Boarding processing method and device for automatic driving taxi

Abstract

The invention discloses a getting-on processing method and device for an automatic driving taxi. The method comprises the following steps: analyzing positioning information; when it is determined that the passenger is within the preset range, feature information of pedestrians on the current road is detected and analyzed; when the analysis result shows that the vehicle stopping behavior is detected and the duration of the vehicle stopping behavior exceeds the preset duration, identifying the current position information of the passenger; determining the parking position of the vehicle according to the position information; the vehicle is controlled to stop according to a route corresponding to the stop position, so that a right rear vehicle door is aligned with the current position information; then, acquiring unlocking information initiated by passenger equipment; after the information verification is passed, a right rear door is triggered to be opened, so that the passenger gets on the bus. According to the invention, the technical problem that the passenger needs to walk to the designated station to get on the taxi and the riding experience is affected because the unmanned taxi is not flexible in parking mode and can only be parked at the preset station and cannot be parked at the non-predetermined station in the prior art is solved.

Description

Technical Field

[0001] This invention relates to the field of autonomous vehicle control technology, and more specifically, to a method and apparatus for handling the boarding of an autonomous taxi. Background Technology

[0002] Traditional robotaxi operations typically rely on pre-set pick-up points. Passengers must book a vehicle in advance via a mobile app and wait at the designated location. This model limits passenger flexibility, especially when passengers are unsure of the exact pick-up location or when weather conditions are inclement. In such cases, passengers may need to walk in rain or snow to the designated pick-up point and wait for the robotaxi to arrive. This not only reduces the passenger experience but may also prolong waiting times due to the uncertainty of outdoor conditions.

[0003] Most robotaxis on the market currently use a fixed-stop pick-up method, where passengers need to enter or select a pick-up point in the app, and the robotaxi will then go to the designated location to pick them up. While this model simplifies vehicle dispatching to some extent, it also has many problems. For example, on busy streets, there may be pedestrians or obstacles between the passenger and the stop, affecting the passenger's ability to quickly find the vehicle; in inclement weather, passengers are often unwilling to walk far and hope that the vehicle will proactively approach them; at night or in poor visibility conditions, the difficulty of passenger-vehicle identification increases, which may lead to inaccurate passenger location and affect the boarding experience.

[0004] Furthermore, existing robotaxi technology primarily relies on passenger location information from their mobile phones for passenger identification, matching passenger location with vehicle location to pick up passengers. However, this method has limitations in practical applications. For example, passenger location information may be inaccurate when mobile signal is unstable; in multi-passenger scenarios, the vehicle may have difficulty determining which passenger is the one who made the reservation, easily leading to incorrect pick-up.

[0005] There is currently no effective solution to the above problems. Summary of the Invention

[0006] This invention provides a method and apparatus for handling the boarding of autonomous taxis, which at least solves the technical problem in the related art that the stopping method of driverless taxis is not flexible enough, and they can only stop at preset stations and cannot stop at non-predetermined station locations, causing passengers to have to walk to a designated station to board, thus affecting the riding experience.

[0007] According to one aspect of the present invention, a method for handling boarding of an autonomous taxi is provided, comprising: upon receiving positioning information from a passenger device, analyzing the positioning information to determine whether a passenger is located within a predetermined range around a preset starting point, wherein the preset starting point is a boarding starting point set by the passenger device; when it is determined that the passenger is within the predetermined range, detecting feature information of pedestrians on the current road using sensor devices of the autonomous taxi; analyzing the feature information to obtain an analysis result; when the analysis result indicates that a hailing behavior has been detected and the duration of the hailing behavior exceeds a preset duration, identifying the current location information of the passenger corresponding to the hailing behavior; determining the stopping position of the autonomous taxi according to the longitudinal coordinates corresponding to the current location information; controlling the autonomous taxi to stop according to the route corresponding to the stopping position, so that the right rear door of the autonomous vehicle is aligned with the current location information; after the right rear door is aligned with the current location information, acquiring unlocking information initiated by the passenger device; and after the unlocking information is verified, triggering the opening of the right rear door of the autonomous taxi to allow the passenger to board.

[0008] Optionally, determining that the passenger is located within the predetermined range includes: analyzing the location information to obtain the current distance between the passenger device and the preset starting point; determining that the passenger is located within the predetermined range when the current distance is continuously less than a preset distance within a predetermined time window; and determining that the passenger is located within the predetermined range upon receiving a first notification message from the passenger device indicating arrival at the preset starting point.

[0009] Optionally, the sensor device includes a vision device and a lidar device. Detecting pedestrian feature information on the road using the sensor device of the autonomous taxi includes: detecting passenger hailing actions in a preset area on the right side of the autonomous taxi using the vision device to obtain a pedestrian image in the preset area on the right side; extracting features from the pedestrian image to obtain the pedestrian's body movements, wherein the body movements include at least: arm and hand movements and head gaze direction; detecting point cloud data of the pedestrian using the lidar device; and fusing the body movements with the point cloud data to obtain the feature information.

[0010] Optionally, the feature information is analyzed to obtain the analysis result, including: analyzing the feature information to obtain the pedestrian's action and the duration of the action, and obtaining the analysis result.

[0011] Optionally, the boarding process further includes: when the analysis result indicates that a vehicle-blocking behavior has been detected and the duration of the vehicle-blocking behavior exceeds a first preset duration, generating a second prompt message to notify the passenger that the vehicle-blocking behavior has taken effect.

[0012] Optionally, the boarding process further includes: during the process of controlling the autonomous taxi to stop according to the route corresponding to the stop location, if it is detected that the total duration of the passenger continuously moving away from the autonomous taxi is greater than or equal to a second preset duration; or, when it is detected that the identifier displayed in the display component of the autonomous taxi disappears, stopping according to the route corresponding to the stop location is stopped, wherein the identifier is an identifier assigned by the autonomous taxi to the identified passenger, and the identifier is used to track the passenger's behavior and location.

[0013] Optionally, the boarding process further includes: after stopping along the route corresponding to the stop location, continuing to stop at the preset starting point.

[0014] Optionally, the boarding process further includes: during the process of controlling the autonomous taxi to stop according to the route corresponding to the stop location, acquiring the signal strength of the Bluetooth signal of the passenger device at a predetermined period; when it is determined that the signal strength increases sequentially according to the acquisition order, continuing to control the autonomous taxi to stop according to the route corresponding to the stop location; when it is determined that the signal strength decreases sequentially according to the acquisition order within a predetermined time period, stopping according to the route corresponding to the stop location is stopped, and then continuing to stop towards the preset starting point.

[0015] Optionally, the boarding process further includes: generating a temporary state while controlling the autonomous taxi to stop according to the route corresponding to the stop location so that the right rear door of the autonomous vehicle is aligned with the current location information; switching the order processing flow of the autonomous taxi to the temporary state; and switching from the temporary state to the state of arriving at the preset starting point after determining that the right rear door is open.

[0016] According to another aspect of the present invention, a boarding processing device for an autonomous taxi is also provided, comprising: a first determining unit, configured to analyze the positioning information received from a passenger device to determine whether a passenger is located within a predetermined range around a preset starting point, wherein the preset starting point is a boarding starting point set by the passenger device; a first detecting unit, configured to detect the characteristic information of pedestrians on the current road using the sensor device of the autonomous taxi when it is determined that the passenger is located within the predetermined range; a first analyzing unit, configured to analyze the characteristic information to obtain an analysis result; and a first identifying unit, configured to identify the passenger when the analysis result indicates that a hailing behavior has been detected. When the duration of the hailing behavior exceeds a preset duration, the system identifies the current location information of the passenger corresponding to the hailing behavior; a second determining unit is used to determine the stopping position of the autonomous taxi based on the longitudinal coordinates corresponding to the current location information; a first control unit is used to control the autonomous taxi to stop according to the route corresponding to the stopping position, so that the right rear door of the autonomous vehicle is aligned with the current location information; a first acquiring unit is used to acquire unlocking information initiated by the passenger device after the right rear door is aligned with the current location information; a first triggering unit is used to trigger the right rear door of the autonomous taxi to open after the unlocking information is verified, so that the passenger can board the vehicle.

