System and method for generating a vehicle alert

Abstract

Systems and methods of alerting vehicle occupants of an obstacle on a side of the vehicle. The systems and methods include receiving turn indication data from at least one vehicle system, receiving perception data from a perception system of the vehicle, predicting a turn of the vehicle based on the turn prediction data, generating an obstacle alert output through an output device of the vehicle when an obstacle is detected within a first size detection region or a second size detection region using the perception data, and generating the obstacle alert in response to predicting the turn of the vehicle from switching from using the first size detection region to using the second size detection region. The second size detection region is expanded compared to the first size detection region.

Description

Technical Field

[0001] This disclosure generally relates to vehicles, systems, and methods for warning vehicle occupants of obstacles. In particular, this disclosure relates to vehicles, systems, and methods for performing blind spot detection. Background Technology

[0002] Vehicles include alarm systems that detect objects near the vehicle and alert the driver to those objects. Alarms are typically generated based on the object's location and a specific driving maneuver that is occurring or about to occur. Such alarm systems can include, but are not limited to, side blind spot warning systems, lane change warning systems, and other systems using forward, side, and rear-view cameras and other sensing devices. Typically, sensing devices are positioned and / or calibrated to detect objects within a defined area around the vehicle. For example, the defined area may be intended to include the adjacent lane on one side of the vehicle. If the detection area is too large, the driver may be bothered by harmful alarms about obstacles that are not actually in the adjacent lane or pose no risk of collision with the vehicle. If the detection area is too small, especially when turning, the driver may not be adequately warned of an impending collision hazard.

[0003] Therefore, systems and methods are desired to provide harmful warnings that reduce the risk of collision and to appropriately alert the driver to the risk of collision. Furthermore, other desirable features and characteristics of this disclosure will become apparent from the following detailed description and appended claims, taken in conjunction with the accompanying drawings and the foregoing technical and background information. Summary of the Invention

[0004] In one aspect, a method for warning vehicle occupants of an obstacle on one side of the vehicle. The method includes receiving turning prediction data from at least one vehicle system via at least one processor, receiving perception data from a vehicle perception system via at least one processor, predicting a vehicle turn based on the turning prediction data via at least one processor, generating an obstacle warning via at least one processor, the obstacle warning being output through an output device of the vehicle, and, when an obstacle is detected using the perception data in a first-size detection area or a second-size detection area, switching from using the first-size detection area to using the second-size detection area via at least one processor to generate the obstacle warning in response to the predicted vehicle turn. The second-size detection area is expanded compared to the first-size detection area.

[0005] In an embodiment, the turning prediction data includes at least one of the following types of turning prediction data: map data describing an upcoming intersection, navigation data describing an upcoming intersection, perception data describing an upcoming intersection, braking data indicating vehicle braking application, perception data describing the absence of lane lines on one side of the vehicle, throttle data describing the throttle position causing the vehicle to decelerate, turning signal data describing the activation of a turning signal, driver monitoring data, perception data describing the lateral movement of the vehicle path, inertial measurement data describing the lateral movement of the vehicle, speed data describing the deceleration of the vehicle, steering wheel angle data describing the lateral movement of the vehicle, and vehicle dynamics data describing the deceleration or lateral movement of the vehicle.

[0006] In this embodiment, the turning prediction data includes at least two types of turning prediction data. A probabilistic algorithm for predicting the probability of a vehicle turning can be used to combine the at least two types of turning prediction data.

[0007] In this embodiment, the output device is at least one of an audio, visual, and tactile output device. The output device may be a visual output device contained within a side mirror.

[0008] In this embodiment, the second size detection area is laterally expanded compared to the first size detection area.

[0009] In one embodiment, the method includes detecting the completion of a vehicle turn via at least one processor based on turn prediction data; and in response to detecting the completion of the vehicle turn, generating an obstacle warning via the at least one processor by switching from using a second-size detection area to using a first-size detection area.

[0010] In an embodiment, the completion of a vehicle turn is based on at least one of the following types of turn prediction data: steering angle data indicating substantially straight wheels, braking data indicating reduction or completion of vehicle braking, throttle data describing the throttle position causing longitudinal acceleration of the vehicle, turn signal data describing the deactivation of a turn signal, inertial measurement data describing the vehicle's linear motion, speed data describing the vehicle's speed or acceleration; and vehicle dynamics data describing the vehicle's longitudinal acceleration or substantially linear motion.

