Control algorithm for opening approaching side door using autonomous sensor

Abstract

A system and method includes detecting an authenticated device in a proximity of a vehicle, activating a perception system for the proximity of the vehicle, and detecting a user in the proximity of the vehicle and approaching the vehicle in user data captured by the perception system. The system and method also include classifying an identity of a user in the vicinity of the vehicle based on the user data, identifying a target door of the vehicle for the user based on the classified identity of the user, and instructing the target door of the vehicle to automatically open for the user.

Description

TECHNICAL FIELD

[0001] The information provided in this section is for the purpose of generally presenting the context of the disclosure. The work of the presently named inventors, to the extent the work is described in this portion of this specification, and the descriptions of aspects that can not be eligible for present existing technology at the time the application is filed, are not, and are not to be interpreted to be, admitted as prior art to the disclosure.

[0002] The present disclosure relates generally to systems and methods for opening a proximate side door using autonomous sensors. BACKGROUND

[0003] Generally, vehicles use multiple autonomous sensors to detect a key fob proximate to the vehicle, detect a user, and / or detect a potential collision with a vehicle door. These autonomous sensors can include passive entry passive start (PEPS) detection and / or door anti-collision radar (DAR) detection.

[0004] Notably, not all users proximate to a vehicle have a hand available to open a door, whether due to mobility challenges or due to carrying items, pets, or other users (e.g., children). Thus, a system that intelligently predicts and automatically opens the correct door for a user as the user approaches the vehicle would greatly enhance the user experience. Moreover, opening only the door that the user intends to open can increase the security of the vehicle by limiting the number of opened / unlocked doors that a threat actor can access as the user approaches the vehicle. SUMMARY

[0005] One aspect of the present disclosure provides a computer-implemented method for controlling an algorithm that opens a proximate side door using autonomous sensors, the control algorithm, when executed on data processing hardware, causes the data processing hardware to perform operations comprising detecting an authenticated device in a proximate area of a vehicle, activating a perception system of the proximate area of the vehicle, and detecting, in user data captured by the perception system, a user in the proximate area of the vehicle and approaching the vehicle. The operations further include classifying an identity of the user in the proximate area of the vehicle based on the user data, identifying a target door of the vehicle for the user based on the classified identity of the user, and instructing the target door of the vehicle to automatically open for the user.

[0006] Implementations of the present disclosure can include one or more of the following optional features. In some implementations, detecting the authenticated device in the proximate area of the vehicle includes receiving authentication data captured by an authentication system. Here, the authentication data indicates that the authenticated device is in the proximate area of the vehicle. In some examples, the authenticated device includes one or more of a mobile device or a key fob. In some implementations, the perception system includes one or more of a light detection and ranging (LIDAR) or a camera system.

[0007] In some examples, classifying the identity of the user in the proximity region of the vehicle based on the user data includes comparing the user data to one or more user accounts, each user account associated with a registered user of the vehicle. In these examples, each user account of the one or more user accounts can include respective user characteristics of the registered user of the vehicle. Here, the respective user characteristics can include one or more of a height of the registered user, a width of the registered user, a door preference of the registered user, or a device of the registered user. Additionally or alternatively, the respective user characteristics can be added to the user account during a registration process.

[0008] In some implementations, identifying the target door of the vehicle for the user based on the classified identity of the user includes receiving the classified identity of the user and one or more user characteristics of the user as inputs to a machine learning model, and generating the target door as an output. In these implementations, the operations can further include receiving user feedback indicative of a preference of the user, and updating the machine learning model based on the user feedback.

[0009] Another aspect of the present disclosure provides a system for controlling an algorithm that utilizes an autonomous sensor to open a proximate side door, the system including data processing hardware and memory hardware in communication with the data processing hardware. The memory hardware stores instructions that, when executed by the data processing hardware, cause the data processing hardware to perform operations including detecting an authenticated device in a proximity region of a vehicle, activating a perception system for the proximity region of the vehicle, and detecting a user in the proximity region of the vehicle and approaching the vehicle in user data captured by the perception system. The operations further include classifying the identity of the user in the proximity region of the vehicle based on the user data, identifying a target door of the vehicle for the user based on the classified identity of the user, and instructing the target door of the vehicle to automatically open for the user.