[0017] Optionally, the first determining unit includes: a first analysis module, configured to analyze the positioning information to obtain the current distance between the passenger device and the preset starting point, and determine that the passenger is located within the predetermined range when the current distance is continuously less than the preset distance within a predetermined time window; and a first determining module, configured to determine that the passenger is located within the predetermined range when receiving a first prompt message initiated by the passenger device indicating arrival at the preset starting point.

[0018] Optionally, the first detection unit includes: a first detection module, configured to detect passenger hailing actions in a preset area on the right side of the autonomous taxi using the vision device to obtain a pedestrian image in the preset area on the right side, and to extract features from the pedestrian image to obtain the pedestrian's limb movements, wherein the limb movements include at least: arm and hand movements and head gaze direction; a second detection module, configured to detect point cloud data of the pedestrian using the lidar device; and a first fusion module, configured to fuse the limb movements with the point cloud data to obtain the feature information.

[0019] Optionally, the first analysis unit includes a second analysis module, used to analyze the feature information to obtain the pedestrian's action and the duration of the action, and to obtain the analysis result.

[0020] Optionally, the boarding processing device further includes: a first prompting module, used to generate a second prompting message when the analysis result indicates that a vehicle-blocking behavior has been detected and the duration of the vehicle-blocking behavior exceeds a first preset duration, so as to prompt the passenger that the vehicle-blocking behavior has taken effect.

[0021] Optionally, the boarding processing device further includes: a first stop module, configured to, during the process of controlling the autonomous taxi to stop according to the route corresponding to the stop location, if it is detected that the total duration of the passenger continuously moving away from the autonomous taxi is greater than or equal to a second preset duration; or, if it is detected that the identifier displayed in the display component of the autonomous taxi disappears, stop stopping according to the route corresponding to the stop location, wherein the identifier is an identifier assigned by the autonomous taxi to the identified passenger, and the identifier is used to track the passenger's behavior and location.

[0022] Optionally, the vehicle loading processing device further includes: a first adjustment module, used to continue stopping towards the preset starting point after stopping along the route corresponding to the stopping position.

[0023] Optionally, the boarding processing device further includes: a first control module, configured to acquire the signal strength of the Bluetooth signal of the passenger device at a predetermined period during the process of controlling the autonomous taxi to stop according to the route corresponding to the stop location; and to continue controlling the autonomous taxi to stop according to the route corresponding to the stop location when it is determined that the signal strength increases sequentially according to the acquisition order; and a second stop module, configured to stop stopping according to the route corresponding to the stop location and continue stopping towards the preset starting point when it is determined that the signal strength decreases sequentially according to the acquisition order within a predetermined time period.

[0024] Optionally, the boarding processing device further includes: a first alignment module, used to generate a temporary state during the process of controlling the autonomous taxi to stop according to the route corresponding to the stopping position so that the right rear door of the autonomous vehicle is aligned with the current position information; a first switching module, used to switch the order processing flow of the autonomous taxi to the temporary state; and a second switching module, used to switch from the temporary state to the state of arriving at the preset starting point after determining that the right rear door is open.

[0025] According to one aspect of the present invention, an autonomous taxi is provided, the autonomous taxi using the boarding processing method for an autonomous taxi as described above.

[0026] According to one aspect of the present invention, a processor is provided for running a program, wherein the program executes the boarding processing method for an autonomous taxi as described in any one of the above embodiments.

[0027] According to one aspect of the present invention, a computer program product is provided, including computer instructions that, when executed by a processor, perform the boarding processing method for an autonomous taxi as described above.

[0028] According to one aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein the program, when executed by a processor, performs the boarding processing method for an autonomous taxi as described in any one of the above embodiments.

[0029] In this embodiment of the invention, after receiving location information from the passenger device, the location information is analyzed to determine whether the passenger is located within a predetermined range around a preset starting point, where the preset starting point is the boarding starting point set by the passenger device. When it is determined that the passenger is within the predetermined range, the sensor device of the autonomous taxi detects the feature information of pedestrians on the current road. The feature information is analyzed to obtain the analysis result. When the analysis result indicates that a hailing behavior has been detected and the duration of the hailing behavior exceeds a preset duration, the current location information of the passenger corresponding to the hailing behavior is identified. The stopping position of the autonomous taxi is determined according to the longitudinal coordinates corresponding to the current location information. The autonomous taxi is controlled to stop according to the route corresponding to the stopping position so that the right rear door of the autonomous vehicle is aligned with the current location information. After the right rear door is aligned with the current location information, the unlocking information initiated by the passenger device is obtained. After the unlocking information is verified, the right rear door of the autonomous taxi is triggered to open so that the passenger can board the vehicle. The above technical solution allows passengers to hail autonomous taxis at non-pre-set locations or in inclement weather conditions. The vehicles can dynamically adjust their stopping positions based on passenger needs, without strictly adhering to fixed stops. This reduces waiting and walking time for passengers in inclement weather or at non-pre-set locations, significantly improving passenger convenience and the overall riding experience. It increases dynamic stopping flexibility, improves passenger recognition accuracy, enhances the flexibility and security of order processing, and improves riding convenience in inclement weather conditions. Furthermore, it solves the technical problem in related technologies where driverless taxis lack flexibility in stopping, only allowing stops at pre-set locations and forcing passengers to walk to designated stops, thus impacting the riding experience. Attached Figure Description

[0030] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0031] Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of handling boarding in an autonomous taxi according to an embodiment of the present invention.

[0032] Figure 2 This is a flowchart of a method for handling the boarding of an autonomous taxi according to an embodiment of the present invention;

[0033] Figure 3 This is a schematic diagram of a boarding processing device for an autonomous taxi according to an embodiment of the present invention.

[0034] The above figures include the following reference numerals:

[0035] 102. Processor; 104. Memory; 106. Transmission device; 108. Input / output device. Detailed Implementation

[0036] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0037] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0038] As described in the background section, the stopping methods of driverless taxis in related technologies are not flexible enough, only allowing them to stop at preset stations and unable to stop at non-predetermined locations. This forces passengers to walk to designated stations to board, impacting the riding experience. To address these issues and improve passenger experience, this invention proposes a new robotaxi boarding process: passengers flag down the vehicle, which is then identified and marked by the vehicle's perception system. The vehicle control module then stops based on the marked passenger's location, prioritizing stopping the right rear door in front of the passenger. This solution aims to improve passenger convenience, reduce waiting time and walking distance in inclement weather, and improve passenger identification accuracy and recall rate through the fusion of visual and lidar perception technologies, ensuring enhanced riding safety and experience. Specifically, this invention provides a method and apparatus for handling boarding in autonomous taxis, an autonomous taxi, a computer-readable storage medium, a processor, and a computer program product.

[0039] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention.

[0040] The methods and embodiments provided in this invention can be executed on a mobile terminal, a computer terminal, or a similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of handling boarding in an autonomous taxi according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0041] The memory 104 can be used to store computer programs, such as application software programs and modules, like the computer program corresponding to the autonomous taxi boarding processing method in this embodiment of the invention. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, thereby implementing the above-described method. The memory 104 may include high-speed random access memory and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor 102, and these remote memories can be connected to the mobile terminal via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. The transmission device 106 is used to receive or send data via a network. Specific examples of the aforementioned networks may include wireless networks provided by the mobile terminal's communication provider. In one example, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to communicate with the Internet. In one example, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0042] Example 1

[0043] According to an embodiment of the present invention, a method embodiment for a method of handling the boarding of an autonomous taxi is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0044] Figure 2 This is a flowchart of a method for handling the boarding of an autonomous taxi according to an embodiment of the present invention, such as... Figure 2 As shown, the method includes the following steps:

[0045] Step S202: After receiving the location information from the passenger device, the location information is analyzed to determine whether the passenger is located within a predetermined range around the preset starting point, where the preset starting point is the boarding starting point set by the passenger device.

[0046] In this embodiment, when the autonomous taxi approaches the starting point of the passenger's scheduled trip, the vehicle will begin to prepare and pay attention to possible passenger hailing behavior within a 100-meter radius before and after the pick-up point.

[0047] In this embodiment, after a passenger sets their boarding starting point (i.e., a preset starting point) via a mobile application or smart device, the system immediately begins monitoring the passenger's location. Based on continuous location data sent by the passenger's device, an algorithm calculates the passenger's relative position to the preset starting point, determining whether the passenger is within a predetermined range of ±100 meters around the starting point.

