Evasive steering assist modification based on manual steering input

Abstract

The techniques and systems herein enable ESA modification based on manual steering input. In particular, a score is determined for manual steering input to the host vehicle while the ESA is actively applying ESA steering input to the host vehicle. The score quantifies an amount of additional steering input (e.g., additional steering angle, steering wheel torque) relative to the ESA steering input. The ESA steering input is maintained, modified, or canceled based on the score. By doing so, the system is able to effectively adapt the ESA to manual steering input, allowing for effective collision mitigation while ensuring that the vehicle operates as the driver intended.

Description

Background Technology

[0001] Driver assistance technologies are increasingly being applied to vehicles to improve safety. Evasive Steering Assist (ESA) is one such driver assistance technology that enables a vehicle to automatically steer to avoid collisions with objects. For example, if a collision with an object is imminent, ESA is activated to provide steering input to the vehicle to avoid it. Typically, when an ESA system is activated, the vehicle's driver provides additional (manual) steering input (e.g., through the steering wheel). Adjusting the ESA based on these additional steering inputs is crucial to ensuring that safety is maintained while still allowing for adequate driver control. Summary of the Invention

[0002] This document relates to systems, apparatuses, techniques, and methods for implementing ESA modification based on manual steering input. These systems and apparatuses may include components or devices (e.g., processing systems) for performing the techniques and methods described herein. Some aspects described below include a system comprising at least one processor configured to determine that the ESA of a primary vehicle is providing ESA steering input to the primary vehicle to avoid a collision with a target. The processor is also configured to: determine a manual steering input provided to the primary vehicle by the driver of the primary vehicle and a fraction of that manual steering input. The fraction quantifies the amount of additional steering input provided by the manual steering input relative to the ESA steering input. The processor is further configured to: determine whether the fraction satisfies a first threshold for adjusting the ESA steering input. In response to determining that the fraction does not satisfy the first threshold, the processor is configured to suppress modification of the ESA steering input. Alternatively, in response to determining that the fraction satisfies the first threshold, the processor is configured to determine whether the fraction satisfies a second threshold for canceling the ESA steering input. In response to determining that the fraction does not satisfy the second threshold, the processor is configured to modify the ESA steering input to provide an ESA steering input different from the original ESA steering input. Alternatively, in response to determining that the score meets the second threshold, the processor is configured to cancel the ESA turn input.

[0003] This technology and method can be performed by the aforementioned system, another system or component, or a combination thereof. Some aspects described below include a method comprising: determining that the ESA of a primary vehicle is providing ESA steering input to the primary vehicle to avoid a collision with a target. The method further comprises: determining a manual steering input provided to the primary vehicle by the driver of the primary vehicle and determining a fraction of that manual steering input. This fraction quantifies the amount of additional steering input provided by the manual steering input relative to the ESA steering input. The method further comprises: determining whether the fraction satisfies a first threshold for adjusting the ESA steering input and whether the fraction satisfies a second threshold for canceling the ESA steering input. The method further comprises: modifying the ESA steering input based on whether the fraction satisfies the second threshold to provide an ESA steering input different from the original ESA steering input.

[0004] The component may include a computer-readable storage medium comprising instructions that, when executed by the system described above, another system or component, or a combination thereof, implement the methods described above and other methods. Some aspects described below include a computer-readable storage medium comprising instructions that, when executed by a processor, cause the processor to determine that the ESA of the primary vehicle is providing ESA steering input to the primary vehicle to avoid a collision with a target. The instructions also cause the processor to determine a manual steering input provided to the primary vehicle by the driver of the primary vehicle and a fraction of that manual steering input. This fraction quantifies the amount of additional steering input provided by the manual steering input relative to the ESA steering input. The instructions further cause the processor to determine whether the fraction satisfies a first threshold for adjusting the ESA steering input. In response to determining that the fraction does not satisfy the first threshold, the instructions cause the processor to suppress modification of the ESA steering input. Alternatively, in response to determining that the fraction satisfies the first threshold, the instructions cause the processor to determine whether the fraction satisfies a second threshold for canceling the ESA steering input. In response to determining that the fraction does not satisfy the second threshold, the instructions cause the processor to modify the ESA steering input to provide an ESA steering input different from the original ESA steering input. Alternatively, in response to determining that the score meets the second threshold, the instruction causes the processor to cancel the ESA redirection input.