[0010] This aspect can include one or more of the following optional features. In some implementations, detecting the authenticated device in the proximity region of the vehicle includes receiving authentication data captured by an authentication system. Here, the authentication data indicates that the authenticated device is in the proximity region of the vehicle. In some examples, the authenticated device includes one or more of a mobile device or a key fob. In some implementations, the perception system includes one or more of a light detection and ranging (LIDAR) or a camera system.

[0011] In some examples, classifying the identities of users in a vehicle's vicinity based on user data involves comparing the user data with one or more user accounts, each associated with a registered user of the vehicle. In these examples, each of the one or more user accounts may include corresponding user characteristics of the vehicle's registered user. Here, the corresponding user characteristics may include one or more of the registered user's height, width, door preference, or device. Additionally or alternatively, the corresponding user characteristics may be added to the user account during the registration process.

[0012] In some implementations, identifying a target gate for a vehicle based on a user's classified identity includes receiving the user's classified identity and one or more user features as input to a machine learning model, and generating a target gate as output. In these implementations, the operation may further include receiving user feedback indicating user preferences, and updating the machine learning model based on the user feedback.

[0013] Details of one or more embodiments of this disclosure are set forth in the accompanying drawings and the description below. Other aspects, features, and advantages will be apparent from the specification, drawings, and claims. Attached Figure Description

[0014] The accompanying drawings described herein are for illustrative purposes only for the selected configurations and are not intended to limit the scope of this disclosure.

[0015] Figure 1 This is a schematic diagram of an example system for a control algorithm that uses autonomous sensors to open an approaching side door.

[0016] Figure 2 yes Figure 1 A schematic diagram of an example component of the system.

[0017] Figure 3 Is execution Figure 1 Example vehicles of the system.

[0018] Figure 4 yes Figure 1 A schematic diagram of the system registration process.

[0019] Figure 5 This is a flowchart illustrating an example of the operational setup of a control algorithm that utilizes autonomous sensors to open an approaching side door.

[0020] In all the accompanying drawings, the corresponding reference numerals denote the corresponding parts. Detailed Implementation

[0021] The example configuration will now be described more fully with reference to the accompanying drawings. The example configuration is provided so that this disclosure will be thorough and will fully communicate the scope of this disclosure to those skilled in the art. Specific details, such as examples of specific components, devices, and methods, are set forth to provide a thorough understanding of the configuration of this disclosure. It will be apparent to those skilled in the art that specific details are not required, the example configuration may be embodied in many different forms, and the specific details and example configuration should not be construed as limiting the scope of this disclosure.

[0022] The terminology used herein is for the purpose of describing a particular exemplary configuration only and is not intended to be limiting. As used herein, the singular articles “a” and “the” may also be intended to include plural forms unless the context clearly indicates otherwise. The terms “comprises,” “comprising,” “including,” and “having” are inclusive and therefore specify the presence of features, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, steps, operations, elements, components, and / or groups thereof. The method steps, processes, and operations described herein should not be construed as requiring them to be performed in the specific order discussed or shown, unless specifically identified as such. Additional or alternative steps may be employed.

[0023] When an element or layer is referred to as “on another element or layer,” “joined to,” “connected to,” “attached to,” or “linked to” another element or layer, it may be directly on, joined to, connected to, attached to, or linked to the other element or layer, or there may be intermediate elements or layers present. Conversely, when an element is referred to as “directly on another element or layer,” “directly joined to,” “directly connected to,” “directly attached to,” or “directly linked to” another element or layer, there may be no intermediate elements or layers present. Other terms used to describe relationships between elements should be interpreted in a similar manner (e.g., “between” vs. “directly between,” “adjacent” vs. “directly adjacent,” etc.). As used herein, the term “and / or” includes any and all combinations of one or more of the associated listed items.

[0024] The terms “first,” “second,” “third,” etc., may be used herein to describe various elements, components, regions, layers, and / or parts. These elements, components, regions, layers, and / or parts should not be limited by these terms. These terms may be used only to distinguish one element, component, region, layer, or part from another. Unless the context clearly indicates otherwise, terms such as “first,” “second,” and other numerical terms do not imply order or sequence. Therefore, without departing from the teachings of the example configuration, the first element, component, region, layer, or part discussed below may be referred to as the second element, component, region, layer, or part.