[0011] In an embodiment, the vehicle system includes at least one of a vehicle dynamics sensor system, a navigation system, a perception system, a driver monitoring system, and one or more vehicle actuator sensors.

[0012] On the other hand, a vehicle is provided. The vehicle includes an output device, a sensing system, and at least one processor operably in communication with the output device and the sensing system. The at least one processor is configured to execute program instructions. The program instructions are configured to cause the at least one processor to: receive turning prediction data from at least one vehicle system of the vehicle; receive sensing data from the sensing system; predict a vehicle turn based on the turning prediction data; generate an obstacle alarm output through the output device when an obstacle is detected using the sensing data in a first-size detection area or a second-size detection area; and switch from using the first-size detection area to using the second-size detection area to generate the obstacle alarm in response to the predicted vehicle turn. The second-size detection area is expanded compared to the first-size detection area.

[0013] In this embodiment, the turning prediction data includes at least one of the following types of turning prediction data: map data describing an upcoming intersection, navigation data describing an upcoming intersection, perception data describing an upcoming intersection, braking data indicating vehicle braking application, perception data describing the absence of lane lines on one side of the vehicle, throttle data describing the throttle position causing vehicle deceleration, and turning signal data describing the activation of a turning signal. Driver monitoring data, perception data describing the lateral movement of the vehicle's path, inertial measurement data describing the lateral movement of the vehicle, speed data describing vehicle deceleration, steering wheel angle data describing the lateral movement of the vehicle, and vehicle dynamics data describing vehicle deceleration or lateral movement.

[0014] In one embodiment, the turning prediction data includes at least two types of turning prediction data. In one embodiment, a probabilistic algorithm for predicting the probability of a vehicle turning is used to combine the at least two types of turning prediction data.

[0015] In one embodiment, the output device is at least one of an audio, visual, and tactile output device. In one embodiment, the output device is a visual output device included in a side mirror.

[0016] In this embodiment, the second size detection area is laterally expanded compared to the first size detection area.

[0017] In an embodiment, the program instructions are configured to cause at least one processor to: detect the completion of a vehicle turn based on turn prediction data; and, in response to detecting the completion of a vehicle turn, switch from using a second-sized detection area to using a first-sized detection area to generate an obstacle warning.

[0018] In an embodiment, the completion of a vehicle turn is based on at least one of the following types of turn prediction data: steering angle data indicating substantially straight wheels, braking data indicating reduction or completion of vehicle braking, throttle data describing the throttle position that causes longitudinal acceleration of the vehicle, turn signal data describing the deactivation of a turn signal, inertial measurement data describing the straight-line motion of the vehicle, speed data describing the vehicle's speed or acceleration, and vehicle dynamics data describing the vehicle's longitudinal acceleration or straight-line motion.

[0019] In an embodiment, the vehicle system includes at least one of a vehicle dynamics sensor system, a navigation system, a perception system, a driver monitoring system, and one or more vehicle actuator sensors. Attached Figure Description

[0020] Exemplary embodiments will now be described in conjunction with the following accompanying drawings, wherein the same reference numerals denote the same elements, in which:

[0021] Figure 1 This is a functional block diagram illustrating an autonomous or semi-autonomous vehicle system utilizing an alarm system according to various embodiments;

[0022] Figure 2 This is a schematic diagram illustrating a vehicle and associated detection area according to various embodiments;

[0023] Figure 3 This is a system diagram illustrating the functional blocks of an alarm system according to various embodiments;

[0024] Figure 4 This is a flowchart illustrating the method steps of an algorithm process for alerting the driver according to various embodiments; and

[0025] Figure 5 This is a schematic diagram illustrating a map displaying vehicle trajectories according to various embodiments. Detailed Implementation

[0026] The following detailed description is merely exemplary in nature and is not intended to limit application and use. Furthermore, there is no intention to be bound by any express or implied theory set forth in the preceding technical field, background art, summary of the invention, or the following detailed description. As used herein, the term "module" refers to any hardware, software, firmware, electronic control components, processing logic, and / or processor device, individually or in any combination, including but not limited to: application-specific integrated circuits (ASICs), electronic circuits, processors (shared, dedicated, or grouped) and memories executing one or more software or firmware programs, combinational logic circuits, and / or other suitable components providing the described functionality.