[0048] For example, autonomous vehicles (i.e., autonomous taxis) can obtain real-time GPS or BeiDou satellite positioning data from passengers' smartphones (i.e., passenger devices) or other positioning devices to locate passengers. Upon receiving the location information, it compares it with the coordinates of a preset starting point. By calculating the straight-line distance between the two or using more complex path planning algorithms to estimate the travel distance, it determines whether the passenger is within a predetermined range around the preset starting point. If the passenger is indeed within the predetermined range near the preset starting point, the system considers the passenger capable of hailing the taxi and further verifies whether the relevant stopping logic needs to be activated. Conversely, if the passenger is far from the preset starting point, the system considers that hailing the taxi may not be applicable in the current situation and therefore will not initiate the corresponding response procedure.

[0049] By implementing this control method, passenger locations are pre-screened, ensuring that only passengers within a reasonable range are identified and responded to. This avoids ineffective processing of irrelevant information from a distance, improving system efficiency and resource utilization. When a passenger approaches the preset starting point, the system can enter a ready state in advance to more promptly capture and respond to the passenger's waving action, reducing passenger waiting time.

[0050] Step S204: When it is determined that the passenger is within the predetermined range, the sensor equipment of the autonomous taxi detects the characteristic information of pedestrians on the current road.

[0051] In this embodiment, the autonomous vehicle uses a combination of vision and LiDAR technologies to detect and identify specific actions made by passengers to flag down a vehicle. Visual perception typically refers to image data captured by cameras, while LiDAR provides high-precision 3D point cloud data. Visual perception helps identify action details, while LiDAR provides additional spatial positioning and object boundary information; the two complement each other, ensuring the system can accurately distinguish passengers from other pedestrians. The system focuses on pedestrians near the right side of the road and in the rightmost lane, because flagging down a vehicle usually occurs on the right side of the vehicle, facilitating direct boarding, and the rightmost lane is an ideal parking location for vehicles, minimizing traffic interference. The system pays particular attention to pedestrians' arm and hand movements, as well as the direction of their head gaze.

[0052] Autonomous vehicles are typically equipped with a variety of sensors, including but not limited to high-definition cameras, LiDAR, millimeter-wave radar, and ultrasonic sensors. These sensors each provide different types of data, such as visual images, 3D environment modeling, and information on the speed and direction of moving objects. By integrating the information from these sensors, a comprehensive pedestrian detection and behavior recognition system can be established.

[0053] By implementing this control method, autonomous vehicles can more intelligently and accurately identify and respond to passengers' hailing requests, improving the user experience while ensuring operational safety and efficiency. This technological solution has significant practical application value in the field of driverless taxis, especially in complex urban environments, where it can effectively improve service quality and operational efficiency.

[0054] Step S206: Analyze the feature information to obtain the analysis results.

[0055] In this embodiment, the system defines several explicit actions for stopping a vehicle, including raising the arm and waving the palm, extending the arm and waving it left and right and up and down, and raising one arm diagonally upward with the thumb. Although head posture recognition is technically challenging, it can enhance the system's confidence as an auxiliary judgment factor.

[0056] This method utilizes computer vision and machine learning techniques. The system can extract key pedestrian features, such as body shape, posture, facial expressions, and gestures, from video streams captured by cameras. LiDAR provides the pedestrian's precise 3D position and trajectory relative to vehicles. The extracted pedestrian feature information is then fed into a deep learning model for processing. This model, trained on a large labeled dataset, is capable of recognizing specific gestures used to flag down or board vehicles.

[0057] By implementing this control method, the system can accurately distinguish between different individuals on the road and identify specific hailing behaviors, thereby avoiding misidentification of other non-passengers and improving service accuracy. Rapid analysis of sensor data enables vehicles to make immediate stopping decisions, reducing decision delays and improving vehicle dispatching and operational efficiency.

[0058] Step S208: When the analysis result indicates that a vehicle-blocking behavior has been detected and the duration of the vehicle-blocking behavior exceeds a preset duration, the current location information of the passenger corresponding to the vehicle-blocking behavior is identified.

[0059] In this embodiment, the duration of the action must be at least 1 second. This threshold is set to filter out brief, sporadic actions, ensuring that the system's recognition of passenger actions is stable and intentional, rather than random or unintentional physical movements. The passenger's mobile phone location has been verified at least once, and the distance to the station has consistently been ≤100 meters within any 5-second interval (slider range).

[0060] This method continuously observes the pedestrian's arm and hand movements, verifying whether the behavior has reached a preset duration. By integrating data from a visual perception system (i.e., a camera) and LiDAR, it achieves precise location tracking of the pedestrian. The visual system provides details about the posture and movement, while LiDAR supplements this with high-precision location information, including the pedestrian's exact location and trajectory in three-dimensional space.

[0061] By implementing this control method, the system can accurately identify passengers waving for a ride, avoiding misidentification of irrelevant pedestrians, reducing unnecessary stops, and improving the smoothness of the entire service process and passenger satisfaction. Precise passenger identification and dynamic location updates help vehicles schedule and stop more efficiently, avoiding delays caused by inaccurate location information, and improving the operational efficiency and responsiveness of the entire autonomous taxi service.

[0062] Step S210: Determine the stopping position of the autonomous taxi based on the longitudinal coordinates corresponding to the current location information.

[0063] In this embodiment, when a vehicle-stopping behavior is detected, the autonomous vehicle will obtain the location and mark the passenger, and provide the target stopping point based on its longitudinal coordinates or distance.

[0064] This method determines the optimal stopping point for the vehicle based on the longitudinal coordinate analysis of the passenger's current precise location. In this scenario, the longitudinal coordinate refers to the passenger's position relative to a preset starting point or the detected point of hail-a-car behavior in the road direction (i.e., the direction of vehicle travel).

[0065] By implementing this control method, autonomous taxis can achieve instant response to passenger requests and precise adjustment of stopping locations. First, the vehicle stops directly in front of the passenger, significantly reducing the walking distance before boarding, especially in non-designated locations or in inclement weather, greatly improving the convenience and comfort of the ride. Second, by dynamically adjusting the stopping location, autonomous vehicles can avoid wasting time at unnecessary stops, reducing ineffective stops and waiting, thereby improving overall dispatch efficiency and vehicle turnover rate. Finally, determining the stopping point based on precise coordinate data ensures the safety of stopping operations, avoiding potential traffic accidents or legal disputes caused by improper stopping, and providing a safer traffic environment for passengers and road users.

[0066] Step S212: Control the autonomous taxi to stop according to the route corresponding to the stop location, so that the right rear door of the autonomous vehicle is aligned with the current location information.

[0067] In this embodiment, after receiving a passenger's hailing signal and determining the passenger's precise location, the autonomous taxi adjusts its trajectory. The ultimate goal is to align the vehicle's right rear door with the passenger's location, with an error range controlled within ±0.5 meters. In other words, the vehicle will stop as accurately as possible in front of the passenger, ensuring the right rear door is right next to them for easy boarding. The ±0.5-meter error mentioned here refers to the maximum permissible deviation between the vehicle's stopping position and the target stopping position (i.e., the passenger's actual location).

[0068] This method involves the collaborative operation of the vehicle control system and the path planning algorithm. After confirming the passenger's specific location (especially the longitudinal coordinates), the vehicle's central processing unit (CPU) synchronizes this information with the autonomous driving module. Subsequently, based on the passenger's location information and the vehicle's current state, the autonomous driving algorithm generates a new driving route, the destination of which is the designated parking location. During route planning, the algorithm not only considers the shortest straight distance but also ensures the safety and legality of the path, avoiding situations such as driving against traffic or crossing obstacles. As the vehicle travels along the planned route, its control system continuously adjusts steering, acceleration, and braking to ensure the vehicle can stop smoothly and accurately. During the parking process, the vehicle's positioning system (such as a combination of GPS and IMU, lidar ranging, etc.) continuously provides feedback on the distance between the vehicle and the destination until the right rear door is aligned with the passenger's position, with the error remaining within ±0.5 meters.