[0025] In this application, including the following definitions, the term "module" may be replaced by the term "circuit". The term "module" may refer to, be part of, or include the following: application-specific integrated circuit (ASIC); digital, analog, or mixed-signal analog / digital discrete circuit; digital, analog, or mixed-signal analog / digital integrated circuit; combinational logic circuit; field-programmable gate array (FPGA); processor (shared, dedicated, or grouped) that executes code; memory (shared, dedicated, or grouped) that stores code executed by the processor; other suitable hardware components that provide the described functionality; or combinations of some or all of the foregoing, such as in a system-on-a-chip.

[0026] The term "code" as used above can include software, firmware, and / or microcode, and can refer to programs, routines, functions, classes, and / or objects. The term "shared processor" includes a single processor that executes some or all of the code from multiple modules. The term "group processor" includes processors that, in combination with additional processors, execute some or all of the code from one or more modules. The term "shared memory" covers a single memory that stores some or all of the code from multiple modules. The term "group memory" includes memory that, in combination with additional memory, stores some or all of the code from one or more modules. The term "memory" can be a subset of the term "computer-readable medium." The term "computer-readable medium" does not include transient electrical and electromagnetic signals propagating through the medium, and therefore can be considered tangible and non-transitory memory. Non-limiting examples of non-transitory memory include tangible computer-readable media, which include non-volatile memory, magnetic memory, and optical memory.

[0027] The apparatus and methods described in this application can be implemented, partially or entirely, by one or more computer programs executed by one or more processors. The computer program includes processor-executable instructions stored on at least one non-transitory tangible computer-readable medium. The computer program may also include and / or depend on stored data.

[0028] A software application (i.e., a software resource) can refer to computer software that enables a computing device to perform tasks. In some examples, a software application may be referred to as an "application," "app," or "program." Example applications include, but are not limited to, system diagnostic applications, system management applications, system maintenance applications, word processing applications, spreadsheet applications, messaging applications, media streaming applications, social networking applications, and game applications.

[0029] Non-transitory memory can be a physical device used to temporarily or permanently store programs (e.g., instruction sequences) or data (e.g., program state information) for use by a computing device. Non-transitory memory can be volatile and / or non-volatile addressable semiconductor memory. Examples of non-volatile memory include, but are not limited to, flash memory and read-only memory (ROM) / programmable read-only memory (PROM) / erasable programmable read-only memory (EPROM) / electrically erasable programmable read-only memory (EEPROM) (e.g., commonly used in firmware, such as boot programs). Examples of volatile memory include, but are not limited to, random access memory (RAM), dynamic random access memory (DRAM), static random access memory (SRAM), phase-change memory (PCM), and magnetic disks or magnetic tapes.

[0030] These computer programs (also referred to as programs, software, software applications, or code) include machine instructions for a programmable processor and can be implemented using high-level procedural and / or object-oriented programming languages ​​and / or assembly / machine languages. As used herein, the terms “machine-readable medium” and “computer-readable medium” refer to any computer program product, non-transitory computer-readable medium, device, and / or apparatus (e.g., disk, optical disk, memory, programmable logic device (PLD)) used to provide machine instructions and / or data to a programmable processor, including machine-readable media that receive machine instructions as machine-readable signals. The term “machine-readable signal” refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0031] Various implementations of the systems and techniques described herein can be implemented in digital electronic and / or optical circuits, integrated circuits, specially designed ASICs (Application-Specific Integrated Circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementations in one or more computer programs executable and / or interpretable on a programmable system, which includes at least one programmable processor, which may be dedicated or general-purpose, coupled to receive data and instructions from a storage system, at least one input device, and at least one output device, and to transmit data and instructions to the storage system, at least one input device, and at least one output device.

[0032] The processes and logical flows described in this specification can be executed by one or more programmable processors (also known as data processing hardware) that execute one or more computer programs to perform functions by manipulating input data and generating output. The processes and logical flows can also be executed by special-purpose logic circuitry (e.g., FPGAs (Field-Programmable Gate Arrays) or ASICs (Application-Specific Integrated Circuits). As an example, processors suitable for executing computer programs include both general-purpose and special-purpose microprocessors, as well as any one or more processors of any type of digital computer. Typically, the processor receives instructions and data from read-only memory or random access memory, or both. The basic elements of a computer are a processor for executing instructions and one or more memory devices for storing instructions and data. Typically, a computer will also include one or more mass storage devices (e.g., magnetic disks, magneto-optical disks, or optical disks) for storing data, or operatively coupled to receive data from or transfer data to, or both. However, a computer does not need to have such devices. Computer-readable media suitable for storing computer program instructions and data include all forms of non-volatile memory, media, and memory devices, including, for example, semiconductor memory devices such as EPROM, EEPROM, and flash memory devices; magnetic disks such as internal hard disks or removable disks; magneto-optical disks; and CD-ROMs and DVD-ROMs. Processors and memory may be supplemented by or incorporated into dedicated logic circuitry.

