Date
- 2026-04-24
AI Technical Summary
The driver may unintentionally provide incorrect steering input, causing the vehicle's actual trajectory to differ from its apparent trajectory, resulting in a potential collision risk, and the driver fails to correct this in time.
The actual and apparent trajectories of the vehicle are determined by the trajectory calculation module, and potential collision risks are identified by the obstacle mesh generation module. Warnings are issued or brakes are applied when necessary to prevent collisions.
Effective identification and prevention of potential collisions caused by unreliable steering inputs improves vehicle safety and reduces the likelihood of accidents.
Smart Images
Figure CN121912950A_ABST
Abstract
Description
Background Technology
[0001] The information provided in this section is for the purpose of generally presenting the context of this disclosure. The work of the inventors under the current name to the extent described in this section, as well as aspects that might not have qualified as prior art at the time of filing, are neither expressly nor implicitly acknowledged as prior art to this disclosure.
[0002] This disclosure relates to vehicles, and more particularly to a vehicle path assessment system for detecting and correcting unreliable steering inputs of a vehicle.
[0003] The vehicle may include a steering wheel for controlling the vehicle's direction, acceleration, and speed, an accelerator pedal, and a brake pedal. While driving, the steering wheel can be rotated multiple times from lock to lock. As a result, the steering wheel can be positioned near-center, while the front wheels are not aligned in a straight or near-straight direction. In some situations, the driver may not be aware that the steering wheel is in an incorrect position and may not be able to correct its position before accelerating the vehicle. Summary of the Invention
[0004] A path assessment system for a vehicle includes: a trajectory calculation module configured to determine an actual trajectory of the vehicle based on the actual position of the vehicle's steering wheel and to determine an apparent trajectory of the vehicle based on the apparent position of the vehicle's steering wheel; an obstacle mesh generation module configured to generate an obstacle mesh; a collision probability module configured to determine a probability of collision based on the obstacle mesh and the vehicle's actual trajectory; and a mitigation module configured to, in response to the probability being greater than a predetermined percentage, perform at least one of warning the driver, applying the vehicle's brakes, and requesting a change in acceleration.
[0005] Among other features, the path evaluation system includes at least one of a light detection and ranging (LiDAR) sensor, a radar detection and ranging (radar) sensor, and a camera / image sensor.
[0006] Among other features, the obstacle mesh generation module generates an obstacle mesh in response to at least one of a LiDAR sensor, a radar sensor, and a camera / image sensor. The apparent position of the steering wheel corresponds to the absolute steering wheel angle and the remainder of 360 degrees. Before the vehicle begins to move, the trajectory calculation module determines the vehicle's actual trajectory and apparent trajectory. The trajectory calculation module determines the vehicle's actual trajectory and apparent trajectory by assuming the vehicle's nominal acceleration. The trajectory calculation module is enabled in response to a gear selector event. The trajectory calculation module is enabled in response to the gear selector moving from park to drive or reverse. The trajectory calculation module is enabled in response to the absolute value of the wheel angle being greater than a first threshold. The first threshold is greater than or equal to 5°. The trajectory calculation module is enabled in response to the absolute value of the steering wheel angle and the remainder of 360 degrees being less than a second threshold. The second threshold is less than or equal to 45°.
[0007] Among other features, the trajectory calculation module is enabled in response to the following conditions: the gear selector moves from park to drive or reverse; the absolute value of the wheel angle is greater than a first threshold; and the absolute value of the steering wheel angle and the remainder of 360 is less than a second threshold.
[0008] A vehicle includes at least one of a light detection and ranging (LiDAR) sensor, a radar detection and ranging (radar) sensor, and a camera / image sensor. A trajectory calculation module is configured to: determine the actual trajectory of the vehicle based on the actual position of the vehicle's steering wheel before the vehicle begins to move; and determine the apparent trajectory of the vehicle based on the apparent position of the vehicle's steering wheel before the vehicle begins to move, wherein the apparent position of the steering wheel corresponds to the absolute value of the steering wheel angle and the remainder of 360 degrees. An obstacle mesh generation module is configured to generate an obstacle mesh in response to at least one of the LiDAR sensor, radar sensor, and camera / image sensor. A collision probability module is configured to determine the probability of a collision based on the obstacle mesh and the actual trajectory of the vehicle. A mitigation module is configured to, in response to the probability being greater than a predetermined percentage, perform at least one of warning the driver, applying the vehicle's brakes, and requesting a change in acceleration.
