Systems and methods for active blind spot assistance

Abstract

Systems and methods for active blind spot assistance are disclosed. The method includes receiving a plurality of sensor values prior to a first time and identifying a target vehicle in a blind spot of a host vehicle based on the plurality of sensor values. The method also includes determining that the host vehicle initiates a turning maneuver at the first time and identifying a plurality of time periods between the first time and a second time. The method also includes updating the plurality of sensor values and determining a heading angle of the target vehicle relative to the host vehicle. The method also includes estimating a location of the target vehicle for each of the plurality of time periods and estimating a location of the target vehicle at the second time using each location of the target vehicle for each corresponding time period of the plurality of time periods.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to vehicle active blind spot assistance, and in particular to systems and methods for cameraless active blind spot assistance. BACKGROUND

[0002] Vehicles, such as cars, trucks, sport utility vehicles, crossovers, vans, boats, airplanes, all-terrain vehicles, recreational vehicles, or other suitable vehicles, are increasingly including blind spot assistance systems. Such systems can be configured to use various sensors, including image capture devices, such as cameras disposed proximate a front of a corresponding vehicle (e.g., a host vehicle). Generally, such systems are configured to warn an operator of the vehicle and avoid potential collisions in response to potential risks of collisions detected during, for example, execution of a lane change.

[0003] In such systems, short-range sensors, such as radio detection and ranging (radar) sensors, housed on both sides of a rear bumper of the host vehicle can monitor an area directly to the side and rear of the host vehicle. Image capture devices (e.g., cameras) can be forward-facing and can be used to detect lane markers, and based on the lane markers, a controller of the vehicle can determine a location of a target vehicle at a blind spot of the host vehicle. Such location information of the target vehicle can be used by the controller during a lane change maneuver of the host vehicle to avoid a collision between the host vehicle and the target vehicle. SUMMARY

[0004] The present disclosure relates generally to vehicle blind spot assistance.

[0005] One aspect of the disclosed embodiments includes a method for active blind spot assistance. The method includes receiving a plurality of sensor values from at least one sensor disposed proximate a rear of a host vehicle prior to a first time, and identifying a target vehicle in a blind spot of the host vehicle based on the plurality of sensor values. The method further includes determining that the host vehicle initiates a turning maneuver at the first time and identifying a plurality of time periods between the first time and a second time. The method further includes updating the plurality of sensor values using at least one transformation function, and determining a heading angle of the target vehicle relative to the host vehicle using the updated plurality of sensor values. The method further includes estimating a location of the target vehicle at each of the plurality of time periods based on the heading angle of the target vehicle relative to the host vehicle, and estimating a location of the target vehicle at the second time using each location of the target vehicle at each corresponding time period of the plurality of time periods.

[0006] In some embodiments, a system for active blind spot assistance without using image capture devices includes a processor and a memory. The memory includes instructions that, when executed by the processor, cause the processor to: receive a plurality of sensor values from at least one sensor disposed proximate a rear of a host vehicle prior to a first time; identify a target vehicle in a blind spot of the host vehicle based on the plurality of sensor values; determine that the host vehicle initiates a turning maneuver at the first time; identify a plurality of time periods between the first time and a second time; update the plurality of sensor values using at least one transformation function; determine a heading angle of the target vehicle relative to the host vehicle using the updated plurality of sensor values; estimate a position of the target vehicle at each of the plurality of time periods based on the heading angle of the target vehicle relative to the host vehicle; and estimate a position of the target vehicle at the second time using each position of the target vehicle at each corresponding time period of the plurality of time periods.

[0007] In some embodiments, a device for active blind spot assistance includes a processor and a memory. The memory includes instructions that, when executed by the processor, cause the processor to: receive a plurality of sensor values from at least one radio detection and ranging sensor disposed proximate a rear of a host vehicle prior to a first time; identify a target vehicle in a blind spot of the host vehicle based on the plurality of sensor values; determine that the host vehicle initiates a turning maneuver at the first time; identify a plurality of time periods between the first time and a second time; update the plurality of sensor values using at least one transformation function; determine a heading angle of the target vehicle relative to the host vehicle by applying a linear regression to the updated plurality of sensor values; estimate a position of the target vehicle at each of the plurality of time periods based on the heading angle of the target vehicle relative to the host vehicle; estimate a position of the target vehicle at the second time using each position of the target vehicle at each corresponding time period of the plurality of time periods; determine a time to collision between the host vehicle and the target vehicle using at least the position of the target vehicle at the second time; and in response to determining that the time to collision is less than a threshold value, apply a torque overlay to at least one motor of a steering system of the host vehicle to direct the host vehicle away from the target vehicle.

[0008] These and other aspects of the present disclosure are disclosed in the following detailed description of embodiments, accompanied by the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0009] The present disclosure is best understood from the following detailed description when read in conjunction with the accompanying drawings. It is emphasized that, according to common practice, the various features of the drawings are not to scale. On the contrary, the dimensions of the various features are arbitrarily expanded or reduced for clarity. Included in the detailed description below are specific details to provide a thorough understanding of embodiments of the present disclosure. However, various embodiments can be practiced without necessarily being limited to any one of the specific details described.

[0010] Figure 1 A vehicle in accordance with the principles of the present disclosure is generally shown.

[0011] Figure 2 An active blind spot assist system including a controller is generally shown in accordance with the principles of the present disclosure.

[0012] Figure 3A and Figure 3B A vehicle lane change maneuver is generally shown in accordance with the principles of the present disclosure.

[0013] Figure 4 A flowchart of an active blind spot assist method in accordance with the principles of the present disclosure is generally shown. DETAILED DESCRIPTION

[0014] The following discussion is presented to aid in the understanding of various embodiments of the present disclosure. Although one or more of these embodiments can be preferred, the disclosed embodiments should not be construed as limiting the scope of the present disclosure including the claims. Further, those skilled in the art will appreciate that the description herein has broad application and the discussion of any embodiment is meant only to be exemplary of that embodiment, and is not intended to suggest that the scope of the present disclosure including the claims is limited to that embodiment.