[0033] To provide interaction with a user, one or more aspects of this disclosure can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube), LCD (liquid crystal display) monitor, or touchscreen) for displaying information to the user and optionally a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback, such as visual, auditory, or tactile feedback; and input from the user can be received in any form, including sound, speech, or tactile input. Additionally, the computer can interact with the user by sending documents to and receiving documents from the device used by the user; for example, by sending a webpage to a web browser on the user's client device in response to a request received from a web browser.

[0034] refer to Figure 1In some embodiments, system 100 includes vehicle 10 and / or remote system 60 communicating with vehicle 10 via network 40 (e.g., wired or wireless communication). Vehicle 10 and / or remote system 60 perform an approach side door system 200, which operates to detect one or more users 102 approaching vehicle 10, accurately detect and distinguish one or more users 102, and automatically open one or more doors 20, 20a-d of vehicle 10 for one or more users 102 without requiring one or more users 102 to open doors 20, 20a-d. In short, and as described further in detail below, approach side door system 200 is configured to detect an authentication device 104 of user 102 in one of the proximity areas 22, 22a-22d of vehicle 10, detect user 102 authenticated by device 104, and identify a target door 20 among one or more doors 20 based on user 102 and a specific proximity area 22 in which user 102 is moving, to automatically open for user 102. Advantageously, by automatically opening the target door 20, the access side door system 200 allows one or more users 102 to access the vehicle 10 without physical interaction.

[0035] In the example shown, the access side door system 200 is implemented within vehicle 10. However, the access side door system 200 can be implemented in any other propulsion system, such as, but not limited to, motorcycles, trucks, off-road vehicles, farm equipment, trains, airplanes, etc. Vehicle 10 includes data processing hardware 12 and memory hardware 14 storing instructions that, when executed on the data processing hardware 12, cause the data processing hardware 12 to perform operations. The exterior of vehicle 10 can generally be divided into one or more adjacent regions 22, 22a-n, where each region 22 corresponds to a portion of the area surrounding vehicle 10, such that the adjacent regions 22 collectively cover a 360-degree area surrounding vehicle 10. Figure 1 As shown, vehicle 10 may include four (4) adjacent regions 22a-22d, wherein adjacent region 22a corresponds to the left side of vehicle 10 extending along the length of vehicle 10, adjacent region 22b corresponds to the front side of vehicle 10, adjacent region 22c corresponds to the right side of vehicle 10 extending along the length of vehicle 10, and adjacent region 22d corresponds to the rear side of vehicle 10. Although adjacent regions 22a-22d are shown as including overlap between adjacent adjacent regions 22, in some embodiments, adjacent adjacent regions 22 may not overlap but are adjacent to each other. Furthermore, although the examples used generally involve four (4) adjacent regions 22a-22d, it should be understood that the access side door system 200 may divide the area around vehicle 10 into any number of adjacent regions 22, such as, but not limited to, two (2) adjacent regions 22, six (6) adjacent regions 22, or any other number of adjacent regions 22.

[0036] Vehicle 10 also includes an authentication system 16 and a perception system 18. The authentication system 16 is configured to capture authentication data 30 within the vicinity area 22 of vehicle 10. For example, the authentication data 30 may include wireless communication signals transmitted by the authenticated device 104 of user 102. Figure 1 As shown, authentication device 104 may refer to the mobile device of registered user 102 of vehicle 10 and / or the key card associated with vehicle 10. Here, wireless communication signals may include, but are not limited to, radio frequency identification (RFID) signals. The signal can be an infrared signal, an NFC signal, or an ultrasonic signal. In other examples, the wireless communication signal captured by the authentication system 16 may be an audible or inaudible signal output from the authenticated device 104.