[0027] This document describes embodiments of the present disclosure based on functional and / or logical block components and various processing steps. It should be understood that such block components can be implemented by any number of hardware, software, and / or firmware components configured to perform specified functions. For example, embodiments of the present disclosure may employ various integrated circuit components, such as memory elements, digital signal processing elements, logic elements, lookup tables, etc., which can perform various functions under the control of one or more microprocessors or other control devices. Furthermore, those skilled in the art will understand that embodiments of the present disclosure can be practiced in conjunction with any number of systems, and the systems described herein are merely exemplary embodiments of the present disclosure.

[0028] For the sake of brevity, conventional techniques related to signal processing, data transmission, signaling, control, and other functional aspects of the system (as well as the various operating components of the system) may not be described in detail herein. Furthermore, the connecting lines shown in the various figures contained herein are intended to represent exemplary functional relationships and / or physical connections between the various elements. It should be noted that many alternative or additional functional relationships or physical connections may exist in the embodiments of this disclosure.

[0029] The systems and methods described herein provide a novel probabilistic approach to systematically adjust sensing coverage by predicting vehicle turning. In this disclosure, the sensing area is actively and dynamically adjusted based on different driving scenarios. In one embodiment, a side blind zone alert (SBZA) system utilizes radar with a sensing area that expands before the vehicle turns to warn the driver in advance of any obstacles within the sensing area. This disclosure provides a probabilistic algorithm that explicitly predicts primary vehicle maneuvers (e.g., turning) using standard vehicle dynamics and active safety sensors, enabling sensors on the vehicle to adjust the sensing area with the advance time required for threat detection. The developed method predicts turning, with the radar area expanding only during turning, while a standard area remains unchanged when not turning. This system and method enable early detection of vulnerable road users during turning.

[0030] The systems and methods described herein provide systems and methods for detecting a driver's turning intention. The vehicle turning detection method described herein can utilize advanced driver assistance system (ADAS) sensors, including camera information, map information, driver input, and vehicle dynamics sensors. In one embodiment, a combination of vehicle path parameters is used to detect the vehicle turning. Additionally or alternatively, a pre-defined route from navigation and a Global Positioning System (GPS) is utilized to predict the upcoming turn. To reduce collisions at intersections, the radar-sensing detection area is expanded during left turns. The radar-sensing detection area is expanded during right turns for the detection of vulnerable road users (e.g., cyclists and pedestrians).

[0031] refer to Figure 1According to various embodiments, the vehicle system, generally shown as 100, is associated with vehicle 10. Typically, vehicle system 100 includes alarm system 200. Alarm system 200 combines information from various data sources to predict vehicle turning and expands the detection area of ​​the sensing area when a turning is predicted.

[0032] like Figure 1 As shown, vehicle 10 typically includes a chassis 12, a body 14, front wheels 16, and rear wheels 18. The body 14 is mounted on the chassis 12 and substantially surrounds the components of vehicle 10. The body 14 and chassis 12 may together form a frame. The wheels 16-18 are each rotatably connected to the chassis 12 near a corresponding corner of the body 14.

[0033] In some embodiments, the alarm system 200 described herein is envisioned for use in semi-autonomous motor vehicles or other vehicles having a perception system included in ADAS. In particular, the alarm system 200 has utilities associated with ADAS, such as adaptive cruise control and collision avoidance systems.

[0034] In the illustrated embodiment, vehicle 10 is described as a passenger car, but it should be understood that any other vehicle, including motorcycles, trucks, sport utility vehicles (SUVs), recreational vehicles (RVs), etc., may also be used.

[0035] As shown, vehicle 10 typically includes a propulsion system 20, a transmission system 22, a steering system 24, a braking system 26, a sensor system 28, an actuator system 30, at least one data storage device 32, at least one controller 34, and a communication system 36. In various embodiments, the propulsion system 20 may include an internal combustion engine, an electric motor such as a traction motor, and / or a fuel cell propulsion system. The transmission system 22 is configured to transmit power from the propulsion system 20 to the wheels 16-18 according to a selectable speed ratio. According to various embodiments, the transmission system 22 may include a stepped automatic transmission, a continuously variable transmission (CVT), or other suitable transmission. The braking system 26 is configured to provide braking torque to the wheels 16-18. In various embodiments, the braking system 26 may include friction brakes, line brakes, regenerative braking systems such as electric motors, and / or other suitable braking systems. The steering system 24 affects the position of the wheels 16-18 and is associated with a steering wheel.