[0015] As noted above, vehicles such as cars, trucks, sport utility vehicles, crossovers, minivans, boats, airplanes, all-terrain vehicles, recreational vehicles, or other suitable vehicles are increasingly including blind spot assist systems. Such systems can be configured to use various sensors, including image capture devices such as cameras disposed adjacent to the front of a corresponding vehicle (e.g., a host vehicle). Typically, such systems are configured to warn an operator of the vehicle and avoid potential collisions in response to potential risks of a collision detected during, for example, the performance of a lane change.

[0016] In such systems, short-range sensors such as radio detection and ranging (radar) sensors housed on both sides of the host vehicle's rear bumper can monitor the area directly to the side and rear of the host vehicle. Image capture devices (e.g., cameras) can be forward-facing and can be used to detect lane markers, and based on the lane markers, a controller of the vehicle can determine the location of a target vehicle at the blind spot of the host vehicle. This location information of the target vehicle can be used by the controller during a lane change maneuver of the host vehicle to avoid a collision between the host vehicle and the target vehicle.

[0017] However, the performance of the image capture device depends on the conditions of the surroundings of the host vehicle (e.g., because the image capture device can be a passive sensor). For example, fog, direct sunlight, dust on the image capture device lens or covering the lane markings, heavy rain blocking the image capture device lens, snow on the image capture device lens or covering the lane markings, faded lane markings on the road adjacent to the host vehicle, or no lane markings on the road adjacent to the host vehicle, and / or other conditions of the environment of the host vehicle can reduce the efficacy of the image capture device (e.g., because the image capture device can not be able to capture images of the environment of the host vehicle that can be used to identify lane markings, other vehicles, etc.), which can reduce the efficacy of the blind zone assist feature of the host vehicle. Additionally or alternatively, the image capture device can experience a malfunction and / or a malfunction can occur in the communication path between the controller and the image capture device. Furthermore, some host vehicles can not include an image capture device. Such systems can use the image capture device to determine a polynomial Y = a0+ a1x + a2x 2 + a3x 3 given as a marker. Such systems can use the polynomial to identify objects adjacent to the vehicle.

[0018] Accordingly, it can be desirable to perform a blind zone assist feature without using an image capture device, such as described herein. In some embodiments, the systems and methods described herein can be configured to provide a blind zone assist using one or more sensors, such as one or more radar sensors or other suitable sensors (e.g., without using a passive image capture sensor or device).

[0019] In some embodiments, the systems and methods described herein can be configured to use a steering system of the host vehicle in response to measurements or sensed values of the one or more sensors to avoid a collision between the host vehicle and a target vehicle and / or to mitigate the consequences of a collision between the host vehicle and the target vehicle. The systems and methods described herein can be configured to use corner sensors (e.g., radar or other suitable sensors disposed at or near each side of the rear of the host vehicle) to track objects (e.g., such as a target vehicle or other suitable object) at a blind zone of the host vehicle. The systems and methods described herein can be configured to use measurements or sensed values of the corner sensors of the host vehicle to predict a possible collision during a steering maneuver performed by the host vehicle.

[0020] In some embodiments, the systems and methods described herein can be configured to receive a plurality of sensor values from at least one sensor disposed proximate a rear of a host vehicle prior to a first time. The at least one sensor can include at least one radar sensor. For example, the host vehicle can include a respective radar sensor disposed on each side of a rear of the host vehicle. The host vehicle can include an electrically assisted steering system, a steer-by-wire steering system, or other suitable steering system.

[0021] The systems and methods described herein can be configured to identify a target vehicle in a blind zone of the host vehicle based on the plurality of sensor values. The systems and methods described herein can be configured to determine that the host vehicle initiates a steering maneuver at the first time. The steering maneuver includes a lane change maneuver or other suitable steering maneuver.

[0022] The systems and methods described herein can be configured to identify a plurality of time periods between the first time and a second time. The systems and methods described herein can be configured to update the plurality of sensor values using at least one transformation function. In some embodiments, the at least one transformation function includes a homogeneous transformation matrix or other suitable transformation function. In some embodiments, the systems and methods described herein can be configured to apply a linear regression to the updated plurality of sensor values.

[0023] In some embodiments, the systems and methods described herein can be configured to determine a heading angle of the target vehicle relative to the host vehicle using the plurality of sensor values updated after applying the linear regression. The systems and methods described herein can be configured to estimate a position of the target vehicle at each time period of the plurality of time periods based on the heading angle of the target vehicle relative to the host vehicle. The systems and methods described herein can be configured to estimate a position of the target vehicle at the second time using each position of the target vehicle at each corresponding time period of the plurality of time periods.

[0024] In some embodiments, the systems and methods described herein can be configured to estimate a speed of the target vehicle relative to the host vehicle using the updated plurality of sensor values and a constant speed model. The systems and methods described herein can be configured to determine a speed of the host vehicle. The systems and methods described herein can be configured to estimate a position of the host vehicle at each time period of the plurality of time periods using a constant turn radius model.

[0025] In some embodiments, the systems and methods described herein can be configured to determine, for each time period of the plurality of time periods, a time at which a collision between the host vehicle and the target vehicle is to occur based on one or more of the estimated speed of the target vehicle, the speed of the host vehicle, the position of the target vehicle at each time period of the plurality of time periods, the position of the host vehicle at each time period of the plurality of time periods, other suitable information, or any combination thereof.

[0026] In some embodiments, the systems and methods described herein can be configured to determine whether a time to collision for a respective time period of the plurality of time periods is less than a threshold value. The systems and methods described herein can be configured to initiate at least one steering control operation in response to determining that the time to collision for a respective time period of the plurality of time periods is less than the threshold value. The at least one steering control operation includes applying a torque override to the at least one motor of the steering system of the host vehicle, other suitable steering control operations, or a combination thereof. The steering control operation (e.g., including applying a torque override to the at least one motor of the steering system) can be configured to direct the host vehicle away from the target vehicle.

[0027] Figure 1 A vehicle 10 according to the principles of the present disclosure is generally shown. The vehicle 10 can include any suitable vehicle, such as a car, a truck, a sport utility vehicle, a van, a crossover, any other passenger vehicle, any suitable commercial vehicle, or any other suitable vehicle. Although the vehicle 10 is illustrated as a passenger vehicle having wheels and used on a road, the principles of the present disclosure can be applied to other vehicles, such as an airplane, a boat, a train, a drone, or other suitable vehicles.