[0037] The perception system 18 is configured to capture user data 32 detected within the proximity area 22 of the authenticated device 104. In some embodiments, the perception system 18 remains in a dormant / inactive state and is activated only when the proximity side door system 200 detects that the authenticated device 104 is within the proximity area 22 of the vehicle 10. The perception system 18 may include one or more of a light detection and ranging (LIDAR) system or a camera system configured to capture image data. In some cases, to improve computational efficiency, the perception system 18 only captures user data 32 within the proximity area 22 that includes the authenticated device 104. In other words, the portion of the perception system 18 corresponding to the proximity area 22 that includes the authenticated device 104 can be activated / wake up, while the portion of the perception system 18 corresponding to the proximity area 22 that does not include the authenticated device 104 remains inactive / dormant.

[0038] The remote system 60 (e.g., a server, cloud computing environment) also includes data processing hardware 62 and memory hardware 64 storing instructions that, when executed on the data processing hardware 62, cause the data processing hardware 62 to perform operations. In some embodiments, the execution of the access side door system 200 is shared between the vehicle 10 and / or the remote system 60. See below for reference. Figure 2In more detail, the approach side door system 200 executes a device detector module 210, a perception module 220, a user classifier 230, and a door selection model 240. In some embodiments, the approach side door system 200 may access a user data storage 250, which records / stores multiple user accounts 252, 252a-n, each user account 252 associated with a registered user 102R of the vehicle 10 and having corresponding user characteristics 254, 254a-n of the registered user 102R, as well as historical user feedback 256, 256a-n of the registered user 102R collected / recorded during previous interactions between the registered user 102R and the approach side door system 200. User characteristics 254 may typically refer to the height H of the registered user 102R. 102 The width W of registered user 102R 102 The user data storage 250 can be stored on any of the memory hardware 14, 64. This includes the user's gate preferences or the device 104 for registering user 102R.

[0039] Continue to refer to Figure 1 and Figure 2 The device detector module 210 is configured to receive authentication data 30 captured by the authentication system 16 as input, and to detect in the authentication data 30 whether the authenticated device 104 is within one or more proximity areas 22 of the vehicle 10. In other words, the authentication data 30 can indicate that the authenticated device 104 is within the proximity area 22 of the vehicle 10 when the strength of the wireless signal transmitted by the authenticated device 104 is higher than a threshold strength that enables the authentication system 16 to detect the presence of the authenticated device 104. In some embodiments, the device detector module 210 identifies which specific proximity area 22 the authenticated device 104 is located in based on the authentication data 30. For example, as... Figure 1 As shown, user 102 is located in the vicinity area 22a and may be approaching the driver's side door 20a of vehicle 10. Here, device detector module 210 determines that user 102's authenticated device 104 is located in the vicinity area 22a based on authentication data 30, and generates trigger 212, which activates / wakes up the portion of sensing system 18 corresponding to the vicinity area 22a to begin collecting user data 32 within the vicinity area 22a.

[0040] Subsequently, the perception module 220 receives user data 32 captured by the perception system 18 as input, and uses image processing to detect whether the user 102 is in the vicinity area 22 of the vehicle 10 and is approaching the vehicle 10. Here, the user data 32 may include image data including the user 102 detected by the perception module 220. In addition, the user data 32 may include one or more frames containing image data of the user 102, indicating that the user is approaching (i.e., getting closer) the vehicle 10.

[0041] The classifier module 230 can receive user data 32 as input and classify the identity 232 of user 102 based on the user data 32. The identity 232 of user 102 can refer to a type of user of vehicle 10 (e.g., adult, child) or registered user 102R. For example, the classifier module 230 can estimate the height H of user 102 based on the user data 32. 102 Width W of user 102 102 And classify the identity 232 of user 102 as an adult (i.e., possibly sitting in the driver's or passenger seat of vehicle 10) or a child (i.e., possibly sitting in the back seat of vehicle 10).

[0042] Additionally or alternatively, the user classifier 230 may take one or more user accounts 252 of the corresponding registered user 102R of vehicle 10 as input and compare user data 32 with each user account 252. For example, as described above, each user account 252 may include a corresponding user feature 254 of the registered user 102R of vehicle 10. User feature 254 may include, but is not limited to, the height H of the registered user 102R. 102 The width W of registered user 102R 102 One or more of the following: the gate preferences of registered user 102R or the device of registered user 102R (e.g., certified device 104).