[0005] This invention provides a simplified concept for implementing ESA modifications based on manual steering input, which is further described in the detailed description and accompanying drawings. This invention is not intended to identify essential features of the claimed subject matter, nor is it intended to define the scope of the claimed subject matter. Attached Figure Description

[0006] The following figures illustrate the systems and techniques for implementing ESA modifications based on manual steering inputs, and these figures consistently use some of the same numbers to represent examples of analogous or similar functions and components. Figure 1 An example environment that can use ESA modifications based on manual steering input according to the technology of this disclosure is shown. Figure 2 An example ESA modification based on the technology disclosed herein is shown. Figure 3 An example system of a primary vehicle configured to implement ESA modification based on manual steering input is shown, according to the technology of this disclosure. Figure 4 An example data stream for ESA modification based on manual steering input is shown according to the techniques of this disclosure. Figure 5 An example method for modifying ESA based on manual steering input according to the technology of this disclosure is shown. Detailed Implementation Overview

[0007] ESA systems apply steering input to a vehicle to mitigate a potential collision with an object. During this intervention, the driver can provide additional steering input to the vehicle (e.g., via the steering wheel). However, doing so can cause conventional ESA systems to operate erratically. For example, many conventional ESA systems cancel ESA when the steering torque provided by the driver exceeds a threshold. In many cases, simply canceling ESA can be dangerous because the driver may inadvertently react to the ESA intervention.

[0008] The techniques and systems described in this paper enable ESA modification based on manual steering input. Specifically, a fraction is assigned to the manual steering input of the primary vehicle when the ESA actively applies the ESA steering input. This fraction quantifies the amount of additional steering input (e.g., additional steering angle, steering wheel torque) relative to the ESA steering input. The ESA steering input is maintained, modified, or canceled based on the fraction. By doing so, the system can effectively adapt the ESA to the manual steering input, thereby allowing for effective collision mitigation while ensuring the vehicle operates as the driver intends. Example Environment

[0009] Figure 1Example environment 100 is shown, in which ESA modifications based on manual steering input can be used. Example environment 100 contains a primary vehicle 102 and a target 104. The primary vehicle 102 can be any type of system (car, sedan, truck, motorcycle, electric bicycle, boat, air vehicle, etc.). The target 104 can be any type of moving or stationary object (car, sedan, truck, motorcycle, electric bicycle, boat, pedestrian, cyclist, boulder, etc.).

[0010] In example environment 100, the main vehicle 102 determines that a collision with the target 104 is imminent and activates ESA. ESA generates path 106 to avoid the target 104 and provides steering input to the main vehicle 102 to follow path 106.

[0011] In addition to the ESA steering input, manual steering input is also provided by the driver of the main vehicle 102. For example, the driver may wish to modify path 106 or manually control the main vehicle 102. In some cases, there may be another object or target (e.g., on the left side of the path), which may cause the driver to want to get closer to avoid target 104 (e.g., by pushing path 106 to the right). In other cases, the driver may want to further avoid target 104 (e.g., by pushing the path further to the left).

[0012] The total steering input (e.g., provided by the ESA and the driver) is indicated by the steering angle 108 and the manual steering torque 110. The steering angle 108 can be the angle of the steering wheel relative to zero (e.g., a straight path). The steering angle 108 is a combination of the steering angle provided by the ESA and the steering angle provided by the driver. Therefore, the manual steering angle (e.g., the steering angle provided other than by the ESA) can be the difference between the steering angle 108 and the expected steering angle for following path 106. The manual steering torque 110 indicates the amount of torque provided to the steering column of the main vehicle 102.

[0013] The ESA module 112, at least partially implemented in hardware, of the primary vehicle calculates a fraction 114 of the manual steering input (e.g., additional steering input provided by the driver relative to the ESA steering input). This fraction is based on the steering angle 108, the expected steering angle from the ESA (e.g., the steering angle for following path 106), and the manual steering torque 110. The calculation of fraction 114 is further described below.

[0014] ESA module 112 uses score 114 to determine whether to maintain the ESA steering input (e.g., at 116), modify the ESA steering input (e.g., at 118), or cancel the ESA steering input (e.g., at 120). Maintaining the ESA steering input may involve the ESA continuing to steer the main vehicle 102 along path 106. Canceling the ESA steering input may involve the ESA stopping the ESA steering input to allow the driver to manually steer the main vehicle 102. Modifying the ESA steering input may involve ESA module 112 modifying path 106. Modification of the ESA steering input will be discussed further below.