[0028] The vehicle 10 includes a vehicle body 12 and a hood 14. A passenger compartment 18 is at least partially defined by the vehicle body 12. Another portion of the vehicle body 12 defines an engine compartment 20. The hood 14 is movably attached to a portion of the vehicle body 12 such that the hood 14 provides access to the engine compartment 20 when the hood 14 is in a first or open position, and the hood 14 covers the engine compartment 20 when the hood 14 is in a second or closed position. In some embodiments, the engine compartment 20 can be disposed at a rear portion of the vehicle 10 (as compared to what is typically shown).

[0029] The passenger compartment 18 can be disposed rearward of the engine compartment 20, but in embodiments in which the engine compartment 20 is disposed at a rear portion of the vehicle 10, the passenger compartment 18 can be disposed forward of the engine compartment 20. The vehicle 10 can include any suitable propulsion system, including an internal combustion engine, one or more electric motors (e.g., an electric vehicle), one or more fuel cells, a hybrid (which includes a combination of an internal combustion engine and one or more electric motors and is, for example, a hybrid vehicle) propulsion system, and / or any other suitable propulsion system.

[0030] In some embodiments, vehicle 10 can include a gasoline fuel engine, such as a spark-ignition engine. In some embodiments, vehicle 10 can include a diesel fuel engine, such as a compression-ignition engine. Engine compartment 20 houses and / or encloses at least some components of the propulsion system of vehicle 10. Additionally or alternatively, propulsion control devices, such as accelerator actuators (e.g., accelerator pedal), brake actuators (e.g., brake pedal), steering wheel, and other such components, are disposed in passenger compartment 18 of vehicle 10. The propulsion control devices can be actuated or controlled by a driver of vehicle 10 and can be directly connected to corresponding components of the propulsion system, such as throttle, brakes, axles, and vehicle transmission, among others. In some embodiments, the propulsion control devices can transmit signals to a vehicle computer (e.g., steer-by-wire driving), which in turn can control corresponding propulsion components of the propulsion system. As such, in some embodiments, vehicle 10 can be an autonomous vehicle.

[0031] In some embodiments, vehicle 10 includes a transmission in communication with the crankshaft via a flywheel or clutch or a hydrodynamic coupling. In some embodiments, the transmission includes a manual transmission. In some embodiments, the transmission includes an automatic transmission. In the case of a combustion engine or hybrid vehicle, vehicle 10 can include one or more pistons that operate in conjunction with the crankshaft to generate a force that is transmitted through the transmission to one or more axles to turn wheels 22. When vehicle 10 includes one or more electric motors, a vehicle battery and / or a fuel cell provides energy to the electric motor(s) to turn wheels 22.

[0032] Vehicle 10 can include an automatic vehicle propulsion system, such as a cruise control, adaptive cruise control, automatic brake control, other automatic vehicle propulsion system, or combination thereof. Vehicle 10 can be an autonomous vehicle or a semi-autonomous vehicle, or other suitable type of vehicle. Vehicle 10 can include additional or fewer features than those generally shown and / or disclosed herein.

[0033] In some embodiments, vehicle 10 can include an Ethernet component 24, a controller area network (CAN) bus 26, a media oriented systems transport component (MOST) 28, a FlexRay component 30 (e.g., a steer-by-wire brake system, among others), and a local interconnect network component (LIN) 32. Vehicle 10 can use CAN bus 26, MOST 28, FlexRay component 30, LIN 32, other suitable network or communication system, or combination thereof, to transmit various information from, for example, sensors within or outside the vehicle, to, for example, various processors or controllers within or outside the vehicle. Vehicle 10 can include additional or fewer features than those generally shown and / or disclosed herein.

[0034] In some embodiments, vehicle 10 can include a steering system, such as an EPS system, a steer-by-wire steering system (e.g., which can include one or more controllers that control components of the steering system without using a mechanical connection between a hand-held steering wheel of vehicle 10 and wheels 22 or that are in communication with the one or more controllers), or other suitable steering system. The system can include an open loop feedback control system or mechanism, a closed loop feedback control system or mechanism, or a combination thereof. The steering system can be configured to receive various inputs, including but not limited to a hand-held steering wheel position, an input torque, one or more wheel positions, other suitable inputs or information, or a combination thereof. Additionally or alternatively, the inputs can include a hand-held steering wheel torque, a hand-held steering wheel angle, a motor speed, a vehicle speed, an estimated motor torque command, other suitable inputs, or a combination thereof. The steering system can be configured to provide steering functionality and / or control to vehicle 10. For example, the steering system can generate an assist torque based on the various inputs. The steering system can be configured to selectively control a motor of the steering system using the assist torque to provide steering assist to an operator of vehicle 10.

[0035] In some embodiments, vehicle 10 can include a controller, such as controller 100 as generally shown in Figure 2 In some embodiments, vehicle 10 can include a controller, such as controller 100 as generally shown in Figure 2 Controller 100 can include any suitable controller, such as an electronic control unit or other suitable controller. Controller 100 can be configured to control various functions of, for example, a steering system and / or various functions of vehicle 10. Controller 100 can include a processor 102 and a memory 104. Processor 102 can include any suitable processor, such as those described herein. Additionally or alternatively, controller 100 can include any suitable number of processors in addition to or instead of processor 102. Memory 104 can include a single disk or multiple disks (e.g., hard drives) and include a storage management module that manages one or more partitions within memory 104. In some embodiments, memory 104 can include flash memory, semiconductor (solid state) memory, or the like. Memory 104 can include random access memory (RAM), read only memory (ROM), or a combination thereof. Memory 104 can include instructions that, when executed by processor 102, cause processor 102 to control at least various aspects of vehicle 10.