[0009] Among other features, the trajectory calculation module determines the vehicle's actual and apparent trajectories by assuming the vehicle's nominal acceleration. The trajectory calculation module is activated in response to the following conditions: the gear selector moves from park to drive or reverse; the absolute value of the wheel angle is greater than a first threshold; and the remainder of the absolute value of the steering wheel angle and 360 degrees is less than a second threshold.
[0010] Among other features, the trajectory calculation module is activated in response to the gear selector moving from park to drive or reverse. The trajectory calculation module is activated in response to the absolute value of the wheel angle being greater than a first threshold. The trajectory calculation module is activated in response to the remainder of the absolute value of the steering wheel angle divided by 360 degrees being less than a second threshold. The second threshold is less than or equal to 45°.
[0011] Further areas of applicability of this disclosure will become clear from the detailed description, claims, and drawings. The detailed description and specific examples are intended for illustrative purposes only and are not intended to limit the scope of this disclosure. Attached Figure Description
[0012] This disclosure will become more fully understood through detailed description and accompanying drawings, in which:
[0013] Figure 1A The illustration shows an example of a steering wheel positioned at a first rotational position and corresponding to the first front wheel of the vehicle.
[0014] Figure 1B The illustration shows examples of rotating a steering wheel through various steering wheel angles.
[0015] Figure 1C The illustration shows an example of the steering wheel in a first rotational position and the corresponding second position of the vehicle's front wheels;
[0016] Figure 2A The illustration shows an example of a vehicle located in a parking space, while other vehicles are located in adjacent parking spaces;
[0017] Figure 2B The illustration shows an example of a steering wheel with a low apparent steering wheel angle and wheels that turn at a higher actual angle.
[0018] Figure 2C The illustration shows an example of a vehicle collision caused by the difference between the actual steering wheel angle and the apparent steering wheel angle.
[0019] Figure 3 The illustration shows an example of an obstacle grid relative to actual and apparent trajectories according to this disclosure;
[0020] Figure 4 The present disclosure provides a functional block diagram of an example vehicle, which includes a driver assistance controller and a vehicle route assessment module.
[0021] Figure 5 This is a functional block diagram of an example of a vehicle routing assessment module according to this disclosure;
[0022] Figure 6A and 6B The illustrations depict the actual and apparent trajectories of the vehicles according to this disclosure; and
[0023] Figure 7 This is a flowchart of a method for detecting and reacting to the apparent steering wheel position corresponding to an unreliable steering angle.
[0024] In the accompanying drawings, reference numerals may be reused to identify similar and / or identical elements. Detailed Implementation
[0025] There are numerous instances where a vehicle driver may unintentionally provide incorrect steering input. The steering wheel has a centered position corresponding to the wheels of a vehicle pointing in a straight direction. After the steering wheel has been rotated 360°, it appears centered, but the wheels are deviating from a straight line. For example, the steering wheel may have an apparent angle of +10° relative to the centered position. However, the driver may not realize that the actual angle of the steering wheel relative to the centered position is actually -350° or +370° (because the steering wheel appears the same at both of these angles). The vehicle's wheels may actually be turning at a higher angle, rather than closer to a straight line.
[0026] It is understood that the apparent trajectory of a vehicle as perceived by the driver differs from its actual trajectory. An accident may occur if the driver accelerates and an obstacle is present in the vehicle's actual trajectory. Furthermore, there may not be enough time for the driver to react to an unexpected trajectory.
[0027] The vehicle path assessment system disclosed herein identifies scenarios when untrusted steering wheel input occurs. When certain conditions are present, the vehicle path assessment system determines the vehicle's actual and apparent trajectories, generates an obstacle grid, and identifies the probability of a collision based on this grid. In some examples, the vehicle path assessment system determines the vehicle's actual and apparent trajectories (by assuming the vehicle's nominal acceleration) before the vehicle begins to move.