[0069] By implementing this control method, autonomous taxis can achieve a highly personalized response to passenger requests in complex urban environments. Precise vehicle parking reduces inconvenience for passengers before boarding, especially for those with mobility issues, carrying large luggage, or traveling in inclement weather conditions, greatly enhancing the convenience and comfort of the ride.

[0070] Step S214: After the right rear door is aligned with the current location information, obtain the unlocking information initiated by the passenger device.

[0071] In this embodiment, once the system recognizes and responds to a passenger's hailing action, causing the vehicle to successfully stop near the passenger, the vehicle's order management system will automatically switch to a special state—stopping after a passenger hailed the vehicle. This state is specifically designed to address the workflow issue when a passenger hailes a ride; it allows the passenger to unlock the door and board immediately before the vehicle has fully reached the preset starting point, without any additional waiting.

[0072] This method utilizes wireless communication technology between the passenger's mobile device (such as a smartphone) and the vehicle to achieve remote unlocking. Once the vehicle's right rear door is precisely aligned with the passenger's position, the vehicle's control system begins listening for unlock signals from the passenger's device. This operation relies on various communication modules installed in the vehicle, such as Bluetooth, Wi-Fi, or cellular networks, which can receive unlock commands from the passenger's device within a specific range. Typically, this unlock command is issued by the passenger using a dedicated ride-hailing app on their mobile device. Upon receiving the unlock request, the vehicle performs a series of verifications, including checking whether the signal source matches pre-registered passenger information and confirming whether the alignment accuracy meets the unlocking conditions. Once the verification is successful, the vehicle's electronic lock system is activated, allowing the passenger to open the door and board the vehicle.

[0073] By implementing this control method, passengers can send an unlock command via a mobile app to open the door and board the vehicle even before it has fully arrived at its planned starting point. This not only reduces passenger waiting time in inclement weather or emergencies and improves the convenience of boarding, but also effectively mitigates the risk of system misjudgment, because the system has a second chance to confirm before the passenger actually unlocks and boards, ensuring the accuracy of service connection.

[0074] Step S216: After the unlocking information is verified, the right rear door of the autonomous taxi is opened to allow passengers to board.

[0075] In this embodiment, if the system discovers during the subsequent confirmation process that the previously identified "passenger" is not actually a real reserved passenger, or that the passenger has changed their decision to board, the vehicle can quickly exit the "passenger-hailed and stopped" state, restart the normal passenger pick-up process, and proceed to the next reserved starting point or perform other tasks, without causing confusion or unnecessary waiting time due to the unlocked vehicle status.

[0076] This method involves the system immediately initiating a verification procedure after the vehicle successfully receives the unlocking request initiated by the passenger's device. This procedure involves checking the legitimacy of the signal source and the accuracy of the location information. During verification, the vehicle control system compares the passenger ID carried in the unlocking signal with the passenger information of the booked trip in the system to confirm the legitimacy of the request source. Simultaneously, by continuously tracking the passenger's movement path and real-time location, the system checks whether the vehicle's right rear door is indeed aligned with the passenger's location information to ensure the correct opening direction and avoid situations where passengers need to walk to the other side of the vehicle or search for the door. Once the unlocking information is verified correctly, confirming the passenger's identity and boarding location, the vehicle's electronic door lock system is activated, the right rear door unlocks and opens automatically, providing passengers with a seamless and secure boarding route.

[0077] By implementing this control method, autonomous taxis can provide passengers with a more efficient, convenient, and safer boarding experience. When passengers successfully unlock the door using their mobile devices, they not only eliminate the need for manual unlocking but also avoid the inconvenience of searching for the correct door in inclement weather such as rain or snow. More importantly, this process significantly enhances boarding safety, as the door will only open automatically after the system has fully verified the legitimacy of the unlock request and confirmed that the right rear door is precisely aligned with the passenger's location information. This design avoids safety hazards caused by unauthorized personnel or misoperation, ensuring that only passengers with pre-booked trips can smoothly enter the vehicle and enjoy the service.

[0078] As described above, in this embodiment, after receiving location information from the passenger device, the location information is analyzed to determine whether the passenger is within a predetermined range around a preset starting point, where the preset starting point is the boarding starting point set by the passenger device. When it is determined that the passenger is within the predetermined range, the sensor devices of the autonomous taxi detect the feature information of pedestrians on the current road. The feature information is analyzed to obtain the analysis results. The stopping position of the autonomous taxi is determined based on the longitudinal coordinates corresponding to the current location information. The autonomous taxi is controlled to stop according to the route corresponding to the stopping position, so that the right rear door of the autonomous vehicle is aligned with the current location information. Once the right rear door is aligned with the current location information... Afterwards, the system obtains the unlocking information initiated by the passenger's device. Once the unlocking information is verified, the right rear door of the autonomous taxi is opened to allow the passenger to board. This achieves the goal of allowing passengers to hail an autonomous taxi at non-preset locations or in inclement weather conditions. The vehicle can dynamically adjust its stopping position according to the passenger's actual needs, without strictly adhering to fixed stops. This reduces the waiting and walking time for passengers in inclement weather or at non-stop locations, significantly improving passenger convenience and riding experience. Thus, it achieves the technical effects of increasing dynamic stopping flexibility, improving passenger recognition accuracy, enhancing the flexibility and security of the order processing process, and improving riding convenience in inclement weather conditions.

[0079] Therefore, the technical solution provided by the above embodiments of the present invention solves the technical problem in the related art that the stopping method of driverless taxis is not flexible enough, and can only stop at preset stations, and cannot stop at non-predetermined station locations, which causes passengers to have to walk to the designated station to board the car, thus affecting the riding experience.

[0080] According to the above embodiments of the present invention, determining that a passenger is located within a predetermined range includes: analyzing location information to obtain the current distance between the passenger device and a preset starting point; determining that the passenger is located within a predetermined range when the current distance is continuously less than a preset distance within a predetermined time window; and determining that the passenger is located within a predetermined range when a first notification message indicating arrival at the preset starting point is received from the passenger device.

[0081] In this embodiment, the geographical range within which the autonomous taxi begins responding to a passenger's hailing action is defined as within 100 meters before and after the preset passenger pick-up point. To improve the accuracy of vehicle stopping and passenger identification, two pre-judgment conditions are proposed. If either condition is met, the vehicle will initiate the hailing and stopping process. These two conditions are: within any past 5 seconds, the passenger's mobile phone location has at least once recorded showing that they are no more than 100 meters away from the preset pick-up point. This means that even if the passenger does not directly click "Arrived at the pick-up point," as long as their actual location is close enough to the point, the autonomous taxi will recognize their hailing action and prepare to stop; or the passenger actively clicks the "I have arrived at the pick-up point" button on the ride-hailing app to directly inform the vehicle that they are ready to board. If neither of the above two situations occurs, that is, the passenger is neither within 100 meters of the point nor has confirmed arrival through the app, then even if the vehicle detects the hailing action, it will not initiate the stopping process.

[0082] This method analyzes the location information of passenger devices (such as smartphones), combined with time windows and preset distance conditions, to intelligently determine whether a passenger is in a valid location where an autonomous taxi can respond to their hailing request. Specifically, the system continuously tracks and analyzes the GPS or BeiDou positioning data of the passenger device to calculate the distance between the passenger's current location and a preset starting point. If this distance remains within a preset distance (e.g., 100 meters) for any consecutive predetermined time window (e.g., 5 seconds), the system determines that the passenger is within a responsive predetermined range, thereby activating the hailing behavior recognition mechanism.

[0083] By implementing this control method, autonomous taxis can significantly improve their service quality and operational efficiency in complex urban environments. Accurate passenger location determination not only avoids false responses to distant or irrelevant hailing attempts and reduces ineffective stop attempts, but also ensures that when a passenger is indeed hailing near a preset starting point, the vehicle can respond quickly and precisely to their needs, shortening passenger waiting times and enhancing the riding experience.

[0084] According to the above embodiments of the present invention, the sensor device includes a vision device and a lidar device. The sensor device of the autonomous taxi detects the feature information of pedestrians on the current road, including: detecting passenger hailing actions in a preset area on the right side of the autonomous taxi using the vision device to obtain a pedestrian image in the preset area on the right side; extracting features from the pedestrian image to obtain the pedestrian's limb movements, wherein the limb movements include at least: arm and hand movements, and head gaze direction; detecting point cloud data of the pedestrian using the lidar device; and fusing the limb movements with the point cloud data to obtain feature information.