[0036] The controller 100 can receive one or more signals from various measurement devices or sensors 106 indicative of sensed or measured characteristics of the vehicle 10. The sensors 106 can include any suitable sensors, measurement devices, and / or other suitable mechanisms. For example, the sensors 106 can include one or more torque sensors or devices, one or more hand-held steering wheel position sensors or devices, one or more motor position sensors or devices, one or more position sensors or devices, other suitable sensors or devices, or combinations thereof. The one or more signals can be indicative of hand-held steering wheel torque, steering wheel angle, motor speed, vehicle speed, other suitable information, or combinations thereof.

[0037] In some embodiments, the sensors 106 can include one or more image capture devices (e.g., such as a camera), one or more audio input devices (e.g., such as a microphone), one or more global positioning devices, one or more proximity sensing devices, one or more radar sensors, one or more light detection and ranging sensors, one or more ultrasonic sensors, other suitable sensors or devices, or combinations thereof.

[0038] In some embodiments, the controller 100 can be configured to perform a blind spot assist feature of the vehicle 10. For example, the controller 100 can receive measured or sensed values from the sensors 106. As described above, the sensors 106 can include one or more radar sensors disposed proximate a rear of the vehicle 10. For example, a first sensor 106 can be disposed on a first side of the vehicle 10, at or proximate a first rear corner of the vehicle 10, and a second sensor 106 can be disposed on a second side of the vehicle 10 opposite the first side, at or proximate a second rear corner of the vehicle 10 opposite the first corner. It should be understood that although a first sensor and a second sensor are described, the vehicle 10 can include any suitable number of sensors 106 or other suitable sensors. The controller 100 can use the measured or sensed values of the sensors 106 to determine one or more locations of objects proximate the vehicle 10. The controller 100 can selectively control various aspects of a steering system of the vehicle 10 based on the measured or sensed values of the sensors 106 to avoid collisions with the objects or mitigate the consequences of collisions with the objects.

[0039] In some embodiments, as in Figure 3AAs generally shown, at a time t (which can be referred to as a first time), the controller 100 can use values received from the sensor 106 to track one or more positions of the target vehicle 200 (e.g., prior to the time t). In some embodiments, the controller 100 can use a ring buffer or other suitable mechanism to track values from the sensor 106 indicative of positions of the target vehicle 200. The controller 100 determines (e.g., based on inputs provided by various components of the steering system or other suitable components of the vehicle 10) that the vehicle 10 (which can be referred to as a host vehicle 10 or host vehicle) is initiating a steering maneuver, such as a lane change maneuver or other suitable steering maneuver, at a time t + dt (which can be referred to as a second time).

[0040] At the time t + dt, the controller 100 can update the values received from the sensor 106 (e.g., and corresponding positions or states of the target vehicle 200) using one or more transformation functions. For example, the controller 100 can update the values of the sensor 106 using any suitable transformation function (including, but not limited to, a homogeneous transformation matrix), which can be defined as:

[0041]

[0042] where h indicates a vehicle speed of the vehicle 10 at the time t + dt, k is a constant set to 0 (e.g., or other suitable value), and a indicates a yaw rate of the vehicle 10 at the time t + dt. The vehicle speed, yaw rate, and / or other suitable characteristics of the vehicle 10 can be provided to the controller 100, which can be various sensors or components of the vehicle 10.

[0043] In some embodiments, after the values of the sensor 106 (e.g., and corresponding states or positions of the target vehicle 200) are updated, the controller 100 can apply a linear regression to the updated values of the sensor 106 (e.g., and corresponding states or positions of the target vehicle 200). The controller 100 can use results of applying the linear regression to the updated values of the sensor 106 to calculate a relative heading angle of the target vehicle 200 (e.g., relative to a heading angle of the vehicle 10). The calculation of the relative heading angle of the target vehicle 200 can be defined as:

[0044]

[0045] where y indicates a position component of the vehicle 10 along the y-axis as Figure 3A As generally shown in the equation above, and x indicates a position component of the vehicle 10 along the x-axis as Figure 3A As generally shown in the equation above, and x indicates a position component of the vehicle 10 along the x-axis as

[0046] In some embodiments, the controller 100 can be configured to, for each time period of a plurality of time periods between time t and time t+dt, predict or estimate a position of the target vehicle 200 and a position of the vehicle 10. For example, the time periods can correspond to subdivisions of time between time t and time t+dt. The controller 100 can estimate the position of the target vehicle 200 for each time period and the position of the vehicle 10 for each time period using values of the sensors 106, results of applying linear regression to values of the sensors 106, a heading angle of the target vehicle 200 relative to the vehicle 10, other suitable information, or a combination thereof.

[0047] In some embodiments, the controller 100 can avoid and / or mitigate consequences of a potential collision between the target vehicle 200 and the vehicle 10 based on the position of the target vehicle 200 at each time period, the position of the vehicle 10 at each time period, a speed of the target vehicle 200 relative to the vehicle 10, a speed of the vehicle 10, other suitable information, or a combination thereof. The controller 100 can determine a speed of the target vehicle 200 relative to the vehicle 10. The speed of the target vehicle 200 relative to the vehicle 10 can be defined as:

[0048] VehSpd TV = SQRT[(RelSpd.x) 2 +(RelSpd.y) 2 ]

[0049] where VehSpd TV corresponds to a speed of the target vehicle 200, RelSpdX corresponds to an X component of a relative (e.g., relative to the vehicle 10) speed of the target vehicle 200, and RelSpdY corresponds to a Y component of the relative (e.g., relative to the vehicle 10) speed of the target vehicle 200. The controller 100 can determine the speed of the vehicle 10 based on one or more values received from one or more various sensors of the vehicle 10. The controller 100 can calculate for the vehicle 10:

[0050] a radius (Radius),

[0051] S' y , EV = R - R.Cos(dΦ)

[0052] S' x , EV = R.Sin(dΦ)

[0053] The controller 100 can further calculate a yaw rate (YawRate) in steady state, r = [(V / L)*{1 / (1+KV2 / 57.3Lg)}]*δ, δ corresponds to a steering angle (degrees), V corresponds to a speed of the vehicle 10, L corresponds to a wheelbase (feet), K corresponds to an understeer gradient (degrees / g), g corresponds to a gravitational acceleration constant (e.g., 32.2 (feet / sec2)), R corresponds to an associated circular motion, S'yEV corresponds to a Y component of a distance traveled between t and dt, S'xEV corresponds to an X component of a distance traveled between t and dt, and dΦ (e.g., a heading angle) = r*dt. 2 The controller 100 can determine a distance between the front point 202 of the target vehicle 200 and the respective points 204 of the vehicle 10, as generally shown in