[0015] By using a score 114 to maintain, modify, or cancel the ESA steering input, the technique described herein enables the ESA module 112 to tune the ESA steering input based on additional manual steering input. In doing so, a collision with target 104 can still be mitigated, while the driver of the primary vehicle 102 provides further control over how the primary vehicle 102 avoids target 104. Furthermore, using a steering angle 108 when calculating the score 114 allows the ESA module 112 to more accurately determine the driver's intent, which can lead to improved safety and driver satisfaction.

[0016] Figure 2 This is an example illustration 200 of ESA modification (e.g., at 118). As described above, modifying ESA can involve adjusting path 106 based on manual steering input. As shown, path 106 has a corresponding destination point 202. Destination point 202 represents a point on path 106 that is laterally adjacent to target 104 and located at a longitudinal distance close to target 104. In many cases, path 106 may end when the main vehicle 102 has no target 104 laterally. Therefore, the end of path 106 can be destination point 202. Regardless of the longitudinal position of destination point 202 relative to the main vehicle 102, destination point 202 has a certain lateral distance 204. Lateral distance 204 can be calculated relative to any datum (e.g., centerline 206) of the main vehicle 102 or target 104.

[0017] ESA module 112 uses steering angle 108 and path 106 to determine the manual steering angle (or uses a manual steering angle calculated as part of fraction 114). Similarly, the manual steering angle is an angle provided by the driver, other than the angle expected via ESA. This manual steering angle is used to generate a modified destination 208, which has a modified lateral distance 210 relative to a reference (e.g., centerline 206). For example, the modified lateral distance 210 can be calculated based on Equation 1. y+c*Angle Add(1) Where y is the lateral distance 204, c is a constant, and Angle Add It is an additional steering angle provided by the driver (e.g., steering angle 108 minus the steering angle expected via ESA and / or path 106).

[0018] Based on the modified destination 208 relative to the current position of the main vehicle 102, the ESA module 112 generates a polynomial 212 of the curve from the current position to the modified destination 208. The polynomial 212 can be of any order (e.g., a 4th or 5th order polynomial). The ESA module 112 can then use the polynomial 212 to create a modified path 214 for following for itself or an associated ESA system.

[0019] By generating a modified path 214 based on an additional steering angle, the ESA module enables the primary vehicle 102 to better adapt to driver input during an ESA event. For example, the driver of the primary vehicle 102 might intend to modify the ESA without canceling it. Since many conventional systems simply cancel the ESA due to driver input, the technique described herein can enable increased safety and driver satisfaction. Example System

[0020] Figure 3 An example system 300 is illustrated, configured to be disposed within a main vehicle 102 and configured to implement ESA modification based on manual steering input. Components of the example system 300 may be arranged anywhere within or on the main vehicle 102. The example system 300 may include at least one processor 302, a computer-readable storage medium 304 (e.g., multiple media, one medium), and vehicle components 306. These components are operatively and / or communicatively coupled via a link 308.

[0021] Processor 302 (e.g., application processor, microprocessor, digital signal processor (DSP), controller) is coupled to computer-readable storage medium 304 via link 308 and executes instructions (e.g., code) stored in computer-readable storage medium 304 (e.g., a non-transient storage device such as a hard disk drive, solid-state drive (SSD), flash memory, read-only memory (ROM)) to implement or otherwise cause the ESA module (or a portion thereof) to perform the techniques described herein. Although shown as residing within computer-readable storage medium 304, ESA module 112 may be a separate component (e.g., having a dedicated computer-readable storage medium including instructions and / or executing on dedicated hardware such as a dedicated processor, pre-programmed field-programmable gate array (FPGA), system-on-a-chip (SOC), etc.). The processor 302 and the computer-readable storage medium 304 can be any number of components, including multiple components distributed throughout the main vehicle 102, located remotely from the main vehicle 102, dedicated or shared with other components, modules or systems of the main vehicle 102, and / or configured in a manner different from that shown in the figures without departing from the scope of this disclosure.

[0022] The computer-readable storage medium 304 also contains sensor data 310 generated by one or more sensors (not shown), which may be local or remote relative to the example system 300. The sensor data 310 indicates or otherwise makes it possible to determine information that can be used to perform the techniques described herein. For example, the sensors may generate sensor data 310 indicating a steering angle 108 (e.g., at the steering rack, steering column, or at the wheel) and manual steering torque (e.g., in the steering column). The sensor data 310 can be used to determine other properties, as discussed below.