[0085] In this embodiment, hailing a taxi is defined as a series of common human actions that conform to daily habits, such as raising the arm above the shoulder, waving the hand, or giving a thumbs up. These are all actions that people naturally make when hailing a taxi on the street. To ensure that passengers are aware of and can utilize this service, the ride-hailing app has a dedicated reminder entry. In the passenger's interface, this reminder entry clearly informs the passenger: "You can use these actions to directly hail a taxi, and the vehicle will stop for you, improving your boarding experience."

[0086] This method involves the efficient collaboration of vision and lidar devices. The vision device is primarily used to capture and analyze pedestrian images in a pre-defined area to the right of the autonomous taxi. Its core task is to accurately identify pedestrian body movements, including but not limited to arm waving, hand gestures, and head gaze direction—all important characteristics of traditional taxi-hailing behaviors. Simultaneously, the lidar device generates pedestrian point cloud data by emitting laser pulses and receiving the reflected signals. This data provides precise location and contour information of pedestrians in three-dimensional space, effectively supplementing the vision information.

[0087] For example, by recognizing a passenger's act of hailing a vehicle, a visual + LiDAR perception fusion method can be used to identify key passenger actions: a. Target detection range: Targeting pedestrians near the right side of the road and the rightmost lane; b. Key posture extraction: Arm and hand movements, head gaze direction. Specific movements include, but are not limited to: i. Arm raised above shoulder, palm swinging up and down (waving); ii. Arm extended, swinging left and right / up and down (waving); iii. Single arm extended diagonally upward with a thumb raised (signaling to stop); iv. Head gaze direction is only used as an auxiliary indicator due to accuracy issues; the core is the aforementioned key body movements. Furthermore, regarding duration, the overall duration of the first three actions must be ≥1 second.

[0088] By implementing this control method, the system ensures that vehicles can respond to passenger boarding requests promptly and accurately. Even without a driver, it can understand pedestrians' hand gestures to flag down the vehicle, just like a human driver, increasing vehicle flexibility and passenger convenience. Secondly, by fusing visual and lidar data, the system can effectively filter out background pedestrians or other irrelevant actions, reducing the false recognition rate and improving passenger experience and vehicle operational efficiency. Furthermore, the accurate recognition of body movements, especially arm and hand movements and head gaze direction, allows the vehicle to more intelligently determine the passenger's true intentions, avoiding invalid stops due to misunderstandings and further improving service accuracy.

[0089] According to the above embodiments of the present invention, the feature information is analyzed to obtain the analysis results, including: analyzing the feature information to obtain the pedestrian's actions and the duration of the actions, and obtaining the analysis results.

[0090] In this embodiment, the system stipulates that these key physical actions must be performed continuously for at least 1 second. This duration threshold is set to filter out brief, unintentional physical actions and avoid misjudgments. The 1-second time window can capture the complete sequence of vehicle-stopping actions while effectively avoiding unnecessary vehicle stopping decisions caused by momentary actions.

[0091] This method comprehensively utilizes data collected by the vision and LiDAR devices onboard autonomous taxis, employing advanced machine learning and artificial intelligence algorithms to meticulously analyze body movements in pedestrian images. The algorithm focuses on identifying arm waving, hand waving, and head direction; these elements are comprehensively evaluated to determine whether a pedestrian is performing a specific hailing action. Simultaneously, the system monitors the duration of these key postures, ensuring they reach a preset threshold—at least one second—to improve accuracy and stability, avoiding false alarms caused by brief or accidental movements.

[0092] By implementing this control method, the accuracy of autonomous taxis in recognizing passengers' intentions to hail a ride has been significantly improved, thereby optimizing the vehicle's stopping response mechanism. This mechanism ensures that the vehicle path will only be adjusted to approach and stop towards the target pedestrian when the system is certain that the pedestrian is making a clear attempt to hail a ride. This avoids responding to irrelevant pedestrians or erroneous actions, reduces the number of false stops and invalid stops, and improves operational efficiency.

[0093] According to the above embodiments of the present invention, the boarding processing method further includes: when the analysis result indicates that a vehicle-blocking behavior has been detected and the duration of the vehicle-blocking behavior exceeds a first preset duration, generating a second prompt message to prompt the passenger that the vehicle-blocking behavior has taken effect.

[0094] In this embodiment, in order to enhance the interaction and experience with passengers in the road environment and let passengers know that the autonomous vehicle has "seen" the vehicle being flagged down, the LED screen facing the autonomous vehicle will display the corresponding text "Vehicle flagged down, stopping in progress" and turn on the hazard lights in advance.

[0095] This method involves the intelligent perception system of an autonomous taxi analyzing feature information to identify that a passenger has indeed performed a compliant hailing action, and that the duration of this action exceeds a preset first threshold (e.g., 1 second). The system will then automatically trigger the generation of a specific second notification message. The logic behind this process is the application of a two-way confirmation mechanism: on the one hand, the system continuously observes and analyzes pedestrian actions to ensure the reliability and authenticity of the hailing signal; on the other hand, by sending a second notification message to the passenger, such as displaying "Hail detected, stopping" on the vehicle's LED screen or sending a reminder via a mobile app, the system clearly informs the passenger that their hailing action has been identified and is effective, and that the vehicle will respond soon.

[0096] Implementing this control method significantly improved the passenger experience and satisfaction with autonomous taxi services. By promptly sending a second notification message, passengers are clearly informed that the vehicle is responding to their hailing request, which not only reduces passenger anxiety and waiting time but also increases the transparency and interactivity of the entire service process. For passengers, this is similar to direct communication with a human driver, making the autonomous driving service feel more human.

[0097] According to the above embodiments of the present invention, the boarding process further includes: during the process of controlling the autonomous taxi to stop according to the route corresponding to the stop location, if it is detected that the total duration of the passenger continuously moving away from the autonomous taxi is greater than or equal to a second preset duration; or, when it is detected that the identifier displayed in the display component of the autonomous taxi disappears, stopping according to the route corresponding to the stop location is stopped, wherein the identifier is an identifier assigned by the autonomous taxi to the identified passenger, and the identifier is used to track the passenger's behavior and location.

[0098] In this embodiment, if the vehicle detects that a person originally marked as the target passenger has been moving away from the vehicle for more than 2 seconds during the parking process, or if the visual and lidar sensors can no longer "see" the passenger due to obstruction or other reasons (i.e. the marked ID disappears), the system will automatically cancel the current parking attempt.

[0099] This method employs a dynamic verification mechanism to monitor changes in the relative position between the passenger and the vehicle in real time. As the vehicle prepares to stop based on previously identified passenger location information, the system continuously monitors the passenger's behavior and position, particularly whether the passenger is moving towards the vehicle or maintaining sufficient proximity. If the system detects that a passenger has been moving away from the vehicle for more than a pre-set second preset time (e.g., 2 seconds), this may indicate that the passenger has changed their intention to board or encountered an emergency, causing them to be outside the vehicle's preset stopping range. Furthermore, the system also monitors whether the specific identifier assigned to the passenger on the autonomous taxi's display has disappeared. This identifier is crucial for the vehicle to track and confirm passenger identity; its disappearance may mean the passenger has left the camera's field of view or that the sensors can no longer accurately track their position. In this situation, to ensure operational safety and efficiency, the system immediately halts the current stopping operation and executes an emergency plan, such as rerouting to the original stop or searching for the next suitable stopping location.

[0100] Implementing this control method has yielded significant positive effects on improving the operational efficiency and passenger experience of autonomous taxis. First, it greatly enhances the flexibility and adaptability of vehicle stopping operations. When faced with uncertainties in passenger behavior, such as a passenger deciding not to board, experiencing sudden illness, or being distracted by other emergencies, the vehicle can react quickly, avoiding wasted time at unoccupied locations and reducing the impact on other road users. Second, this mechanism also improves service safety, particularly by avoiding the potential risk of attempting to stop when passengers are clearly away from the vehicle, reducing the likelihood of traffic accidents. For passengers, this mechanism means that even if their boarding intentions change, the vehicle can adjust its stopping strategy promptly, reducing passenger anxiety and waiting time, and improving the overall travel experience. Finally, by reducing unnecessary stops and waiting, this mechanism also reduces vehicle energy consumption, improves its operational efficiency in busy urban environments, and makes a positive contribution to environmental protection and resource conservation.