[0054] The controller 100 can determine a distance between the front point 202 of the target vehicle 200 and the respective points 204 of the vehicle 10, as generally shown in Figure 3B In some embodiments, the controller 100 can use a constant radius model to predict a position of the vehicle 10 (e.g., and / or a distance between the vehicle 10 and the target vehicle 200) for each time period. In some embodiments, the controller 100 can use a constant speed model to determine a position of the target vehicle 200 (e.g., and / or a distance between the vehicle 10 and the target vehicle 200) for each time period. For example, the controller 100 can determine a distance between the front point 202 of the target vehicle 200 and a first upper corner point 204' of the vehicle 10. The distance between the front point 202 and the first upper corner point 204' of the vehicle 10 can be defined as:

[0055] S' y,EV,firstupper = S' y,EV + (dl)*sin(dΦ) + (w)*cos(dΦ)

[0056] S' x,EV,firstupper = S' x,EV + (dl)*cos(dΦ) + (w)*(-sin(dΦ))

[0057] which can define a new position of the first upper corner point 204' of the vehicle 10.

[0058] The controller 100 can determine a distance between the front point 202 of the vehicle 10 and a second lower corner point 204". The distance between the front point 202 and the second lower corner point 204" can be defined as:

[0059] S' y,EV,secondlower = S' y，EV + (-d2)*sin(dΦ) + (-w)*cos(dΦ)

[0060] S' x,EV,secondlower = S' x，EV+ (-d2) * cos(dΦ) + (-w) * (-sin(dΦ))

[0061] which can define a new position of the second lower corner point 204" of the vehicle 10.

[0062] where d1 corresponds to a distance between a center of a rear axle of the vehicle 10 and a front end of the vehicle 10, d2 corresponds to a distance between a center of the rear axle of the vehicle 10 and a rear end of the vehicle 10, and w corresponds to a half of a width of the vehicle 10.

[0063] In some embodiments, the controller 100 can determine a path of the target vehicle 200 based on a vehicle speed of the target vehicle 200 relative to the vehicle 10 and a heading angle of the target vehicle 200 relative to the vehicle 10. The path of the target vehicle 200 can be defined as:

[0064] S' x,TV = S' 0x + VehSpd TV . Cos(headngAngle TV ). dt

[0065] S' y,TV = S' 0y + VehSpd TV . Sin(headAngle TV ). dt

[0066] The controller 100 can determine whether the predicted distance between the target vehicle 200 and the vehicle 10 is less than a threshold distance. If the controller 100 determines that the predicted distance between the target vehicle 200 and the vehicle 10 is equal to or greater than the threshold distance, the controller 100 can allow the vehicle 10 to perform a steering maneuver.

[0067] Optionally, if the controller 100 determines that the predicted distance between the target vehicle 200 and the vehicle 10 is less than the threshold distance, the controller 100 can initiate at least one steering control operation to avoid or mitigate the consequences of a potential collision indicated by the predicted distance between the target vehicle 200 and the vehicle 10 being less than the threshold distance. For example, the controller 100 can determine a suitable amount of torque override to apply to at least one motor of a steering system of the vehicle 10 to direct the vehicle 10 away from the target vehicle 200. The controller 100 can apply the torque override to the motor of the steering system. The vehicle 10 can change course to avoid a collision with the target vehicle 200. Additionally or alternatively, in addition to or instead of applying the torque override, the controller 100 can initiate other control steering operations, such as providing an indication to an operator of the vehicle 10 that a collision is possible (e.g., using one or more output devices of the vehicle 10).

[0068] In some embodiments, the controller 100 receives a plurality of sensor values from at least one sensor 106 disposed proximate a rear of the host vehicle 10 prior to the first time. The at least one sensor can include at least one radar sensor. For example, the host vehicle 10 can include a respective radar sensor disposed on each side of a rear of the host vehicle 10. The host vehicle 10 can include an electrically assisted steering system, a steer-by-wire steering system, or other suitable steering system.

[0069] The controller 100 can identify the target vehicle 200 in a blind zone of the host vehicle 10 based on the plurality of sensor values. The controller 100 can determine that the host vehicle 10 initiates a steering maneuver at the first time. The steering maneuver includes a lane change maneuver or other suitable steering maneuver.

[0070] The controller 100 can identify a plurality of time periods between the first time and the second time. The controller 100 can update the plurality of sensor values using at least one transformation function. In some embodiments, the at least one transformation function includes a homogeneous transformation matrix or other suitable transformation function. In some embodiments, the controller 100 can apply a linear regression to the updated plurality of sensor values.

[0071] In some embodiments, the controller 100 can determine a heading angle of the target vehicle 200 relative to the host vehicle 10 using the plurality of sensor values updated after applying the linear regression. The controller 100 can estimate a position of the target vehicle 200 at each of the plurality of time periods based on the heading angle of the target vehicle 200 relative to the host vehicle 10. The controller 100 can use each position of the target vehicle 200 at each corresponding time period of the plurality of time periods to estimate a position of the target vehicle 200 at the second time.

[0072] In some embodiments, the controller 100 can estimate a speed of the target vehicle 200 relative to the host vehicle 10 using the updated plurality of sensor values and the constant speed model. The controller 100 can determine a speed of the host vehicle 10. The controller 100 can estimate a position of the host vehicle 10 at each of the plurality of time periods using the constant turning radius model.

[0073] In some embodiments, the controller 100 can determine a time to collision between the host vehicle 10 and the target vehicle 200 for each of the plurality of time periods based on one or more of the estimated speed of the target vehicle 200, the speed of the host vehicle 10, the position of the target vehicle 200 at each of the plurality of time periods, the position of the host vehicle 10 at each of the plurality of time periods, other suitable information, or any combination thereof.