[0036] Sensor system 28 includes one or more sensing devices 40a-40n that sense observable conditions of the external and / or internal environment of vehicle 10. Sensing devices 40a-40n may include, but are not limited to, a global positioning system, sensing devices 140a-140e (e.g., radar, lidar, thermal cameras, ultrasonic sensors, etc., but specific radar), and / or other sensors. Sensing devices 140a-140e are mounted on vehicle 10 and arranged to capture images (e.g., radar images) of the environment surrounding vehicle 10. In the illustrated embodiment, sensing devices 140c and 140e are located on opposite lateral sides of vehicle 10. In other embodiments, first and second front sensing devices (e.g., optical cameras) are arranged to image a wide-angle near field of view and a narrow-angle far field of view, respectively. A rear-facing camera sensing device (e.g., an optical camera) is also shown. The number and location of the various sensing devices 140a-140e are merely exemplary, and other arrangements are contemplated. Sensing devices 140a-e are included in sensing system 74. The perception system 74 generates perception data from perception devices 140a-e, synthesizes and processes the perception data, and predicts the presence, location, classification, and / or path of objects and features in the environment of the vehicle 10. In various embodiments, the perception system 74 may combine information from multiple sensors, including but not limited to cameras, lidar, radar, and / or any number of other types of sensors. The perception system 74 includes perception devices 140c, 140e, which may be radar devices that generate laterally oriented radar beams and detect the location (and optionally, speed) of any object located within a detection area on the lateral side of the vehicle 10. The size of the detection area is adjusted based on whether an upcoming turn is predicted.

[0037] The radar devices (e.g., side radars) included in the sensing devices 140a-e may include long-range and / or short-range radars. Radar devices distributed around the vehicle may also be included. The radar devices may be specifically configured to provide input to driver assistance systems, such as adaptive cruise control and collision warning. The radar devices are capable of detecting and identifying objects, particularly those located beside the vehicle 10 (e.g., in blind spot areas). The radar devices are adapted to provide radio frequency signals that can be used to determine the distance and / or relative speed of various objects relative to the vehicle 10. The radar devices include transmitters and receivers, or provide a MIMO (Multiple-Input Multiple-Output) radar device including a transmitter array and a receiver array. The radar devices are controlled to generate a radio frequency wavefront, which may be a linear frequency modulated continuous wave (LFM-CW), commonly referred to as a chirped signal. Alternatively, a pulse signal or a combination of pulse and chirped signals may be generated. The radio frequency signal is reflected by various objects in the environment of the vehicle 10. Each of these objects generates a reflected signal in response to receiving the transmitted signal. The radar equipment includes a processor (not shown) for converting the reflected waves into a data format that can be analyzed, such as indicating the distance and angle of the object reflecting the waves. Further processing of the data can reveal the velocity and position of the reflecting surface.

[0038] Actuator system 30 includes one or more actuator devices 42a-42n that control one or more vehicle features, such as, but not limited to, propulsion system 20, transmission system 22, steering system 24, and braking system 26. In various embodiments, vehicle features may further include interior and / or exterior vehicle features, such as, but not limited to, doors, trunk, and cabin features, such as air, music, lighting, etc. (not numbered).

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

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

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

[0042] In various embodiments, one or more instructions of controller 34 are included in alarm system 200 and, when executed by processor 44, are configured to implement the methods and systems described herein for detecting objects in a detection area using sensing devices 140a-e, predicting vehicle turns, and expanding the detection area when a vehicle turn is predicted.

[0043] refer to Figure 2Vehicle 10 is schematically depicted as being associated with a normal detection area 102 and an extended detection area 104. Sensing devices 140a-n generate sensing data, such as images of areas on the relative lateral sides of vehicle 10. When vehicle 10 is detected as traveling in a straight line (or not turning and not predicted to turn), controller 34 generates an alarm when an obstacle is detected in normal detection area 102. This alarm is directional, as a left-side indication alarm is provided when an obstacle is detected in the left-side normal detection area 102, and a right-side indication alarm is provided when an obstacle is detected in the right-side normal detection area 102. Controller 34 receives data from various sources (described further below) to predict when the vehicle is about to turn. When a turn is predicted, the detection area is laterally extended to extended detection area 104. This extension is directional, as a prediction of a right turn will result in an extension of the detection area to the right of vehicle 10, and a prediction of a left turn will result in an extension of the detection area to the left of vehicle 10. In this way, when a turn is predicted, the lateral distance at which an alarm is generated is extended. The normal detection area 102 can be extended laterally (and longitudinally) by a fixed predetermined distance relative to the lateral side of the vehicle 10. The extended detection area 104 can be extended laterally by a further fixed predetermined distance, although the longitudinal coverage may not change compared to the normal detection area 102.