[0028] If the probability of a collision is greater than a threshold, the vehicle path assessment system generates a warning, disables the accelerator pedal, and / or applies the brakes.
[0029] Now refer to Figures 1A to 1B When the front wheels 12 of the vehicle are in a straight line, the steering wheel 10 is usually in the centered position, such as... Figure 1C As shown in the diagram. The steering wheel 10 can be rotated two or more times from one lock position to another, as... Figure 1BAs shown in the diagram. In some examples, the steering wheel rotates -720° from the center position to the leftmost angle position and +720° from the center position to the rightmost angle position. That means that for a range of wheel angles that may or may not be close to a straight line, the steering wheel 10 may be closer to the center position. When the vehicle's actual trajectory is not actually a straight line, the driver may mistakenly assume that the vehicle's actual trajectory is a straight line or near a straight line. In other words, the vehicle's apparent trajectory is significantly different from its actual trajectory.
[0030] Now refer to Figures 2A to 2C An example of a scenario where the apparent trajectory of a vehicle differs from its actual trajectory is illustrated. Figure 2A Vehicle 30 is parked in parking space 34. Vehicle 32 is parked in other parking spaces 36 surrounding vehicle 30. Parking space 38, located in front of parking space 34, is open.
[0031] In this example, the steering wheel 10 of vehicle 30 appears to be centered (e.g., Figure 2B As shown in the diagram, this would correspond to a straight trajectory. However, the driver of the vehicle may not be aware that the wheels of vehicle 30 are at a relatively high angle relative to the straight direction. This is an example of how the apparent trajectory of vehicle 30 differs from its actual trajectory. If the driver does not understand the vehicle's actual trajectory, they may accelerate the vehicle forward and cause an accident.
[0032] The vehicle path assessment module receives sensor data from sensors such as GPS, compass, radio detection and ranging (radar), and light detection and ranging (LiDAR), images from one or more cameras, and so on. Objects in the vehicle's path and / or on each side of the vehicle are sensed, and an obstacle grid or map around the vehicle is generated.
[0033] Based on the actual and apparent position of the steering wheel, the vehicle path assessment module determines the vehicle's actual and apparent trajectory. Based on the actual and apparent trajectory and the obstacle grid, the vehicle path assessment module identifies potential collisions. If a collision is possible, based on the assessment, the vehicle path assessment module generates a warning, disables acceleration, and / or applies the vehicle's brakes. The vehicle path assessment module strikes a practical balance between usability and minimal annoyance.
[0034] Now refer to Figure 3Vehicle 30 is shown relative to an obstacle map, which includes objects in front of and / or around the vehicle. The object map is constructed by a driver assistance controller based on data from one or more sensors described further below. In this example, while the steering wheel appears to be in a near-centered position, the wheels of vehicle 30 are at an angle. The actual trajectory 94 of vehicle 30 would likely lead to an accident, while the apparent trajectory 90 of vehicle 30 would not.
[0035] Now refer to Figure 4 The vehicle 100 includes a driver assistance controller 110, which includes a vehicle path assessment module 112 configured to identify unreliable steering inputs and initiate mitigation actions such as generating a warning, disabling the accelerator pedal, and / or applying the brakes. The vehicle 100 includes sensors such as a Global Positioning System (GPS) / compass 120, which determines the position, path, and / or orientation of the vehicle 100 and outputs GPS / compass data to the driver assistance controller 110.
[0036] Vehicle 100 optionally includes one or more radar sensors 122 that generate radio frequency pulses (pointing forward, in the opposite direction, and / or laterally) and output radar return signals from objects in the corresponding directions to driver assistance controller 110. Vehicle 100 optionally includes one or more light detection and ranging (LiDAR) sensors 124 that generate light pulses (pointing forward, in the opposite direction, and / or laterally) and output return signals to driver assistance controller 110. In some examples, the LiDAR sensor 124 includes one or more lasers 130 and one or more scanners 128 that scan the one or more lasers 130 in a corresponding field of view. Vehicle 100 optionally includes one or more cameras for providing images (in the forward, opposite, and / or lateral directions) and corresponding image analysis modules configured to detect objects in the images, as shown in 132.