[0074] In some embodiments, the controller 100 can determine whether the time to collision for a respective time period of the plurality of time periods is less than a threshold value. The controller 100 can initiate at least one steering control operation in response to determining that the time to collision for a respective time period of the plurality of time periods is less than a threshold value. The at least one steering control operation can include applying a torque override to at least one motor of a steering system of the host vehicle 10, other suitable steering control operations, or a combination thereof. The steering control operation (e.g., including applying a torque override to at least one motor of a steering system) can be configured to direct the host vehicle 10 away from the target vehicle 200.

[0075] In some embodiments, the controller 100 can perform the methods described herein. However, the methods described herein as performed by the controller 100 are not meant to be limiting, and any type of software executing on a controller or processor can perform the methods described herein without departing from the scope of the present disclosure. For example, a controller such as a processor executing software within a computing device can perform the methods described herein.

[0076] Figure 4 is a flowchart generally showing an active blind spot assistance method 300 in accordance with the principles of the present disclosure. At 302, the method 300 receives a plurality of sensor values from at least one sensor disposed proximate a rear of a host vehicle prior to a first time. For example, the controller 100 can receive a plurality of sensor values from the sensor 106.

[0077] At 304, the method 300 identifies a target vehicle in a blind spot of the host vehicle based on the plurality of sensor values. For example, the controller 100 can identify the target vehicle 200 in a blind spot of the vehicle 10 based on the plurality of sensor values.

[0078] At 306, the method 300 determines that the host vehicle is initiating a turning maneuver at the first time. For example, the controller 100 can determine that the vehicle 10 is initiating a turning maneuver.

[0079] At 308, the method 300 identifies a plurality of time periods between the first time and the second time. For example, the controller 100 can identify a plurality of time periods between the first time and the second time.

[0080] At 310, the method 300 updates the plurality of sensor values using the at least one transformation function. For example, the controller 100 can update the plurality of sensor values using the at least one transformation function.

[0081] At 312, the method 300 determines a heading angle of the target vehicle relative to the host vehicle using the updated plurality of sensor values. For example, the controller 100 can determine a heading angle of the target vehicle 200 relative to the vehicle 10 using the updated plurality of sensor values.

[0082] At 314, the method 300 estimates a position of the target vehicle at each of the plurality of time periods based on the heading angle of the target vehicle relative to the vehicle 10. For example, the controller 100 can estimate a position of the target vehicle 200 at each of the plurality of time periods based on the heading angle of the target vehicle 200 relative to the vehicle 10.

[0083] At 316, the method 300 estimates a position of the target vehicle at the second time using each position of the target vehicle at each respective time period of the plurality of time periods. For example, the controller 100 can estimate a position of the target vehicle at the second time using each position of the target vehicle 200 at each corresponding time period of the plurality of time periods.

[0084] In some embodiments, the method 300 can estimate a speed of the target vehicle relative to the host vehicle using the updated plurality of sensor values and a constant speed model. For example, the controller 100 can estimate a speed of the target vehicle 200 relative to the vehicle 10 using the updated plurality of sensor values and a constant speed model.

[0085] In some embodiments, the method 300 can determine a speed of the host vehicle and can estimate a position of the host vehicle at each of the plurality of time periods using a constant turning radius model. For example, the controller 100 can determine a speed of the vehicle 10 and can estimate a position of the vehicle 10 at each of the plurality of time periods using a constant turning radius model.

[0086] In some embodiments, the method 300 can determine, for each time period of the plurality of time periods, a time at which a collision is to occur between the host vehicle and the target vehicle based on at least one of an estimated speed of the target vehicle, a speed of the host vehicle, a location of the target vehicle at each time period of the plurality of time periods, and a location of the host vehicle at each time period of the plurality of time periods. For example, the controller 100 can determine, for each time period of the plurality of time periods, a time at which a collision is to occur between the vehicle 10 and the target vehicle 200 based on at least one of an estimated speed of the target vehicle 200, a speed of the vehicle 10, a location of the target vehicle 200 at each time period of the plurality of time periods, and a location of the vehicle 10 at each time period of the plurality of time periods.

[0087] In some embodiments, the method 300 can determine whether the time at which a collision is to occur for a respective time period of the plurality of time periods is less than a threshold value. For example, the controller 100 can determine whether the time at which a collision is to occur for a respective time period of the plurality of time periods is less than a threshold value.

[0088] In some embodiments, the method 300 can initiate the at least one steering control operation in response to determining that the time at which a collision is to occur for a respective time period of the plurality of time periods is less than a threshold value. For example, the controller 100 can initiate the at least one steering control operation in response to determining that the time at which a collision is to occur for a respective time period of the plurality of time periods is less than a threshold value.

[0089] In some embodiments, a method for active blind spot assistance includes receiving a plurality of sensor values from at least one sensor disposed proximate a rear of a host vehicle prior to a first time and identifying a target vehicle in a blind spot of the host vehicle based on the plurality of sensor values. The method further includes determining that the host vehicle is initiating a steering maneuver at the first time and identifying a plurality of time periods between the first time and a second time. The method further includes updating the plurality of sensor values using at least one transformation function and determining a heading angle of the target vehicle relative to the host vehicle using the updated plurality of sensor values. The method further includes estimating a location of the target vehicle at each time period of the plurality of time periods based on the heading angle of the target vehicle relative to the host vehicle and estimating a location of the target vehicle at the second time using each location of the target vehicle at each respective time period of the plurality of time periods.

[0090] In some embodiments, the at least one transformation function comprises a homogeneous transformation matrix. In some embodiments, determining a heading angle of the target vehicle relative to the host vehicle using the updated plurality of sensor values comprises applying a linear regression to the updated plurality of sensor values. In some embodiments, the method further comprises estimating a speed of the target vehicle relative to the host vehicle using the updated plurality of sensor values and a constant speed model. In some embodiments, the method further comprises determining a speed of the host vehicle and estimating a position of the host vehicle at each of the plurality of time periods using a constant turning radius model. In some embodiments, the method further comprises, for each of the plurality of time periods, determining a time to collision between the host vehicle and the target vehicle based on at least one of the estimated speed of the target vehicle, the speed of the host vehicle, the position of the target vehicle at each of the plurality of time periods, and the position of the host vehicle at each of the plurality of time periods. In some embodiments, the method further comprises determining whether the time to collision for a respective time period of the plurality of time periods is less than a threshold value and initiating at least one steering control operation in response to determining that the time to collision for the respective time period of the plurality of time periods is less than the threshold value. In some embodiments, the at least one steering control operation comprises applying a torque override to at least one motor of a steering system of the host vehicle, wherein the torque override is configured to direct the host vehicle away from the target vehicle. In some embodiments, the at least one sensor comprises at least one radio detection and ranging sensor. In some embodiments, the steering maneuver comprises a lane change maneuver. In some embodiments, the host vehicle comprises an electric power steering system. In some embodiments, the host vehicle comprises a steer-by-wire steering system.