[0044] refer to Figure 3 And continue to refer to Figure 1 and 2 An alarm system 200 is further illustrated according to an exemplary embodiment. The alarm system 200 includes functional modules executed by the program instructions and other system components described above. The alarm system 200 includes a sensor system 28, an infotainment system 204, a driver monitoring system (DMS) 202, a perception system 74, and an ADAS 206.

[0045] Sensor system 28 includes one or more of the following sensors that provide data indicating whether vehicle 10 is predicted to be going essentially straight or turning at an intersection (turning prediction data 224). Sensor system 28 includes a steering angle sensor (SAS) 208, a wheel speed sensor (WSS) 210, an inertial measurement unit (IMU) 212, a global positioning system (GPS) 214, a transmission gear 216, an engine sensor 218, a turn signal sensor 220, and a throttle and / or brake sensor 222. SAS 208 provides data indicating the steering wheel angle, which can provide relevant information for predicting vehicle turning. While the purpose of warning system 200 is to predict vehicle turning before the vehicle begins to turn, the steering wheel angle can indicate that the driver is preparing to turn, for example by detecting that vehicle 10 is turning in the direction it is turning, or by a steering angle profile that matches the time when a turn is likely to occur. WSS 210 provides speed measurements that can indicate an upcoming turn by the deceleration of vehicle 10 or by the speed falling below a threshold indicating vehicle turning, or by following a speed-to-time profile representing the speed at which the vehicle enters a turn. IMU 212 can provide acceleration data indicating that vehicle 10 is decelerating and / or that vehicle 10 has some lateral force indicating an impending turn. Data from GPS 214 can also be processed to provide speed and acceleration data, which can indicate an upcoming turn. Data from engine sensor 218 can indicate reduced engine power or speed. Turn signal sensor 220 can indicate the driver's intention to turn. Throttle / brake sensor 222 can indicate activation of braking system 26 (e.g., via a brake actuator (e.g., brake pedal) actuated by the driver) and / or deceleration of throttle (e.g., via a throttle actuator (e.g., accelerator pedal) at least partially released by the driver).

[0046] Additional sources of the turn prediction data 224 include the infotainment system 204, which includes a navigation device. The navigation device can provide map data and the vehicle 10's position relative to the map. The vehicle 10's position and movement trends can indicate upcoming intersections, increasing the likelihood of a turn. If the navigation device is providing route guidance (e.g., turn-by-turn direction), then based on the resulting route, the navigation device knows the upcoming turn. Furthermore, the navigation device can provide speed limit information, which can be combined with the vehicle speed to obtain an indication of an upcoming turn.

[0047] Another source of the turning prediction data 224 is the DMS 202, which tracks head posture and / or eye position. Drivers can move their head and / or eyes in the direction of the upcoming turn, which can be detected by the DMS 202.

[0048] Another source of the turning prediction data 224 could be the perception system 74. Specifically, intersections can be detected by analyzing image data from forward-looking and / or side-looking optical cameras. Intersections can be detected by locating side lanes and / or by locating gaps in the lane lines on one side of the vehicle 10. Furthermore, lateral offset relative to the lane lines on either side of the vehicle can be detected. Lateral offset may decrease as a turn approaches.

[0049] ADAS 206 may include path planning logic for automatic control of some steering functions. Path planning data can predict upcoming turns.

[0050] The alarm system 200 includes a turn prediction module 226. Turn prediction data 224 obtained from various sources (as described above) is provided as input to the turn prediction module 226. The turn prediction module 226 implements a probabilistic framework to integrate data from multiple sources to predict an upcoming turn. In one embodiment, a Bayesian method is used to infer the probability of an upcoming turn based on the fusion of the turn prediction data 224 collected from various sources. Other probabilistic methods can be used to estimate the probability of an upcoming turn by fusing information from various sources of the turn prediction data 224. An exemplary method for probabilistically predicting vehicle turns is provided below.