[0037] In some examples, the driver assistance controller 110 includes an autonomous driving module 160 configured to operate the vehicle 100 in full and / or partial autonomous driving modes by controlling the vehicle controller 164 (such as the steering wheel, brake pedal, accelerator pedal, turn signals, gear selector, etc.) based on the outputs of the one or more radar sensors 122, the one or more LiDAR sensors 124, and / or other sensors. In some examples, when the autonomous driving module 160 is not activated, the vehicle path assessment module 112 monitors untrusted steering wheel inputs.
[0038] The vehicle path assessment module 112 includes an actual and apparent trajectory calculation module 142, which is configured to determine the actual and apparent trajectory of the vehicle 100 based on the actual and apparent steering wheel position. The obstacle mesh generation module 144 is configured to generate an obstacle mesh or map based on the output of the radar sensor 122, the LiDAR sensor 124, and / or the camera / image analysis module 132.
[0039] The collision probability module 146 is configured to calculate the probability of a collision between vehicle 100 and an object based on actual and apparent trajectories. When the collision probability is greater than a predetermined probability, the mitigation module 148 selectively generates a warning, disables the accelerator pedal, and / or applies the brakes. The driver assistance controller 110 also receives data from other vehicle sensors 170, such as vehicle speed, acceleration, etc. The human-machine interface (HMI) 174 includes a display, such as a touchscreen, that receives input from the driver and / or provides warnings to the driver.
[0040] Now refer to Figures 5 to 6B The current and apparent trajectory calculation module 142 receives the current steering angle δ. c Apparent steering angle δ a And the predicted velocity V based on nominal acceleration x The current and apparent trajectory calculation module 142 is configured to generate the actual / current trajectory 210((x) based on the actual steering wheel position. i ,y i )∈T c ()( Figure 6A And output it to the collision probability module 146, and generate the apparent trajectory 214 based on the apparent steering wheel position of the vehicle. Figure 6B )((x j ,y j )∈T a This is then output to the collision probability module 146. In some examples, two instances of the plant model, the actual trajectory 210 and the apparent trajectory 214, are calculated. In some examples, the plant model includes:
[0041]
[0042] Where C f and C γ It refers to the lateral stiffness of the front and rear axles, I. f and I γ It is the distance from the center of gravity to the front and rear axles, m is the mass of the vehicle, and I is the mass of the vehicle. z It is the moment of inertia, V x and V y The longitudinal and lateral vehicle velocities are x and x', which are the longitudinal and lateral positions, respectively, and ψ and ψ' are the longitudinal and lateral vehicle velocities. These are the yaw angle and yaw rate, and δ c and δ a It is the current and actual road turning angle.
[0043] The collision probability module 146 is configured to determine the probability of a collision relative to the actual trajectory 210, the apparent trajectory 214, and the obstacle mesh or map (e.g., generating the obstacle mesh based on data from sensors (e.g., radar, LiDAR, cameras, etc.)). In some examples, the collision probability is based on the following model:
[0044]
[0045] Where D ijc and D ija P is the distance between the current and apparent trajectories and the occupied grid. a and P c Q is the apparent probability of a collision between the current path and the occupied grid. l and Q o The quality of lane and object detection is given by f(...), which is a probability function that maps the distance of the generated trajectory to the collision probability, g(...), which is a probability function that maps the apparent / current collision probability to the untrusted steering input, where P is the probability of the untrusted steering input, and T is the probability of the untrusted steering input. c and T a It is the set of (x,y) points on the current / apparent trajectory, and O g It occupies the grid.
[0046] Now refer to Figure 7 A method for detecting untrusted input to the steering wheel is shown. At 410, the method determines whether an activation condition is met. Examples of activation conditions include vehicle speed within a predetermined range, gear selector events (such as moving from park to drive or reverse), Abs (wheel angle) > a first threshold, and / or remainder (abs (steering wheel angle), 360) < a second threshold. In some examples, the first threshold is greater than or equal to 5°. In some examples, the second threshold is less than or equal to 45°.