[0101] According to the above embodiments of the present invention, the boarding process further includes: after stopping along the route corresponding to the stopping position, continuing to stop at a preset starting point.

[0102] In this embodiment, when the system automatically cancels the current stop attempt, it then executes the predetermined stop logic, that is, returns to the originally planned boarding station to stop.

[0103] The core of this method is the "alternative plan" mechanism, which means that when the current task (i.e., dynamic passenger docking) encounters obstacles or cannot continue, the autonomous driving system will seamlessly switch to a pre-planned alternative route or operation procedure. The system pre-calculates the optimal path to the preset starting point based on map data, traffic conditions, and station information. When dynamic docking attempts are blocked, this path becomes the vehicle's default navigation target.

[0104] By implementing this control method, the reliability of autonomous taxi services and passenger confidence have been significantly enhanced. In practice, this means that even if a passenger fails to board on time or the vehicle cannot stop safely due to environmental factors, the vehicle will not remain stranded or blindly search for a new stop. Instead, it will orderly return to the preset starting point along a pre-set route to wait for the next passenger or proceed with the next dispatch. This approach not only ensures the efficient completion of each trip but also reduces passenger anxiety and dissatisfaction caused by abnormal situations, thus improving the overall riding experience.

[0105] According to the above embodiments of the present invention, the boarding process further includes: during the process of controlling the autonomous taxi to stop according to the route corresponding to the stop location, acquiring the signal strength of the Bluetooth signal of the passenger device at a predetermined period; when it is determined that the signal strength increases sequentially according to the acquisition order, continuing to control the autonomous taxi to stop according to the route corresponding to the stop location; when it is determined that the signal strength decreases sequentially according to the acquisition order within a predetermined time period, stopping according to the route corresponding to the stop location is stopped, and then continuing to stop towards the preset starting point.

[0106] In this embodiment, during the stopping process of the autonomous taxi, the system relies not only on visual and lidar recognition but also on changes in Bluetooth signal strength to determine whether a target passenger is approaching the vehicle. As the vehicle stops and gradually approaches the passenger, the Bluetooth signal between the vehicle and the passenger's phone strengthens as the distance decreases. The system periodically checks this signal strength (every second). If the signal continues to strengthen, it indicates that the vehicle is correctly approaching the passenger, and the system assumes that the stopping operation is in progress and in the correct direction, thus continuing the stopping procedure until the right rear door of the vehicle is aligned with the passenger. Conversely, if the Bluetooth signal strength weakens for two consecutive seconds during the stopping process, it indicates that the distance between the vehicle and the passenger is increasing, meaning the passenger may not be at the correct stopping position. This signal weakening is considered a warning of stopping failure, and the system immediately aborts the current special stopping operation because it means the vehicle cannot accurately stop in front of the passenger, or the passenger may have moved from their original position. To avoid getting stuck in an infinite loop after identifying the wrong passenger or failing to stop, the system employs a "fallback" strategy. If the aforementioned cancellation conditions are triggered during the stop, the vehicle will continuously monitor roadside hailing attempts en route to the original preset stop. If a valid hailing attempt is detected again, the system will update the target passenger's ID and restart the stop process. However, to prevent this process from repeating itself and affecting overall order-taking efficiency and service quality, the system limits this re-identification and stop attempt to a maximum of two times. If two consecutive attempts fail to stop or identify the correct passenger, the system will completely stop attempting to stop the vehicle by hailing and will only execute the normal stop process to the preset stop.

[0107] This method involves the system collecting Bluetooth signal strength from the passenger's device at set time intervals (e.g., every second) as the vehicle begins to stop in the direction of the identified passenger. If the signal strength increases over time, meaning each signal measurement is stronger than the previous one, it indicates that the distance between the vehicle and the passenger is gradually decreasing. The system determines that the stopping process is on the correct track and continues executing the current stopping command until the vehicle's right rear door is perfectly aligned with the passenger's position. However, if the signal strength decreases over a preset period (e.g., consecutive 2 seconds), meaning each measurement is weaker than the previous one, it indicates that the distance between the vehicle and the passenger is increasing instead of decreasing, potentially meaning the passenger has already moved or the vehicle is not stopping in the correct direction. In this case, the system immediately stops the stopping operation and abandons the current stopping position route. Subsequently, the vehicle will automatically resume the original route plan and head towards the preset pick-up point.

[0108] Implementing this control method has significantly improved the passenger boarding experience and overall operational efficiency of autonomous taxis. It not only provides vehicles with a real-time means of verifying passenger location, ensuring accurate stopping and reducing passenger waiting time due to positioning errors, but also enhances the system's ability to respond to unexpected situations, such as sudden passenger movement or slight deviations in the vehicle's positioning system. When the vehicle detects a weakening signal strength, it can quickly adjust its strategy, avoiding unnecessary stops, preventing potential passenger loss and dissatisfaction, and also reducing potential interference with other vehicles and pedestrians on the road, thus improving the overall safety of the traffic environment.

[0109] According to the above embodiments of the present invention, the boarding process further includes: generating a temporary state while controlling the autonomous taxi to stop according to the route corresponding to the stop location so that the right rear door of the autonomous vehicle is aligned with the current location information; switching the order processing flow of the autonomous taxi to the temporary state; and switching from the temporary state to the state of arriving at the preset starting point after determining that the right rear door is open.

[0110] In this embodiment, when the autonomous taxi recognizes a passenger's hailing signal and stops, the vehicle management system does not immediately enter the traditional "arrival at the origin" state. Instead, it first enters a new temporary state—"passenger hailing and stopping." In this temporary state, although the vehicle is not yet officially marked as "arrived at the origin," the passenger can already issue a command to unlock the vehicle door via a mobile app and board the vehicle.

[0111] This method is based on real-time response to passenger behavior and dynamic adjustment of vehicle location. When a temporary state is activated, the vehicle's order processing flow automatically switches to this state. At this time, the vehicle has not yet fully reached the preset "arrival at the origin" state, as it may be stopped at a location closer to the passenger than the originally planned stop. Once the vehicle has stopped in place and the passenger has successfully unlocked and opened the right rear door to board, the system's intelligent logic recognizes this behavior as a clear signal that the passenger has indeed boarded. At this point, the temporary state automatically ends, and the vehicle's order processing flow officially switches to the "arrival at the preset origin" state, signifying that the passenger has successfully boarded, and the vehicle can begin executing subsequent trip instructions, such as confirming passenger information and updating the trip status.

[0112] By implementing this control method, it allows passengers to begin the boarding process immediately the moment the vehicle comes to a complete stop, without waiting for any additional confirmation or status change, thereby significantly reducing passenger waiting time and improving the immediacy and convenience of boarding.

[0113] As described above, in this embodiment of the invention, by limiting the aforementioned constraints, while improving the accuracy of behavior recognition: during vehicle stops, a passenger waves to flag down the vehicle → the vehicle perception system identifies and marks the vehicle → a new parking location preference is assigned to the vehicle control module → the vehicle's right rear door is positioned as close to the passenger as possible. Of course, more location and interaction information will be utilized during the process to improve accuracy and recall, thereby enhancing the passenger experience.

[0114] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0115] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods of the various embodiments of this application.

[0116] Example 2

[0117] According to embodiments of the present invention, a boarding processing apparatus for an autonomous taxi that implements the above-described boarding processing method for an autonomous taxi is also provided. Figure 3 This is a schematic diagram of a boarding processing device for an autonomous taxi according to an embodiment of the present invention, as shown below. Figure 3 As shown, the device includes: a first determining unit 301, a first detecting unit 303, a first analyzing unit 305, a first identifying unit 307, a second determining unit 309, a first controlling unit 311, a first acquiring unit 313, and a first triggering unit 315. The device will now be described in detail.

[0118] The first determining unit 301 is used to analyze the positioning information after receiving the positioning information from the passenger device in order to determine whether the passenger is located within a predetermined range around the preset starting point, wherein the preset starting point is the boarding starting point set by the passenger device.