[0051] The following model (X) can be established for main vehicle turning detection. host,k ):

[0052]

[0053] Measurement models can also be built:

[0054] Y k =C k X k +δ k ,δ k ~N(0,Q) k (Equation 2)

[0055] Probability prediction of vehicle turning This can be achieved by assuming a piecewise constant A. k and B k And update A k+f and B k+f This can be calculated. This can be done through multi-model observations.

[0056] In one embodiment, u k This includes vehicle status and environmental conditions, including the yaw rate of the main vehicle 10, steering wheel angle, torque applied by the driver, speed of the main vehicle, brake pedal position, vehicle transmission gear position, surrounding lane markings, etc. (e.g., u k =[ωz ,θ,τ,v,p b ,g,l lt ,l rt ,…] k )

[0057]

[0058] In one embodiment, g k The recursive least squares method described below can be used to find: g k

[0059]

[0060]

[0061] The turning prediction module 226 outputs vehicle turning prediction data 228, which can be a probability value or a Boolean value indicating that the probability of an upcoming turn is greater than a set threshold. When the probability value is lower than the threshold, it can be inferred that the vehicle 10 is traveling in a straight line longitudinally. Therefore, the vehicle turning prediction data 228 can output vehicle turning prediction data 228 corresponding to a predicted turn or a predicted straight-line scenario. The turning prediction module 226 can output the predicted turning direction (e.g., right or left) as part of the vehicle turning prediction data 228. The predicted turning direction can be derived by the turning prediction module 226 based on the turning prediction data 224, which includes direction components, such as information from the turning signal sensor 220, information from the IMU 212, information from the GPS 214, information from the WSS 210, information from the SAS, information from the infotainment system 204, information from the DMS 202, and information from the ADAS 206.

[0062] The alarm system 200 includes a detection area determination module 230 that receives vehicle turning prediction data 228. When the vehicle turning prediction data 228 changes from a predicted straight-ahead scenario to a predicted vehicle turning scenario, the detection area determination module 230 switches from the normal detection area 102 to the extended detection area 104. When the vehicle turning prediction data 228 changes from a predicted vehicle turning scenario to a predicted straight-ahead scenario (e.g., completion of a vehicle turn), the detection area determination module 230 switches from the extended detection area 104 back to the normal detection area 102. The detection area determination module 230 can output detection area size data 232, which may be the location and position of the detection area according to a predetermined normal or extended detection area 102, 104, or an identifier of a determined detection area type (e.g., normal or extended) may be output as part of the detection area size data 232.

[0063] The alarm system includes an alarm generation module 234, which receives detection area size data 232 and perception data 238 from the perception system 74. Perception data 238 may include the location of the object / obstacle, the type of the object / obstacle, the speed of the object / obstacle, the trajectory of the object / obstacle, etc. The obstacle's location and optional further obstacle information are evaluated relative to the normal or expanded detection areas 102, 104 (either selected based on the detection area size data 232) to determine whether an obstacle or object exists in the detection area, or to determine whether the obstacle or object tends to move into the detection area within a predetermined time period, or to determine the risk of collision with an obstacle within the detection area. The obstacle or object can be another vehicle, a cyclist, a pedestrian, etc. When a positive assessment is made that an obstacle is located within the detection area, the alarm generation module 234 outputs an alarm 240. The coverage area expands when an upcoming turn is predicted, and contracts when the turn is completed (or additionally when vehicle 10 is not turning at the intersection).

[0064] Alarm 240 is provided to output device 236 of alarm system 200. Output device 236 may be a display integrated into the vehicle dashboard, an indicator light provided as part of the dashboard, an indicator light provided as part of the rearview mirror, an indicator light included in the side mirrors of vehicle 10, an audible alarm, and / or a tactile alarm (e.g., as part of the driver's seat or steering wheel). Alarm 240 may be directional, thereby indicating the left or right position of a collision threat. This can be achieved by having directional indicator lights, displaying the directionality of the alarm, outputting audible signals, and / or tactile alarms.

[0065] Now for reference Figure 4 And continue to refer to Figure 1-3 The flowchart illustrates an alarm method 400 according to this disclosure, which predicts an upcoming vehicle turn, adjusts the size of a detection area based on the predicted turn, evaluates objects or obstacles within the adjusted detection area, and generates an alarm based on this. It will be understood from this disclosure that the order of operations in this method is not limited to... Figure 4 The alarm method 400 may be executed in the order shown, but may be executed in one or more different orders as appropriate, according to this disclosure. In various embodiments, the alarm method 400 may be scheduled to run based on one or more predetermined events, and / or may run continuously during operation of the vehicle 10.