[0091] In some embodiments, a system for active blind spot assistance without using image capture devices comprises a processor and a memory. The memory comprises instructions that, when executed by the processor, cause the processor to: receive a plurality of sensor values from at least one sensor disposed proximate a rear of a host vehicle prior to a first time; identify a target vehicle in a blind spot of the host vehicle based on the plurality of sensor values; determine that the host vehicle initiates a steering maneuver at the first time; identify a plurality of time periods between the first time and a second time; update the plurality of sensor values using at least one transformation function; determine a heading angle of the target vehicle relative to the host vehicle using the updated plurality of sensor values; estimate a position of the target vehicle at each of the plurality of time periods based on the heading angle of the target vehicle relative to the host vehicle; and estimate a position of the target vehicle at the second time using each position of the target vehicle at each respective time period of the plurality of time periods.

[0092] In some embodiments, the at least one transformation function comprises a homogeneous transformation matrix. In some embodiments, the instructions further cause the processor to determine a heading angle of the target vehicle relative to the host vehicle using the updated plurality of sensor values by applying at least a linear regression to the updated plurality of sensor values. In some embodiments, the instructions further cause the processor to determine, for each of the plurality of time periods, a time to collision between the host vehicle and the target vehicle based on at least one of an estimated speed of the target vehicle, a speed of the host vehicle, a location of the target vehicle at each of the plurality of time periods, and a location of the host vehicle at each of the plurality of time periods. In some embodiments, the instructions further cause the processor to determine whether the time to collision for a respective time period of the plurality of time periods is less than a threshold value, and to initiate at least one steering control operation in response to determining that the time to collision for the respective time period of the plurality of time periods is less than the threshold value. In some embodiments, the at least one steering control operation comprises applying a torque override to at least one motor of a steering system of the host vehicle, wherein the torque override is configured to direct the host vehicle away from the target vehicle. In some embodiments, the at least one sensor comprises at least one radio detection and ranging sensor.

[0093] In some embodiments, an apparatus for active blind spot assistance includes a processor and a memory. The memory includes instructions that, when executed by the processor, cause the processor to receive a plurality of sensor values from at least one radio detection and ranging sensor disposed proximate a rear of a host vehicle prior to a first time; identify a target vehicle in a blind spot of the host vehicle based on the plurality of sensor values; determine that the host vehicle is initiating a steering maneuver at the first time; identify a plurality of time periods between the first time and a second time; update the plurality of sensor values using at least one transformation function; determine a heading angle of the target vehicle relative to the host vehicle by applying a linear regression to the updated plurality of sensor values; estimate a location of the target vehicle at each of the plurality of time periods based on the heading angle of the target vehicle relative to the host vehicle; estimate a location of the target vehicle at the second time using each location of the target vehicle at each respective time period of the plurality of time periods; determine a time to collision between the host vehicle and the target vehicle using at least the location of the target vehicle at the second time; and apply a torque override to at least one motor of a steering system of the host vehicle to direct the host vehicle away from the target vehicle in response to determining that the time to collision is less than a threshold value.

[0094] The word “example” is used herein to mean serving as an example, instance, or illustration. Any aspect or design described herein as “example” is not necessarily to be construed as preferred or advantageous over other aspects or designs. Rather, use of the word “example” is intended to present concepts in a concrete fashion. As used in this application, the term “or” is intended to mean an inclusive “or” rather than an exclusive “or”. That is, unless specified otherwise, or clear from context, “X includes A or B” is intended to mean any of the natural inclusive permutations. That is, if X includes A; X includes B; or X includes both A and B, then “X includes A or B” is satisfied under any of the foregoing instances. In addition, the articles “a” and “an” as used in this application and the appended claims should generally be construed to mean “one or more” unless specified otherwise or clear from context to be directed to a singular form. Moreover, use of the term “an implementation” or “one implementation” throughout is not intended to mean the same implementation or implementation unless so described.

[0095] Implementations of the systems, algorithms, methods, and instructions described herein can be realized in hardware, software, or any combination thereof. The hardware can include, for example, computers, intellectual property (IP) cores, application-specific integrated circuits (ASICs), programmable logic arrays, optical processors, programmable logic controllers, microcode, microcontrollers, servers, microprocessors, digital signal processors or any other suitable circuit. In the claims, the term “processor” should be understood as encompassing any of the foregoing hardware either alone or in combination. The terms “signal” and “data” are used interchangeably.

[0096] As used herein, the term module can include a packaged functional hardware unit designed for use in other components, a set of instructions executable by a controller (e.g., a processor executing software or firmware), processing circuitry configured to perform a specified function, and a self-contained hardware or software component that interfaces with a larger system, for example. For example, a module can include an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a circuit, a digital logic circuit, an analog circuit, a combination of discrete circuits, a gate array, and other types of hardware or combinations thereof. In other embodiments, a module can include memory storing instructions that can be executed by a controller to implement features of the module.

[0097] Further, in an aspect, for example, a system described herein can be implemented using a general purpose computer or a general purpose processor with a computer program that, when being executed, carries out any corresponding steps of any of the methods, algorithms and / or instructions described herein. Additionally or alternatively, for example, a special purpose computer / processor can be utilized which can contain other hardware for carrying out any of the methods, algorithms, or instructions described herein.

[0098] Furthermore, all or portions of the embodiments of the present application can take the form of a computer program product accessible from, for example, a computer-usable or computer-readable medium. A computer-usable or computer-readable medium can be, for example, but is not limited to, any apparatus that can contain, store, communicate, or transport the program for use by or in connection with any processor. The medium can be, for example, an electronic, magnetic, optical, electromagnetic, or semiconductor apparatus or device. Other suitable mediums, however, can be used as well.