[0023] In some implementations, sensor data 310 may originate from a remote source (e.g., via link 308). Example system 300 may include a communication system (not shown) that receives sensor data 310 from target 104 or another remote source.

[0024] Vehicle component 306 includes one or more systems or components communicatively coupled to ESA module 112 and configured to apply the output of ESA module 112 to control master vehicle 102 (e.g., to adjust ESA steering inputs, follow path 106, or follow modified path 214). For example, vehicle component 306 may include an ESA system with means for steering master vehicle 102 (e.g., hydraulic devices, servos, actuators). Vehicle component 306 is communicatively coupled to ESA module 112 via link 308. Although shown as a separate component, ESA module 112 may be part of vehicle component 306, or vice versa.

[0025] By using the example system 300, the primary vehicle 102 can adapt to manual steering inputs provided by the driver. For example, the example system 300 can maintain, modify, or cancel ESA intervention based on manual steering inputs. This allows the driver to have more control over the primary vehicle 102 during an ESA event while still ensuring that the ESA functions as intended (e.g., guiding the primary vehicle 102 to avoid target 104), thereby maintaining or improving the safety of the primary vehicle 102. Example data stream

[0026] Figure 4 This is an example data flow 400 based on a modified ESA using manual redirection input. Example data flow 400 can be implemented in any of the environments previously described and can be implemented by any of the systems or components previously described. For example, example data flow 400 can be implemented in example environment 100 according to example illustration 200 and / or by example system 300. Example data flow 400 can also be implemented in other environments, by other systems or components, and using other data flows or technologies. Example data flow 400 can be implemented by one or more entities (e.g., ESA module 112). The order of operations shown and / or described is not intended to be construed as limiting and can be rearranged without departing from the scope of this disclosure. Furthermore, any number of operations can be combined with any other number of operations to implement the example data flow or alternative data flows.

[0027] Example data flow 400 begins with attribute 402 of the environment (e.g., example environment 100) obtained by ESA module 112. As shown, attribute 402 includes steering angle 108, manual steering torque 110, path 106, and ESA activation 404. ESA activation 404 is an indication that the ESA is active (e.g., the ESA is providing ESA steering input to the main vehicle 102). As discussed above, when activated, the ESA creates path 106. Therefore, the presence of path 106 can serve as ESA activation 404. In other scenarios, a separate indication (e.g., ESA activation 404) may be used. Path 106 may be received from another module or component that generates path 106 (e.g., the ESA activation module), or path 106 may be generated by ESA module 112 (e.g., ESA module 112 is also configured to activate ESA).

[0028] Attribute 402 can be acquired, received, or determined by ESA module 112. For example, ESA module 112 can determine attribute 402 directly from sensor data 310, from a bus or interface of a sensor connected to example system 300, or from another module or system of example system 300. Regardless of how or where attribute 402 is collected, received, exported, or calculated, ESA module 112 is configured to use attribute 402 to maintain ESA steering input (e.g., at 116), modify ESA steering input (e.g., at 118), or cancel ESA steering input (e.g., at 120).

[0029] For this purpose, attribute 402 is input into the fraction module 406. The fraction module 406 is configured to generate a fraction 114 that indicates the manual steering input provided by the driver. The fraction 114 can be calculated using Equation 2. Where α is a weighting constant that weights the additional steering angle and the manual steering torque 110, and σ(x) is the Sigmoid function, for example, To saturate x and return it to a value in the range of 0 to 1, β1 and β2 are tuning constants. It's Angle Add ,in It has a steering angle of 108 degrees and is the expected steering angle from ESA (e.g., for following path 106), n is multiple data points representing the moving average of the manual steering torque 110 (e.g., for the latest 0.1 seconds), Torque i It is the manual steering torque.

[0030] Therefore, the score 114 can be based on a moving average of the additional steering angle (relative to the ESA steering input) provided by the driver and the manual steering torque 110. In some implementations, the instantaneous manual steering torque 110 can be used to calculate the score (instead of a moving average). According to Equation 2, the score 114 can be between 0 and 1. When different saturation functions are used, the score 114 can be between different values ​​(e.g., -1 to 1). Different equations can be used to calculate the score (e.g., based on the additional steering angle and the manual steering torque 110) without deviating from the scope of this disclosure. By using the additional steering angle and the manual steering torque 110, the ESA module can more accurately determine the driver's intention (e.g., to maintain, modify, or cancel the ESA) and react accordingly. Furthermore, when using a moving average, transient spikes in the manual steering torque 110 can be compensated for (e.g., due to the driver being startled by the ESA activation).