[0066] When a wake-up condition is met, alarm method 400 may begin. In one embodiment, the wake-up condition may include the detection of an approaching intersection, which may be based on map data provided by the map application of infotainment system 204 and the location of vehicle 10 provided by GPS 214, route navigation data provided by the navigation application of infotainment system 204, and / or analysis of optical images provided by perception system 74 to identify the intersection. The wake-up condition may include brake application detected by throttle / brake sensor 222. The wake-up condition may include perception system 74 detecting that there is no lane to the right of the vehicle. The wake-up condition may include at least partial release of the throttle detected by throttle / brake sensor 222. These wake-up conditions may be cumulative, or only one or some wake-up conditions may be determined to be true for alarm method 400 to continue.

[0067] In step 410, turning prediction data 224 is received. In step 420, the likelihood of an upcoming turn is predicted based on the turning prediction data 224. This prediction can be based on a probabilistic assessment and fusion of turning prediction data 224 from multiple sources. For example, a turn can be predicted based on any combination of the following data elements: the application of brake and / or throttle position from throttle / brake sensor 222; driver head and / or eye movements from DMS 202; whether the turn indicator is on or off as detected by turn signal sensor 220; steering wheel angle from SAS 208; yaw rate of change from IMU 212; deceleration of vehicle 10, which can be derived from data from IMU 212, WSS 210, or GPS; and, as detected by perception system 74, the absence or intermittent detection of lane lines on one side of vehicle 10 for a set period of time. The prediction in step 420 can also provide a predicted direction of the turn (e.g., whether to turn left or right at an intersection). This prediction can be part of the probability assessment described above, or a separate prediction step can be performed to determine the vehicle's turning direction. Exemplary data elements for determining the turning direction may include any one or more of the following: steering yaw angle from SAS 208; vehicle heading, which may be obtained from GPS; vehicle position, indicating the vehicle's alignment in the left or right turn direction, which can be derived from map data and the vehicle's positioning relative to the map; evaluation of optical images from perception system 74, indicating preparation for a left or right turn; and route information provided by the navigation system.

[0068] In step 430, the size or shape of the detection area is determined. When an upcoming turn is predicted in step 420, the detection area expands from the normal detection area 102 to the extended detection area 104. The detection area expands on one side of the vehicle 10 corresponding to the turning direction determined in step 430. Therefore, the detection area can expand on one side of the vehicle 10 while having a normal size on the other side. In this way, an unbalanced detection area can be defined.

[0069] In step 440, perception data 238 is received from perception system 74. Perception data 238 may be data from a vehicle-side radar device that provides perception coverage for at least one blind spot of vehicle 10. Other forms of perception data 238 may be used, such as optical images. Perception data 238 at least identifies the location of obstacles or objects, particularly moving obstacles or objects, such as other vehicles and cyclists. Regarding perception data 238, the detection area coverage determined in step 430 is evaluated in step 450. Specifically, the spatial consistency between the extended detection area 104 and any perceived obstacles or objects is determined. In step 460, an alarm is generated when any obstacle or object is perceived within the extended detection area 104. The alarm may be directional, based on which side of vehicle 10 has been detected within the normal detection area 102 on one side of vehicle 10 and the extended detection area 104 on the other side of vehicle 10. The alarm may be visual, tactile, and / or auditory.

[0070] When vehicle 10 is determined to have completed a turn, alarm method 400 can terminate. This determination can be made by evaluating any combination of the following conditions: the steering wheel angle indicates that the wheels are substantially straight (e.g., below a threshold angle); the brake application or throttle position is released in the direction of increased throttle; the vehicle accelerates or the vehicle speed exceeds a threshold; the turn indicator is off; and inertial motion readings indicate that vehicle 10 is traveling in a longitudinal straight line. When the turn is determined to be complete (or in a straight-line scenario), the detection area shrinks from the extended detection area 104 to the normal detection area 102, such that no alarm is generated when an obstacle or object is located within the extended detection area 104, but an alarm is generated when an obstacle or object is located within the normal detection area 102.

[0071] Figure 5 Map 500 shows a vehicle trajectory 502. It shows the vehicle traveling along a road and heading towards an intersection on the right. At decision point 508, the driver has decided to turn into the intersection on the right at turning point 504. This disclosure utilizes turn prediction, which allows the vehicle's turn to be predicted before turning point 504 begins by accumulating small indications of the driver's intention to perform the upcoming turn. In this way, the detection area can be extended before the actual turning point 504, which is impossible with reactive vehicle turn determination.