[0047] At 414, object information is collected from sensors. At 418, a map of objects around the vehicle is generated based on the data collected from the sensors. At 422, a real vehicle path is generated from the actual steering wheel angle. At 426, an apparent vehicle path is generated from the apparent steering wheel angle. At 430, the method determines whether a collision is likely to occur within a predetermined time period (e.g., x seconds) under nominal acceleration. At 434, the method issues a warning, disables the accelerator, and / or applies the brakes.
[0048] The foregoing description is illustrative in nature and is in no way intended to limit this disclosure, its application, or use. The broad teachings of this disclosure can be implemented in various forms. Therefore, although this disclosure includes specific examples, its true scope should not be limited thereto, as other modifications will become apparent upon studying the accompanying drawings, specification, and the following claims. It should be understood that one or more steps within the method may be performed in a different order (or simultaneously) without altering the principles of this disclosure. Furthermore, while each embodiment in the examples is described above as having certain features, any one or more of those features described for any embodiment of this disclosure can be implemented in any embodiment of other embodiments, and / or combined with features of any embodiment of other embodiments, even if such combination is not explicitly described. In other words, the described embodiments are not mutually exclusive, and the arrangement of one or more embodiments with each other remains within the scope of this disclosure.
[0049] Various terms are used to describe spatial and functional relationships between elements (e.g., between modules, circuit elements, semiconductor layers, etc.), including “connection,” “engagement,” “coupling,” “adjacent,” “next to,” “on top of,” “above,” “below,” and “placed.” Unless explicitly described as “direct,” when describing the relationship between the first and second elements in the above disclosure, the relationship can be a direct relationship where no other intermediary element is present between the first and second elements, or it can be an indirect relationship where one or more intermediary elements are present (spatially or functionally) between the first and second elements. As used herein, the phrases A, B, and C at least one should be interpreted as referring to the logic (A OR B OR C) using non-exclusive logic OR, and should not be interpreted as referring to “at least one of A, at least one of B, and at least one of C.”
[0050] In the accompanying drawings, as indicated by the arrow tips, the direction of the arrows generally illustrates the flow of information of interest (such as data or instructions). For example, when components A and B exchange various information, but the information transmitted from component A to component B is relevant to the illustration, the arrow may point from component A to component B. This unidirectional arrow does not imply that no other information is transmitted from component B to component A. Furthermore, for information sent from component A to component B, component B may send a request for said information or an acknowledgment of receipt of said information to component A.
[0051] In this application, which includes the following definitions, the term "module" or "controller" may be replaced by the term "circuit". The term "module" may refer to, be part of, or include the following: application-specific integrated circuit (ASIC); digital, analog, or mixed-signal analog / digital discrete circuit; digital, analog, or mixed-signal analog / digital integrated circuit; combinational logic circuit; field-programmable gate array (FPGA); processor circuit (shared, dedicated, or group) that executes code; memory circuit (shared, dedicated, or group) that stores code executed by the processor circuit; other suitable hardware components that provide the described functionality; or combinations of some or all of the above, such as in a system-on-a-chip.
[0052] A module may include one or more interface circuits. In some examples, the interface circuits may include wired or wireless interfaces connected to a local area network (LAN), the Internet, a wide area network (WAN), or a combination thereof. The functionality of any given module in this disclosure may be distributed among multiple modules connected via interface circuits. For example, multiple modules may allow for load balancing. In another example, a server (also referred to as a remote or cloud) module may perform some functions on behalf of a client module.
[0053] As used above, the term "code" can include software, firmware, and / or microcode, and can refer to programs, routines, functions, classes, data structures, and / or objects. The term "shared processor circuit" includes a single processor circuit that executes some or all of the code from multiple modules. The term "group processor circuit" includes a processor circuit that, in conjunction with additional processor circuitry, executes some or all of the code from one or more modules. References to multiple processor circuits include multiple processor circuits on a discrete die, multiple processor circuits on a single die, multiple cores of a single processor circuit, multiple threads of a single processor circuit, or a combination of the above. The term "shared memory circuit" includes a single memory circuit that stores some or all of the code from multiple modules. The term "group memory circuit" includes a memory circuit that, in conjunction with additional memory, stores some or all of the code from one or more modules.