[0031] The score 114 is input to the ESA steering module 408, which compares the score 114 with a plurality of thresholds 410. The thresholds 410 may include a first threshold and a second threshold, the first threshold indicating modification of the ESA, and the second threshold being higher than the first threshold and indicating cancellation of the ESA. In response to the score 114 not meeting the first threshold, the ESA steering module 408 may determine to maintain the ESA (e.g., at 116). Doing so may involve causing the vehicle component 306 to maintain the ESA steering input (e.g., to follow path 106). In response to the score 114 meeting the second threshold, the ESA steering module 408 may determine to cancel the ESA (e.g., at 120). Doing so may involve causing the vehicle component 306 to stop providing ESA steering input.

[0032] In response to score 114 meeting the first threshold but not the second threshold, ESA steering module 408 can determine to modify the ESA (e.g., at 118), as described above. For example, path modification module 412 can base its modification on an additional steering angle provided by the driver (e.g., angle). Add The modified path 214 is generated by determining the modified destination location 208 and the destination location 202. The modified path 214 can be sent to the vehicle component 306 or otherwise used to control the vehicle component 306 so that the vehicle component 306 can make the main vehicle 102 follow the modified path 214.

[0033] Although shown as being located within ESA module 112, the fractional module 406, ESA steering module 408, and / or path modification module 412 may be separate from ESA module 112. For example, the fractional module 406, ESA steering module 408, and / or path modification module 412 may be independent components and / or implemented via dedicated hardware.

[0034] By using the aforementioned technology, the ESA can be adapted to additional steering inputs provided by the driver of the main vehicle 102. More specifically, the ESA can be maintained, modified, or canceled based on additional steering angles and manual steering torque 110 provided by the driver. In this way, the ESA can still be maintained while allowing the driver better control over how the ESA mitigates a potential collision with the target 104. This allows for increased safety and experience for passengers of the main vehicle 102, the target 104, and / or others near the main vehicle 102. Example Method

[0035] Figure 5 This is an example method 500 for ESA modification based on manual steering input. Example method 500 can be implemented in any of the environments previously described, by any of the systems or components previously described, and by utilizing any of the data flows, process flows, or techniques previously described. For example, example method 500 can be implemented in example environment 100 (as shown by example illustration 200), by example system 300, and / or by following example data flow 400. Example method 500 can also be implemented in other environments, by other systems or components, and by utilizing other data flows, process flows, or techniques. Example method 500 can be implemented by one or more entities (e.g., ESA module 112). The order of operations shown and / or described is not intended to be construed as limiting and can be rearranged without departing from the scope of this disclosure. Furthermore, any number of operations can be combined with any other number of operations to implement the example process flow or alternative process flows.

[0036] At 502, it is determined that the manual steering input is provided by the driver while the ESA is providing ESA steering input. For example, the ESA module 112 may determine that ESA activation 404 is present and / or path 106 is present, and determine the steering angle 108 and manual steering torque 110.

[0037] At 504, a fraction of the manual steering input is determined. For example, fraction module 406 may determine fraction 114 based on the manual steering angle (e.g., steering angle 108 minus the steering angle expected from the ESA steering input) and manual steering torque 110 (e.g., instantaneous or time-averaged).

[0038] At point 506, it is determined that the score meets the first threshold. For example, the ESA steering module 408 can determine that score 114 meets the first threshold of threshold 410.

[0039] At point 508, it is determined whether the score meets the second threshold. For example, the ESA steering module 408 can determine whether score 114 meets the second threshold of threshold 410.

[0040] At 510, the ESA steering input is adjusted based on whether the score meets a second threshold. For example, ESA module 112 (or ESA steering module 408) may cause vehicle component 306 to modify the ESA steering input (e.g., at 118) in response to score 114 not meeting the second threshold. This modification may involve path modification module 412 creating a modified path 214. Alternatively, ESA module 112 (or ESA steering module 408) may cause vehicle component 306 to cancel the ESA steering input (e.g., at 120) in response to score 114 meeting the second threshold. Cancellation may involve allowing the driver full control of the vehicle without ESA steering input.