[0043] Brief reference Figure 4 The diagram illustrates a registration process 400 for a registered user 102R on vehicle 10, to create a user account 252 including user characteristics 254 of the registered user 102R. For example, when the registered user 102R initiates the registration process 400, the registered user 102R can receive instructions from vehicle 10 and / or an application published by the manufacturer of vehicle 10, instructing the registered user 102R to stand at a configurable distance D from the sensing system 18 of vehicle 10. The sensing system 18 can then collect user data 32 to provide to the sensing module 220 for classifying the registered user 102R. Here, the sensing module 220 can calculate the height H of the registered user 102R. 102 Width W of 102R for registered users 102And the height H of registered user 102R 102 and width W 102 The sum is used as user characteristic 254 for user account 252. In some implementations, the sensing module 220 uses the ground as a reference point to the top of registered user 102R to calculate the height H of registered user 102R. 102 Optionally, registered user 102R can manually set user characteristic 254 (e.g., the height H of registered user 102R). 102 Width W 102 User account 252 is constructed by inputting user preferences and certified device 104 into vehicle 10.

[0044] Refer again Figure 1 and Figure 2 User classifier 230 analyzes user data 32 and classifies the identity 232 of user 102. In an example where user data 32 corresponds to one of user accounts 252, user classifier 230 can classify the identity 232 of user 102 as a registered user 102R belonging to user account 252. Door selection model 240 can receive the identity 232 of user 102 as input and predict / identify the target door 20 of vehicle 10 for user 102 based on the classified identity 232 of user 102. For example, when the identity 232 of user 102 is an adult and user 102 is further carrying an authenticated device 104 (e.g., a mobile device), door selection model 240 can identify the target door 20 as the driver's door 20a and generate an instruction 242 instructing the target door 20a to be opened for user 102. For example, instruction 242 can specify that the target door 20a opens when user 102 enters the proximity area 24 of vehicle 10 close enough to open the target door.

[0045] Refer again Figure 2In some implementations, the door selection model 240 includes a machine learning model. For example, the machine learning model of the door selection model 240 can be continuously fine-tuned / updated through reinforcement learning from user feedback. Here, the machine learning model can be configured to receive the identity 232 of user 102 and user features 254 of user 102 as input, and generate a target door 20 for user 102 as output based on user features 254. Subsequently, user 102 can provide user feedback indicating user preferences 256. For example, when the target door 20 identified by the machine learning model is passenger door 20b, the user feedback can include adult user 102 selecting rear passenger doors 20c, 20d. This user feedback can indicate that user 102 has a user preference 256 of sitting in the rear of vehicle 10 rather than the front seat of vehicle 10. The approach side door system 200 can then fine-tune the machine learning model of the door selection model 240 based on the user feedback indicating user preferences 256 to improve the future predictions and instructions 242 of the door selection model 240.

[0046] Although this example involves a single user 102, it should be understood that the access side door system 200 can be implemented by any number of users 102 of the vehicle 10. For example, when the door selection model 240 receives input from the first and second authentication devices 104 and the classified identities of the first and second adult users 102, the door selection model 240 can select the driver's door 20a and the passenger door 20b as target doors 20a, 20b, and generate an instruction 242 instructing the target doors 20a, 20b to be automatically opened for the first and second adult users 102.

[0047] refer to Figure 3 An example configuration 300 of a user 102 approaching vehicle 10 is shown. As shown, user 102 includes a first user 102a, a second user 102b, a third user 102c, and a fourth user 102d. Here, each user 102a-102d has a corresponding authenticated device 104a-104d (e.g., a mobile device). When each user 102 approaches vehicle 10, device detector module 210 can detect the authenticated devices 104a, 104b, and 104d of user 102a-102d via authentication data 30 and trigger / activate sensing system 18 to collect user data 32 as input to sensing module 220. Here, device detector module 210 can identify neighboring areas 22a and 22b as containing authenticated devices 104a, 104b, and 104d, such that only the portion of sensing system 18 corresponding to neighboring areas 22a and 22b is activated to collect user data 32. Alternatively, the full perception system 18 can be activated to collect user data 32 in a 360-degree area around the vehicle 10.

[0048] Subsequently, user classifier 230 can classify the identities 232a-232d of each of users 102a-102d. For example, user classifier 230 can detect the height H of each of users 102a-102d. 102 and width W 102 The first user 102a is an adult (identity 232a), the second user 102b is an adult (identity 232b), the third user 102c is a child (identity 232c), and the fourth user 102d is a child (identity 232d).