[0072] While at least one exemplary embodiment has been described in the foregoing detailed description, it should be understood that numerous variations exist. It should also be understood that the one or more exemplary embodiments are merely examples and are not intended to limit the scope, applicability, or configuration of this disclosure in any way. Rather, the foregoing detailed description will provide those skilled in the art with a convenient roadmap for implementing one or more exemplary embodiments. It should be understood that various changes can be made to the function and arrangement of the elements without departing from the scope of this disclosure as set forth in the appended claims and their legal equivalents.

Claims

1. A method for warning vehicle occupants of an obstacle on one side of a vehicle, the method comprising: Receives turning prediction data from at least one vehicle system via at least one processor; Sensing data is received from the vehicle's sensing system via the at least one processor; Based on turning prediction data, the vehicle turns are predicted via at least one processor, wherein the prediction is based on probabilistic evaluation and fusion of turning prediction data from multiple sources, including sensor systems, infotainment systems, driver monitoring systems, perception systems, and advanced driver assistance systems. When an obstacle is detected using the perception data in a first-size detection area or a second-size detection area, an obstacle alarm is generated via the at least one processor and output through the vehicle's output device. In response to a predicted vehicle turn, an obstacle warning is generated by switching from using a first-size detection area to using a second-size detection area via the at least one processor. The second size detection area is expanded compared to the first size detection area.

2. The method of claim 1, wherein the turning prediction data includes at least one of the following types of turning prediction data: Map data describing the upcoming intersection; Navigation data describing the upcoming intersection; Sensing data describing the upcoming intersection; Indicates braking data applied by the vehicle's brakes; Describes perception data where there are no lane lines on one side of the vehicle; Throttle data describing the throttle position that causes the vehicle to decelerate; Describes the turning signal data activated by the turning signal; Driver monitoring data; Perception data describing the path of a vehicle moving laterally; Inertial measurement data describing the lateral motion of the vehicle; Describes the speed data used to describe vehicle deceleration; Steering wheel angle data describing the lateral movement of the vehicle; and Vehicle dynamics data describing the deceleration or lateral movement of a vehicle.

3. The method of claim 2, wherein the turning prediction data comprises at least two types of turning prediction data.

4. The method of claim 3, wherein the at least two types of turning prediction data are combined using a probabilistic algorithm that predicts the probability of an upcoming vehicle turning.

5. The method of claim 1, wherein the output device is at least one of an audio, visual, and haptic output device.

6. The method of claim 1, wherein the output device is a visual output device contained in a side mirror.

7. The method of claim 1, wherein the second size detection area is laterally expanded compared to the first size detection area.

8. The method of claim 1, comprising detecting the completion of a vehicle turn via at least one processor based on turn prediction data; and generating an obstacle warning via the at least one processor by switching from using a second-size detection area to using a first-size detection area in response to detecting the completion of the vehicle turn.

9. The method of claim 8, wherein the completion of the vehicle turn is based on at least one of the following types of turn prediction data: The steering angle data indicates that the wheels are basically straight; Braking data indicating whether vehicle braking has been reduced or completed; Throttle data describing the throttle position that causes longitudinal acceleration of the vehicle; Describes the deactivated turn signal data; Inertial measurement data describing the linear motion of a vehicle; Speed ​​data describing the vehicle's speed or longitudinal acceleration; and Vehicle dynamics data describing the longitudinal acceleration or linear motion of a vehicle.

10. A vehicle comprising: Output devices; Sensing system; At least one processor operatively communicating with the output device and the sensing system, wherein the at least one processor is configured to execute program instructions, wherein the program instructions are configured to cause the at least one processor to: Receive turning prediction data from at least one vehicle system of the vehicle; Receive sensing data from the sensing system; Vehicle turning is predicted based on turning prediction data, which is based on probabilistic evaluation and fusion of turning prediction data from multiple sources, including sensor systems, infotainment systems, driver monitoring systems, perception systems, and advanced driver assistance systems. When an obstacle is detected using the sensing data in a first-size detection area or a second-size detection area, an obstacle alarm is generated and output through the output device. In response to a predicted vehicle turn, the system switches from using a first-size detection area to using a second-size detection area to generate an obstacle warning. The second size detection area is expanded compared to the first size detection area.

Images