[0041] By using Example Method 500, the ESA can effectively adapt to manual steering inputs provided by the driver during ESA events / activations. In doing so, the driver gains more vehicle control than with conventional techniques, while still allowing the ESA to operate as designed (e.g., to effectively avoid collisions with targets). Example

[0042] Example 1: A method comprising: determining that an evasive steering assist (ESA) of a primary vehicle is providing ESA steering input to the primary vehicle to avoid a collision with a target; determining a manual steering input provided to the primary vehicle by the driver of the primary vehicle; determining a fraction of the manual steering input, the fraction quantifying the amount of additional steering input provided by the manual steering input relative to the ESA steering input; determining that the fraction satisfies a first threshold for modifying the ESA steering input; determining whether the fraction satisfies a second threshold for canceling the ESA steering input; and adjusting the ESA steering input based on whether the fraction satisfies the second threshold to provide an ESA steering input different from the ESA steering input before modification.

[0043] Example 2: The method of Example 1, where the score is based on the additional steering angle and additional steering torque corresponding to the manual steering input.

[0044] Example 3: The method of Example 1 or 2, wherein the additional steering angle includes the difference between the current steering angle of the main vehicle and the steering angle provided by the ESA steering input.

[0045] Example 4: The method of Example 1, 2 or 3, wherein the additional steering torque includes the amount of torque applied to the steering wheel of the primary vehicle.

[0046] Example 5: Any of the methods in the preceding examples, wherein the additional steering torque comprises a moving average of the torque applied to the steering wheel.

[0047] Example 6: Any of the methods in the preceding examples, wherein adjusting the ESA steering input includes: canceling the ESA steering input in response to determining that the score meets the second threshold.

[0048] Example 7: Any of the methods in the foregoing examples further includes determining a path corresponding to the ESA steering input, wherein adjusting the ESA steering input includes modifying the path in response to determining that the score does not meet the second threshold.

[0049] Example 8: Any of the methods in the preceding examples, where the path modification is based on the difference between the current steering angle of the primary vehicle and the steering angle corresponding to the ESA steering input.

[0050] Example 9: The method of any of the foregoing examples, wherein modifying the path includes: determining the destination location of the path; generating the modified destination location based on the difference between the current steering angle of the main vehicle and the steering angle corresponding to the ESA steering input; generating a polynomial representing the modified path from the current location of the main vehicle to the modified destination location; and adapting the path to the polynomial.

[0051] Example 10: A system including at least one processor configured to: determine that an evasive steering assist (ESA) of a primary vehicle is providing ESA steering input to the primary vehicle to avoid a collision with a target; determine a manual steering input provided to the primary vehicle by the driver of the primary vehicle; determine a fraction of the manual steering input, the fraction quantifying the amount of additional steering input provided by the manual steering input relative to the ESA steering input; determine whether the fraction satisfies a first threshold for adjusting the ESA steering input; and, in response to determining that the fraction does not satisfy the first threshold, suppress the adjustment of the ESA steering input; or, in response to determining that the fraction satisfies the first threshold: determine whether the fraction satisfies a second threshold for canceling the ESA steering input; and, in response to determining that the fraction does not satisfy the second threshold, modify the ESA steering input to provide an ESA steering input different from the ESA steering input before modification; or, in response to determining that the fraction satisfies the second threshold, cancel the ESA steering input.

[0052] Example 11: The system of Example 10, where the score is based on the additional steering angle and additional steering torque corresponding to the manual steering input.

[0053] Example 12: The system of Example 10 or 11, where the score is further based on a weighted average of the additional steering angle and additional steering torque.

[0054] Example 13: The system of Example 10, 11 or 12, wherein the additional steering angle includes the difference between the current steering angle of the main vehicle and the steering angle corresponding to the ESA steering input.

[0055] Example 14: A system of any of Examples 10-13, wherein the additional steering torque includes the amount of torque applied to the steering wheel of the primary vehicle.

[0056] Example 15: A system of any of Examples 10-14, wherein the additional steering torque comprises a moving average of the torque applied to the steering wheel.

[0057] Example 16: A system of any one of Examples 10-15, wherein the processor is further configured to determine a path corresponding to the ESA turning input in response to determining that the score does not meet the second threshold, wherein the modification of the ESA turning input includes modifying the path.

[0058] Example 17: A system of any of Examples 10-16, wherein the path modification is based on the difference between the current steering angle of the primary vehicle and the steering angle corresponding to the ESA steering input.

[0059] Example 18: A system of any of Examples 10-17, wherein path modification includes: determining the destination of the path; and generating a modified destination based on the difference between the current steering angle of the primary vehicle and the steering angle corresponding to the ESA steering input.