[0054] The term memory circuit is a subset of the term computer-readable medium. As used herein, the term computer-readable medium does not include transient electrical or electromagnetic signals propagating through a medium (such as on a carrier wave); the term computer-readable medium can therefore be considered tangible and non-transient. Non-limiting examples of non-transient tangible computer-readable media are non-volatile memory circuits (such as flash memory circuits, erasable programmable read-only memory circuits, or mask read-only memory circuits), volatile memory circuits (such as static random access memory circuits or dynamic random access memory circuits), magnetic storage media (such as analog or digital magnetic tape or hard disk drives), and optical storage media (such as CDs, DVDs, or Blu-ray discs).
[0055] The apparatus and methods described in this application can be implemented, in part or in whole, by a special-purpose computer created by configuring a general-purpose computer to perform one or more specific functions embodied in a computer program. The aforementioned function blocks, flowchart components, and other elements serve as software specifications that can be converted into computer programs through routine work by those skilled in the art or programmers.
[0056] A computer program includes processor-executable instructions stored on at least one non-transitory tangible computer-readable medium. A computer program may also include or depend on stored data. A computer program may include a basic input / output system (BIOS) for interacting with the hardware of a special-purpose computer, device drivers for interacting with specific devices of the special-purpose computer, one or more operating systems, user applications, background services, background applications, etc.
[0057] Computer programs may include: (i) descriptive text to be parsed, such as HTML (Hypertext Markup Language), XML (Extensible Markup Language), or JSON (JavaScript Object Notation); (ii) assembly code; (iii) object code generated from source code by a compiler; (iv) source code for execution by an interpreter; and (v) source code for compilation and execution by a just-in-time (JIT) compiler, etc. As an example only, source code may be written using syntax from languages including C, C++, C#, Objective-C, Swift, Haskell, Go, SQL, R, Lisp, etc. Fortran, Perl, Pascal, Curl, OCaml, HTML5 (Hypertext Markup Language, Fifth Revision), Ada, ASP (Dynamic Server Pages), PHP (PHP: Hypertext Preprocessor), Scala, Eiffel, Smalltalk, Erlang, Ruby, Visual Lua, MATLAB, SIMULINK and
Claims
1. A route evaluation system for vehicles, comprising: The trajectory calculation module is configured as follows: The actual trajectory of the vehicle is determined based on the actual position of the vehicle's steering wheel; and The apparent trajectory of the vehicle is determined based on the apparent position of the steering wheel of the vehicle. The obstacle mesh generation module is configured to generate obstacle meshes; The collision probability module is configured to determine the probability of a collision based on the obstacle grid and the actual trajectory of the vehicle. and The mitigation module is configured to, in response to a probability greater than a predetermined percentage, perform at least one of warning the driver, applying the vehicle's brakes, and requesting a change in acceleration.
2. The path evaluation system as described in claim 1, further comprising at least one of the following: LiDAR (Light Detection and Ranging) sensor; Radar detection and ranging (radar) sensors; and Camera / image sensor.
3. The path assessment system of claim 2, wherein the obstacle mesh generation module generates the obstacle mesh in response to at least one of the LiDAR sensor, the radar sensor, and the camera / image sensor.
4. The path evaluation system of claim 1, wherein the apparent position of the steering wheel corresponds to the remainder of the absolute steering wheel angle and 360 degrees.
5. The path evaluation system of claim 1, wherein the trajectory calculation module determines the actual trajectory and the apparent trajectory of the vehicle before the vehicle begins to move.
6. The path evaluation system of claim 1, wherein the trajectory calculation module determines the actual trajectory and the apparent trajectory of the vehicle by assuming the nominal acceleration of the vehicle.
7. The path evaluation system of claim 1, wherein the trajectory calculation module is enabled in response to a gear selector event.
8. The path evaluation system of claim 1, wherein the trajectory calculation module is activated in response to the gear selector moving from park to drive or reverse.
9. The path evaluation system of claim 1, wherein the trajectory calculation module is activated in response to the absolute value of the wheel angle being greater than a first threshold.
10. The path evaluation system of claim 9, wherein the first threshold is greater than or equal to 5°.