[0119] The first detection unit 303 is used to detect the characteristic information of pedestrians on the road where the autonomous taxi is currently located by using the sensor equipment of the autonomous taxi when it is determined that the passenger is within a predetermined range.

[0120] The first analysis unit 305 is used to analyze the feature information and obtain the analysis results.

[0121] The first identification unit 307 is used to identify the current location information of the passenger corresponding to the vehicle-blocking behavior when the analysis result indicates that the vehicle-blocking behavior has been detected and the duration of the vehicle-blocking behavior exceeds a preset duration.

[0122] The second determining unit 309 is used to determine the stopping position of the autonomous taxi based on the longitudinal coordinates corresponding to the current location information.

[0123] The first control unit 311 is used to control the autonomous taxi to stop according to the route corresponding to the stop location, so that the right rear door of the autonomous vehicle is aligned with the current location information.

[0124] The first acquisition unit 313 is used to acquire unlocking information initiated by the passenger device after the right rear door is aligned with the current position information.

[0125] The first triggering unit 315 is used to trigger the right rear door of the autonomous taxi to open after the unlocking information is verified, so that passengers can get in.

[0126] It should be noted that the first determining unit 301, the first detecting unit 303, the first analyzing unit 305, the first identifying unit 307, the second determining unit 309, the first controlling unit 311, the first acquiring unit 313, and the first triggering unit 315 mentioned above correspond to steps S202 to S216 in the above embodiments. The eight units and the corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments.

[0127] As can be seen from the above, in the solution described in the above embodiments of the present invention, the first determining unit can analyze the positioning information after receiving the positioning information from the passenger device to determine whether the passenger is located within a predetermined range around a preset starting point, wherein the preset starting point is the boarding starting point set by the passenger device; when the first detection unit determines that the passenger is within the predetermined range, it detects the feature information of pedestrians on the current road through the sensor device of the autonomous taxi; the first analysis unit analyzes the feature information to obtain the analysis result; when the analysis result indicates that a car-hailing behavior has been detected and the duration of the car-hailing behavior exceeds a preset duration, the first identification unit identifies the current location information of the passenger corresponding to the car-hailing behavior; the second determining unit determines the stopping position of the autonomous taxi according to the longitudinal coordinates corresponding to the current location information; the first control unit controls the autonomous taxi to stop according to the route corresponding to the stopping position so that the right rear door of the autonomous vehicle is aligned with the current location information; the first acquisition unit acquires the unlocking information initiated by the passenger device after the right rear door is aligned with the current location information; and the first triggering unit triggers the right rear door of the autonomous taxi to open after the unlocking information is verified to allow the passenger to board. The above solution allows passengers to hail autonomous taxis from non-pre-designated locations or in inclement weather conditions. The vehicles can dynamically adjust their stopping positions based on passenger needs, eliminating the need to strictly adhere to fixed stops. This reduces waiting and walking time for passengers in inclement weather or at non-designated locations, significantly improving passenger convenience and the overall riding experience. It achieves the technical benefits of increased dynamic stopping flexibility, improved passenger recognition accuracy, enhanced order processing flexibility and security, and improved riding convenience in inclement weather conditions. Furthermore, it solves the technical problem in related technologies where driverless taxis lack flexibility in stopping, limiting them to pre-designated stops and forcing passengers to walk to designated stops, thus impacting the riding experience.

[0128] Optionally, the first determining unit includes: a first analysis module, used to analyze the positioning information to obtain the current distance between the passenger device and the preset starting point, and to determine that the passenger is within a predetermined range when the current distance is continuously less than the preset distance within a predetermined time window; and a first determining module, used to determine that the passenger is within a predetermined range when receiving a first prompt message from the passenger device indicating arrival at the preset starting point.

[0129] Optionally, the first detection unit includes: a first detection module, used to detect passenger hailing actions in a preset area on the right side of the autonomous taxi using a vision device to obtain a pedestrian image in the preset area on the right side, and to extract features from the pedestrian image to obtain the pedestrian's limb movements, wherein the limb movements include at least: arm and hand movements and head gaze direction; a second detection module, used to detect pedestrian point cloud data using a lidar device; and a first fusion module, used to fuse the limb movements with the point cloud data to obtain feature information.

[0130] Optionally, the first analysis unit includes a second analysis module, used to analyze the feature information to obtain the pedestrian's actions and the duration of the actions, and to obtain the analysis results.

[0131] Optionally, the boarding processing device further includes: a first prompting module, used to generate a second prompting message when the analysis result indicates that a vehicle-blocking behavior has been detected and the duration of the vehicle-blocking behavior exceeds a first preset duration, so as to prompt the passenger that the vehicle-blocking behavior has taken effect.

[0132] Optionally, the boarding processing device further includes: a first stop module, used to stop stopping along the route corresponding to the stop location when, during the process of controlling the autonomous taxi to stop according to the route corresponding to the stop location, it is detected that the total duration of the passenger continuously moving away from the autonomous taxi is greater than or equal to a second preset duration; or, when it is detected that the identifier displayed in the display component of the autonomous taxi disappears, the identifier is an identifier assigned by the autonomous taxi to the identified passenger, and the identifier is used to track the passenger's behavior and location.

[0133] Optionally, the vehicle loading processing device further includes: a first adjustment module, used to continue stopping towards a preset starting point after stopping along the route corresponding to the stopping position.

[0134] Optionally, the boarding processing device further includes: a first control module, used to acquire the signal strength of the Bluetooth signal of the passenger device at a predetermined period during the process of controlling the autonomous taxi to stop according to the route corresponding to the stop location; and to continue controlling the autonomous taxi to stop according to the route corresponding to the stop location when it is determined that the signal strength increases sequentially according to the acquisition order; and a second stop module, used to stop stopping according to the route corresponding to the stop location and continue stopping towards the preset starting point when it is determined that the signal strength decreases sequentially according to the acquisition order within a predetermined time period.

[0135] Optionally, any one of the above modules includes: a first alignment module, used to generate a temporary state during the process of controlling the autonomous taxi to stop according to the route corresponding to the stop location so that the right rear door of the autonomous vehicle is aligned with the current location information; a first switching module, used to switch the order processing flow of the autonomous taxi to the temporary state; and a second switching module, used to switch from the temporary state to the state of arriving at the preset starting point after determining that the right rear door is open.

[0136] According to one aspect of the present invention, an autonomous taxi is provided, wherein the autonomous taxi uses any of the above-described methods for handling the boarding of an autonomous taxi.

[0137] According to one aspect of the present invention, a processor is provided for running a program, wherein the program executes the boarding processing method for an autonomous taxi as described above.

[0138] According to one aspect of the present invention, a computer program product is provided, including computer instructions, which, when executed by a processor, perform a method for handling the boarding of an autonomous taxi as described above.

[0139] According to one aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium including a stored program, wherein the program, when executed by a processor, performs the boarding processing method for an autonomous taxi as described above.

[0140] Optionally, in this embodiment, the computer-readable storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any communication device in a group of communication devices.

[0141] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: after receiving location information from the passenger device, analyzing the location information to determine whether the passenger is located within a predetermined range around a preset starting point, wherein the preset starting point is the boarding starting point set by the passenger device; when it is determined that the passenger is within the predetermined range, detecting the feature information of pedestrians on the current road using the sensor device of the autonomous taxi; analyzing the feature information to obtain analysis results; when the analysis results indicate that a hailing behavior has been detected and the duration of the hailing behavior exceeds a preset duration, identifying the current location information of the passenger corresponding to the hailing behavior; determining the stopping position of the autonomous taxi based on the longitudinal coordinates corresponding to the current location information; controlling the autonomous taxi to stop according to the route corresponding to the stopping position, so that the right rear door of the autonomous vehicle is aligned with the current location information; after the right rear door is aligned with the current location information, obtaining unlocking information initiated by the passenger device; after the unlocking information is verified, triggering the opening of the right rear door of the autonomous taxi to allow the passenger to board.

[0142] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: analyzing the location information to obtain the current distance between the passenger device and the preset starting point; determining that the passenger is within a predetermined range when the current distance is continuously less than the preset distance within a predetermined time window; and determining that the passenger is within the predetermined range when a first prompt message indicating arrival at the preset starting point is received from the passenger device.