[0060] Example 19: A system of any one of Examples 10-18, wherein modifying the path further includes: generating a polynomial representing the modified path from the current location of the primary vehicle to the modified destination; and adapting the path to the polynomial.

[0061] Example 20: A computer-readable storage medium comprising instructions that, when executed by at least one processor, cause the processor to: determine that an evasive steering assist (ESA) of a primary vehicle is providing ESA steering input to the primary vehicle to avoid a collision with a target; determine a manual steering input provided to the primary vehicle by the driver of the primary vehicle; determine a fraction of the manual steering input, the fraction quantifying the amount of additional steering input provided by the manual steering input relative to the ESA steering input; determine whether the fraction satisfies a first threshold for adjusting the ESA steering input; and, in response to determining that the fraction does not satisfy the first threshold, suppress the adjustment of the ESA steering input; or, in response to determining that the fraction satisfies the first threshold: determine whether the fraction satisfies a second threshold for canceling the ESA steering input; and, in response to determining that the fraction does not satisfy the second threshold, modify the ESA steering input to provide an ESA steering input different from the ESA steering input before modification; or, in response to determining that the fraction satisfies the second threshold, cancel the ESA steering input.

[0062] Example 21: A system comprising: a processor configured to perform a method of any one of Examples 1-9.

[0063] Example 22: A computer-readable storage medium comprising instructions that, when executed by at least one processor, cause the processor or an associated system to perform any of the methods in Examples 1-9.

[0064] Example 23: A system comprising means for performing the method of any one of Examples 1-9.

[0065] Example 24: A method executed by a system of any one of Examples 10-19. Conclusion

[0066] While various embodiments of the present disclosure have been described in the foregoing description and illustrated in the accompanying drawings, it should be understood that the present disclosure is not limited thereto, but can be practiced in various ways within the scope of the following claims. It will be apparent from the foregoing description that various modifications can be made without departing from the spirit and scope of the present disclosure as defined by the following claims.

[0067] Unless the context explicitly states otherwise, the use of "or" and grammatically related terms indicates an unrestricted, non-exclusive alternative. As used herein, the phrase referring to "at least one" of a list of items means any combination of those items, including a single member. For example, "at least one of a, b, or c" is intended to cover: a, b, c, ab, ac, bc, and abc, as well as any combination with multiple identical elements (e.g., aa, aaa, aab, aac, abb, acc, bb, bbb, bbc, cc, and ccc, or any other ordering of a, b, and c).

Claims

1. A method for modifying evasive steering assist based on manual steering input, the method comprising: Determine that the Evasive Steering Assist (ESA) of the primary vehicle is providing ESA steering input to the primary vehicle to avoid a collision with the target; Determine the manual steering input provided by the driver of the main vehicle to the main vehicle; Determine the expected steering angle provided by the ESA steering input to the main vehicle; Determine the manual steering torque applied by the driver to the steering column of the main vehicle; The additional steering angle provided by the driver relative to the ESA steering input is determined based on the difference between the manual steering input and the expected steering angle; A score is calculated using the Sigmoid function based on the additional steering angle and the manual steering torque. The score quantifies the amount of additional steering input provided by the manual steering input relative to the ESA steering input and is calculated based on the sum of: (i) the product of a weighting constant and the Sigmoid function of the additional steering angle; and (ii) a minus the product of the weighting constant and the Sigmoid function of the manual steering torque. The score is determined to satisfy a first threshold for modifying the ESA steering input; Determine whether the score meets the second threshold for canceling the ESA steering input; as well as Based on whether the score meets the second threshold, the ESA steering input is adjusted to provide a different ESA steering input than the ESA steering input before adjustment.

2. The method as described in claim 1, characterized in that, The additional steering angle includes the difference between the current steering angle of the main vehicle and the steering angle provided by the ESA steering input.

3. The method as described in claim 1, characterized in that, The manual steering torque includes the moving average of the torque applied to the steering wheel of the primary vehicle.

4. The method as described in claim 1, characterized in that, Adjusting the ESA steering input includes canceling the ESA steering input in response to determining that the score meets the second threshold.

5. The method of claim 1, further comprising: Determine a path corresponding to the ESA steering input, wherein adjusting the ESA steering input includes modifying the path in response to determining that the score does not meet the second threshold.

6. The method as described in claim 5, characterized in that, The path is modified based on the difference between the current steering angle of the primary vehicle and the steering angle corresponding to the ESA steering input.