[0099] The above-described embodiments, implementations and aspects have been described to allow easy understanding of the present disclosure and are not limiting of the present disclosure. On the contrary, the present disclosure is intended to cover various modifications and equivalent arrangements included within the scope of the appended claims, which scope is to be accorded the broadest interpretation so as to encompass all such modifications and equivalent structures as are permitted under the law.

Claims

1. A method for active blind spot assistance, the method comprising: receiving a plurality of sensor values from at least one sensor disposed proximate a rear of a host vehicle prior to a first time; identifying a target vehicle in a blind spot of the host vehicle based on the plurality of sensor values; determining that the host vehicle initiates a turning maneuver at the first time; identifying a plurality of time periods between the first time and a second time; updating the plurality of sensor values using at least one transformation function; determining a heading angle of the target vehicle relative to the host vehicle using the updated plurality of sensor values; estimating a position of the target vehicle at each of the plurality of time periods based on the heading angle of the target vehicle relative to the host vehicle; estimating a position of the target vehicle at the second time using each position of the target vehicle at each corresponding time period of the plurality of time periods; and in response to determining that a distance to an occurrence of a collision between the host vehicle and the target vehicle based on the position of the target vehicle at the second time is less than a threshold value, controlling at least one motor of a steering system of the host vehicle to direct the host vehicle away from the target vehicle. the at least one transformation function comprises a homogeneous transformation matrix.

2. The method of claim 1, wherein, determining the heading angle of the target vehicle relative to the host vehicle using the updated plurality of sensor values comprises applying a linear regression to the updated plurality of sensor values.

3. The method of claim 1, wherein, 4. The method of claim 1, further comprising estimating a speed of the target vehicle relative to the host vehicle using the updated plurality of sensor values and a constant speed model.

5. The method of claim 4, further comprising: determining a speed of the host vehicle; and estimating a position of the host vehicle at each of the plurality of time periods using a constant turning radius model.

6. The method of claim 5, further comprising: for each of the plurality of time periods, determining a distance to an occurrence of a collision between the host vehicle and the target vehicle based on at least one of the estimated speed of the target vehicle, the speed of the host vehicle, the position of the target vehicle at each of the plurality of time periods, the position of the host vehicle at each of the plurality of time periods. controlling the at least one motor of the steering system of the host vehicle comprises applying a torque override to the at least one motor of the steering system of the host vehicle, wherein the torque override is configured to direct the host vehicle away from the target vehicle. the at least one sensor comprises at least one radio detection and ranging sensor.

7. The method of claim 1, wherein, the turning maneuver comprises a lane change maneuver.

8. The method of claim 1, wherein, the host vehicle comprises an electronic power steering system.

9. The method of claim 1, wherein, the host vehicle comprises a steer-by-wire steering system.

10. The method of claim 1, wherein, 12. A system for active blind spot assistance without using image capture devices, the system comprising:

11. The method of claim 1, wherein, a processor; and a memory comprising instructions that, when executed by the processor, cause the processor to: receive a plurality of sensor values from at least one sensor disposed proximate a rear of a host vehicle prior to a first time; ​ ​ ​ identify a target vehicle in a blind zone of the host vehicle based on the plurality of sensor values; determine that the host vehicle initiated a turning maneuver at a first time; identify a plurality of time periods between the first time and a second time; update the plurality of sensor values using at least one transformation function; determine a heading angle of the target vehicle relative to the host vehicle using the updated plurality of sensor values; estimate a position of the target vehicle at each of the plurality of time periods based on the heading angle of the target vehicle relative to the host vehicle; estimate a position of the target vehicle at the second time using each position of the target vehicle at each corresponding time period of the plurality of time periods; and in response to determining that a distance to a collision between the host vehicle and the target vehicle is less than a threshold value based on the position of the target vehicle at the second time, control at least one motor of a steering system of the host vehicle to direct the host vehicle away from the target vehicle.

13. The system of claim 12, wherein, the at least one transformation function comprises a homogeneous transformation matrix.

14. The system of claim 12, wherein, the instructions further cause the processor to determine the heading angle of the target vehicle relative to the host vehicle using the updated plurality of sensor values by applying at least a linear regression to the updated plurality of sensor values.

15. The system of claim 12, wherein, the instructions further cause the processor to: determine, for each of the plurality of time periods, a distance to a collision between the host vehicle and the target vehicle based on at least one of an estimated speed of the target vehicle, a speed of the host vehicle, the position of the target vehicle at each of the plurality of time periods, and a position of the host vehicle at each of the plurality of time periods.

16. The system of claim 12, wherein, controlling at least one motor of a steering system of the host vehicle comprises applying a torque override to at least one motor of a steering system of the host vehicle, wherein the torque override is configured to direct the host vehicle away from the target vehicle.

17. The system of claim 12, wherein, the at least one sensor comprises at least one radio detection and ranging sensor.

18. An apparatus for active blind spot assistance, the apparatus comprising: a processor; and a memory including instructions that, when executed by the processor, cause the processor to: receive a plurality of sensor values from at least one radio detection and ranging sensor disposed proximate a rear of a host vehicle prior to a first time; identify a target vehicle in a blind zone of the host vehicle based on the plurality of sensor values; determine that the host vehicle initiated a turning maneuver at a first time; identify a plurality of time periods between the first time and a second time; update the plurality of sensor values using at least one transformation function; determine a heading angle of the target vehicle relative to the host vehicle by applying a linear regression to the updated plurality of sensor values; estimate a position of the target vehicle at each of the plurality of time periods based on the heading angle of the target vehicle relative to the host vehicle; estimate a position of the target vehicle at the second time using each position of the target vehicle at each corresponding time period of the plurality of time periods; determining, using at least a location of the target vehicle at the second time, a distance at which a collision between the host vehicle and the target vehicle is to occur; and in response to determining that the distance at which the collision is to occur is less than a threshold, applying a torque override to at least one motor of a steering system of the host vehicle to direct the host vehicle away from the target vehicle.

Images