[0143] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: a vision device and a lidar device, detecting the feature information of pedestrians on the current road through the sensor devices of the autonomous taxi, including: detecting passenger hailing actions in a preset area on the right side of the autonomous taxi using the vision device to obtain a pedestrian image in the preset area on the right side, and extracting features from the pedestrian image to obtain the pedestrian's limb movements, wherein the limb movements include at least: arm and hand movements, and head gaze direction; detecting point cloud data of the pedestrian using the lidar device; and fusing the limb movements with the point cloud data to obtain feature information.

[0144] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: analyzing feature information to obtain the pedestrian's actions and the duration of the actions, and obtaining analysis results.

[0145] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: when the analysis result indicates that a vehicle-blocking behavior has been detected and the duration of the vehicle-blocking behavior exceeds a first preset duration, a second prompt message is generated to prompt the passenger that the vehicle-blocking behavior has taken effect.

[0146] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: during the process of controlling the autonomous taxi to stop according to the route corresponding to the stop location, if it is detected that the total duration of the passenger continuously moving away from the autonomous taxi is greater than or equal to a second preset duration; or, when it is detected that the identifier displayed in the display component of the autonomous taxi disappears, stopping according to the route corresponding to the stop location is stopped, wherein the identifier is an identifier assigned by the autonomous taxi to the identified passenger, and the identifier is used to track the passenger's behavior and location.

[0147] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: after stopping along the route corresponding to the stopping position, continue to stop towards the preset starting point.

[0148] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: during the process of controlling the autonomous taxi to stop according to the route corresponding to the stop location, the signal strength of the Bluetooth signal of the passenger device is acquired at a predetermined period; when it is determined that the signal strength increases sequentially according to the acquisition order, the autonomous taxi continues to be controlled to stop according to the route corresponding to the stop location; when it is determined that the signal strength decreases sequentially according to the acquisition order within a predetermined time period, the taxi stops stopping according to the route corresponding to the stop location and continues to stop at the preset starting point.

[0149] Optionally, in this embodiment, the computer-readable storage medium is configured to store program code for performing the following steps: generating a temporary state while controlling the autonomous taxi to stop according to the route corresponding to the stop location so that the right rear door of the autonomous vehicle is aligned with the current location information; switching the order processing flow of the autonomous taxi to the temporary state; and switching from the temporary state to the state of arriving at the preset starting point after determining that the right rear door is open.

[0150] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0151] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some interfaces; indirect couplings or communication connections between units or modules may be electrical or other forms.

[0152] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0153] The units described as separate components may or may not be physically separate. Similarly, the components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0154] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0155] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0156] The above are merely preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for handling the boarding of an autonomous taxi, characterized in that, include: After receiving location information from the passenger device, the location information is analyzed to determine whether the passenger is located within a predetermined range around a preset starting point, wherein the preset starting point is the boarding starting point set by the passenger device. When it is determined that the passenger is within the predetermined range, the sensor equipment of the autonomous taxi detects the characteristic information of pedestrians on the current road. The feature information is analyzed to obtain the analysis results; When the analysis results indicate that a vehicle-stopping behavior has been detected and the duration of the vehicle-stopping behavior exceeds a preset duration, the current location information of the passenger corresponding to the vehicle-stopping behavior is identified; The stopping position of the autonomous taxi is determined based on the vertical coordinates corresponding to the current location information; Control the autonomous taxi to stop according to the route corresponding to the stop location, so that the right rear door of the autonomous taxi is aligned with the current location information; After the right rear door is aligned with the current position information, the unlocking information initiated by the passenger device is obtained; After the unlocking information is verified, the right rear door of the autonomous taxi is opened to allow the passenger to board.

2. The method for handling the boarding of an autonomous taxi according to claim 1, characterized in that, Determining that the passenger is within the predetermined range includes: The location information is analyzed to obtain the current distance between the passenger device and the preset starting point. When the current distance is continuously less than the preset distance within a predetermined time window, it is determined that the passenger is located within the predetermined range. Upon receiving a first notification message from the passenger device indicating arrival at the preset starting point, it is determined that the passenger is located within the predetermined range.

3. The method for handling the boarding of an autonomous taxi according to claim 1, characterized in that, The sensor equipment includes: vision equipment and lidar equipment. The sensor equipment of the autonomous taxi detects the characteristic information of pedestrians on the current road, including: The vision device detects passenger hailing actions in a preset area on the right side of the autonomous taxi to obtain pedestrian images in the preset area on the right side. Features are extracted from the pedestrian images to obtain the pedestrian's body movements, wherein the body movements include at least: arm and hand movements and head gaze direction. The point cloud data of the pedestrian is detected by the lidar device; The feature information is obtained by fusing the limb movements with the point cloud data.

4. The method for handling the boarding of an autonomous taxi according to claim 1, characterized in that, The feature information is analyzed to obtain the analysis results, including: The feature information is analyzed to obtain the pedestrian's actions and the duration of the actions, and the analysis results are obtained.

5. The method for handling the boarding of an autonomous taxi according to claim 1, characterized in that, The boarding process also includes: When the analysis results indicate that a vehicle-blocking behavior has been detected and the duration of the vehicle-blocking behavior exceeds a first preset duration, a second prompt message is generated to indicate that the vehicle-blocking behavior has taken effect.

6. The method for handling the boarding of an autonomous taxi according to claim 1, characterized in that, The boarding process also includes: During the process of controlling the autonomous taxi to stop according to the route corresponding to the stop location, if it is detected that the total time the passenger continuously moves away from the autonomous taxi is greater than or equal to a second preset time; or, if it is detected that the identifier displayed in the display component of the autonomous taxi disappears, the stopping according to the route corresponding to the stop location shall be stopped, wherein the identifier is an identifier assigned by the autonomous taxi to the identified passenger, and the identifier is used to track the passenger's behavior and location.

7. The method for handling the boarding of an autonomous taxi according to claim 1, characterized in that, The boarding process also includes: After stopping along the route corresponding to the stop location, continue stopping towards the preset starting point.

8. The method for handling the boarding of an autonomous taxi according to claim 1, characterized in that, The boarding process also includes: During the process of controlling the autonomous taxi to stop according to the route corresponding to the stop location, the signal strength of the Bluetooth signal of the passenger device is acquired at a predetermined period. When it is determined that the signal strength increases sequentially according to the acquisition order, the autonomous taxi is controlled to continue to stop according to the route corresponding to the stop location. When it is determined that the signal strength decreases sequentially according to the collection order within a predetermined time period, the stopping at the route corresponding to the stopping position is stopped, and the stopping continues to the preset starting point.

9. The method for handling the boarding of an autonomous taxi according to any one of claims 1 to 8, characterized in that, The boarding process also includes: A temporary state is generated during the process of controlling the autonomous taxi to stop according to the route corresponding to the stop location so that the right rear door of the autonomous vehicle is aligned with the current location information; Switch the order processing flow of the autonomous taxi to the temporary state; After confirming that the right rear door is open, the system switches from the temporary state to arriving at the preset starting point.

10. A boarding processing device for an autonomous taxi, characterized in that, include: The first determining unit is configured to analyze the positioning information received from the passenger device after receiving the positioning information, in order to determine whether the passenger is located within a predetermined range around a preset starting point, wherein the preset starting point is the boarding starting point set by the passenger device. The first detection unit is used to detect the characteristic information of pedestrians on the road where the autonomous taxi is currently located by using the sensor equipment of the autonomous taxi when it is determined that the passenger is located within the predetermined range. The first analysis unit is used to analyze the feature information and obtain analysis results; The first identification unit is used to identify the current location information of the passenger corresponding to the vehicle-blocking behavior when the analysis result indicates that the vehicle-blocking behavior has been detected and the duration of the vehicle-blocking behavior exceeds a preset duration. The second determining unit is used to determine the stopping position of the autonomous taxi based on the longitudinal coordinates corresponding to the current location information; The first control unit is used to control the autonomous taxi to stop according to the route corresponding to the stop location, so that the right rear door of the autonomous taxi is aligned with the current location information; The first acquisition unit is used to acquire the unlocking information initiated by the passenger device after the right rear door is aligned with the current position information; The first triggering unit is used to trigger the right rear door of the autonomous taxi to open after the unlocking information is verified, so that the passenger can get in the car.

Images