[0049] Based on the identities 232a-232d of users 102a-102d, door selection model 240 can identify the target door 20 for each of users 102a-102d. In embodiments where any of users 102a-102d is registered user 102R, door selection model 240 can also receive corresponding user features 254, including the door preferences of users 102a-102d, as input. In some cases, door preferences can be provided by each of users 102 during the registration process 400. Continuing with the example, door selection model 240 can identify driver's door 20a as the target door 20 for the first user 102a with adult identity 232a, passenger door 20b as the target door 20 for the second user 102b with adult identity 232b, and left rear passenger door 20d as the target door for the third user 102c and the fourth user 102d, each with child identities 232c and 232d. Door selection model 240 can then generate instruction 242, which instructs doors 20a, 20b, and 20d to automatically open for users 102a to 102d when they arrive at vehicle 10 (e.g., enter adjacent area 24).

[0050] Figure 5 A flowchart illustrating an example arrangement of a method 500 for operating a control algorithm that utilizes autonomous sensors to open an approaching side door. Data processing hardware (e.g., Figure 1 Data processing hardware 12, 62) can execute data stored in memory hardware (e.g., Figure 1 The instructions on the memory hardware (14, 64) are arranged in an example configuration to perform the operations of method 500. At operation 502, method 500 includes detecting an authenticated device 104 in the vicinity area 22 of vehicle 10. At operation 504, method 500 also includes activating a sensing system 19 for the vicinity area 22 of vehicle 10. At operation 506, method 500 also includes detecting a user 102 in the vicinity area 22 of vehicle 10 and approaching vehicle 10, based on user data 32 captured by the sensing system 18.

[0051] At operation 508, method 500 further includes classifying the identity 232 of user 102 in the neighborhood 22 of vehicle 10 based on user data 32. Method 500 also includes, at operation 510, identifying a target door 20 of vehicle 10 for user 102 based on the classified identity 232. At operation 512, method 500 further includes instructing the target door 20 of vehicle 10 to automatically open for user 102.

[0052] Many embodiments have been described. However, it should be understood that various modifications can be made without departing from the spirit and scope of this disclosure. Therefore, other embodiments are within the scope of the appended claims.

[0053] The foregoing description is provided for illustrative and descriptive purposes. It is not intended to be exhaustive or limiting of this disclosure. Elements or features of a particular configuration are generally not limited to that particular configuration, but are interchangeable where applicable and can be used in selected configurations, even if not specifically shown or described. They can also be varied in many ways. Such variations should not be considered as departing from this disclosure, and all such modifications are intended to be included within the scope of this disclosure.

Claims

1. A computer-implemented method that, when executed on data processing hardware, causes the data processing hardware to perform operations comprising: detecting an authenticated device in a proximity area of a vehicle; activating a perception system for the proximity area of the vehicle; detecting, in user data captured by a perception system, a user in a proximity area of a vehicle and approaching the vehicle; classifying an identity of the user in the proximity area of the vehicle based on the user data; identifying, for the user, a target door of the vehicle based on the classified identity of the user; and directing the target door of the vehicle to automatically open for the user. Detecting an authenticated device in a proximity area of a vehicle comprises receiving authentication data captured by an authentication system, the authentication data indicating that an authenticated device is in a proximity area of the vehicle.

2. The method of claim 1, wherein, The authenticated device comprises one or more of a mobile device or a key fob.

3. The method of claim 1, wherein, The perception system comprises one or more of a light detection and ranging (LIDAR) or a camera system.

4. The method of claim 1, wherein, Classifying an identity of the user in the proximity area of the vehicle based on the user data comprises comparing the user data to one or more user accounts, each user account associated with a registered user of the vehicle.

5. The method of claim 1, wherein, Each user account of the one or more user accounts comprises respective user characteristics of a registered user of the vehicle.

6. The method of claim 5, wherein, The respective user characteristics comprise one or more of:

7. The method of claim 6, wherein, a height of the registered user; a width of the registered user; a door preference of the registered user; or a device of the registered user. The respective user characteristics are added to the user account during a registration process.

8. The method of claim 6, wherein, The classified identity of the user and one or more user characteristics of the user are received as inputs to a machine learning model, and the target door is generated as an output.

9. The method of claim 1, wherein identifying, for the user, the target door of the vehicle based on the user's classified identity comprises: The operations further comprise:

10. The method of claim 9, wherein, receiving user feedback indicating a user preference; and updating the machine learning model based on the user feedback. ​

Images