7. The method as described in claim 6, characterized in that, Modifying the path includes: Determine the destination of the route; A modified destination is generated based on the difference between the current steering angle of the main vehicle and the steering angle corresponding to the ESA steering input; Generate a polynomial representing the modified path from the current location of the main vehicle to the modified destination; and Make the path fit the polynomial.

8. A system for modifying evasive steering assist based on manual steering input, the system comprising at least one processor configured to: Determine that the Evasive Steering Assist (ESA) of the primary vehicle is providing ESA steering input to the primary vehicle to avoid a collision with the target; Determine the manual steering input provided by the driver of the main vehicle to the main vehicle; Determine the expected steering angle provided by the ESA steering input to the main vehicle; Determine the manual steering torque applied by the driver to the steering column of the main vehicle; The additional steering angle provided by the driver relative to the ESA steering input is determined based on the difference between the manual steering input and the expected steering angle; A score is calculated using the Sigmoid function based on the additional steering angle and the manual steering torque. The score quantifies the amount of additional steering input provided by the manual steering input relative to the ESA steering input and is calculated based on the sum of: (i) the product of a weighting constant and the Sigmoid function of the additional steering angle; and (ii) a minus the product of the weighting constant and the Sigmoid function of the manual steering torque. Determine whether the score meets a first threshold for adjusting the ESA steering input; and In response to determining that the score does not meet the first threshold, the adjustment of the ESA steering input is suppressed; or In response to determining that the score satisfies the first threshold: Determine whether the score meets the second threshold for canceling the ESA steering input; and In response to determining that the score does not meet the second threshold, the ESA steering input is modified to provide a different ESA steering input than the one before modification; or In response to determining that the score meets the second threshold, the ESA steering input is canceled.

9. The system as described in claim 8, characterized in that, The score is further based on a weighted average of the additional steering angle and the manual steering torque.

10. The system as described in claim 8, characterized in that, The additional steering angle includes the difference between the current steering angle of the main vehicle and the steering angle corresponding to the ESA steering input.

11. The system as described in claim 8, characterized in that, The manual steering torque includes the moving average of the torque applied to the steering wheel of the primary vehicle.

12. The system as described in claim 8, characterized in that, The processor is further configured to: In response to determining that the score does not meet the second threshold, a path corresponding to the ESA steering input is determined; and The ESA steering input is modified by changing the path.

13. The system as described in claim 12, characterized in that, The processor is further configured to modify the path based on the difference between the current steering angle of the primary vehicle and the steering angle corresponding to the ESA steering input.

14. The system as described in claim 13, characterized in that, The processor is further configured to modify the path in the following ways: Determine the destination of the route; and A modified destination is generated based on the difference between the current steering angle of the main vehicle and the steering angle corresponding to the ESA steering input.

15. The system as described in claim 14, characterized in that, The processor is further configured to modify the path in the following ways: Generate a polynomial representing the modified path from the current location of the main vehicle to the modified destination; as well as Make the path fit the polynomial.

16. A computer-readable storage medium comprising instructions that, when executed by at least one processor, cause the processor to: Determine that the Evasive Steering Assist (ESA) of the primary vehicle is providing ESA steering input to the primary vehicle to avoid a collision with the target; Determine the manual steering input provided by the driver of the main vehicle to the main vehicle; Determine the expected steering angle provided by the ESA steering input to the main vehicle; Determine the manual steering torque applied by the driver to the steering column of the main vehicle; The additional steering angle provided by the driver relative to the ESA steering input is determined based on the difference between the manual steering input and the expected steering angle; A score is calculated using the Sigmoid function based on the additional steering angle and the manual steering torque. The score quantifies the amount of additional steering input provided by the manual steering input relative to the ESA steering input and is calculated based on the sum of: (i) the product of a weighting constant and the Sigmoid function of the additional steering angle; and (ii) a minus the product of the weighting constant and the Sigmoid function of the manual steering torque. Determine whether the score meets a first threshold for adjusting the ESA steering input; and In response to determining that the score does not meet the first threshold, the adjustment of the ESA steering input is suppressed; or In response to determining that the score satisfies the first threshold: Determine whether the score meets the second threshold for canceling the ESA steering input; and In response to determining that the score does not meet the second threshold, the ESA steering input is modified to provide a different ESA steering input than the one before modification; or In response to determining that the score meets the second threshold, the ESA steering input is canceled.

Images