A method for assisting autonomous driving to cross a slip lane based on a sense-through algorithm

Abstract

The application relates to a method for assisting automatic driving to cross a taxiway based on a sense-through calculation, and belongs to the technical field of intelligent driving. The method comprises the following steps: a roadside unit detects an airplane through a millimeter wave radar and a sense-through calculation integrated roadside device, and reports inspection information to a cloud platform; when the airplane is detected and identified, the detection information is conditioned into a standard message for broadcasting; after a vehicle-mounted unit receives the standard message, the vehicle-mounted unit combines self-positioning, sends a control instruction to an automatic driving control unit through a control algorithm, synchronously reports self-position information and the control instruction to the cloud platform, and the automatic driving control unit operates the vehicle to safely cross the taxiway according to the control instruction. The millimeter wave radar and the sense-through calculation integrated roadside device are used for continuously detecting both sides of the taxiway to be crossed, so that the safety risk of airplane and automobile collision is avoided.

Description

Technical Field

[0001] This invention relates to the field of intelligent driving technology, and in particular to a method for assisted autonomous driving to cross a taxiway based on sensor-based computing. Background Technology

[0002] As airport construction and autonomous driving in my country continue to reach new heights, the safe passage of autonomous vehicles across taxiways within airports has become an increasingly prominent challenge.

[0003] Currently, the traditional method for functional vehicles to cross taxiways at airports is to reach the intersection, stop, and observe. If there are no aircraft within the airport's designated area, they proceed; otherwise, they wait. For autonomous vehicles, due to the limitations of their sensors' horizontal and vertical sensing range, they cannot accurately identify aircraft, posing significant safety risks to both aircraft passage and autonomous vehicle crossings of taxiways. Summary of the Invention

[0004] To address the aforementioned technical problems, this invention provides a method for assisted autonomous driving to cross a taxiway based on sensor-based computing.

[0005] A method for assisted autonomous driving to cross a taxiway based on sensor-based computation includes:

[0006] Step 1: The roadside unit detects the aircraft using millimeter-wave radar and integrated sensing, communication, and computing roadside equipment, and reports the inspection information to the cloud platform;

[0007] Step 2: Upon detecting and identifying an aircraft, the detection information is formatted into a standard message and broadcast.

[0008] Step 3: After receiving the standard message, the onboard unit, based on its own positioning, sends control commands to the autonomous driving control unit through a control algorithm; simultaneously, it reports its own location information and control commands to the cloud platform; the control algorithm includes pre-entry decision-making and post-entry decision-making, wherein the pre-entry decision-making predicts the crossing point S using a conflict detection model. cross Whether the vehicle is covered by an aircraft restricted area; if covered, a stop command is generated; if not covered, a continue command is generated. The decision after entering the taxiway is to detect in real time whether the vehicle's position is within any aircraft restricted area after the vehicle has entered the taxiway. If covered, a stop command is generated; if not covered, a continue command is generated.

[0009] Step 4: The autonomous driving control unit operates the vehicle to safely cross the skid track according to the control instructions.

[0010] Furthermore, in step 1, the detection of whether an aircraft is on the runway using cameras and radar specifically involves: identifying the data collected by the cameras using an aircraft recognition model, and combining this with aircraft wave data collected by radar to improve recognition accuracy.

[0011] Furthermore, the millimeter-wave radar and the integrated sensing, communication, and computing roadside equipment are deployed at the intersection fence, consisting of two millimeter-wave radars, one integrated sensing, communication, and computing roadside equipment, a 6-meter-high pole, and a switch. The two millimeter-wave radars are positioned back-to-back, respectively detecting the left and right lanes of the crossing, while the integrated sensing, communication, and computing roadside equipment supplements the dark areas under the lights and performs redundant detection.

[0012] Furthermore, the aircraft restricted area is a dynamically moving safety protection space centered on the current position of the aircraft, with its boundary range being: [sp-Lrear*dir,sp+Lfront*dir], where sp is the real-time position of the aircraft, dir is the direction of the aircraft's movement (+1 for movement in the positive direction of the coordinate system, -1 for movement in the negative direction of the coordinate system), Lrear is the front of the aircraft as it taxis, and Lfront is the direction of the aircraft's tail.

[0013] Furthermore, the conflict detection model is specifically as follows:

[0014] Calculation of time window for crossing:

[0015] Among them, t start t is the time when the vehicle begins to cross the skid track. now Where is the current time, D is the distance from the vehicle to the entrance, and v is the distance from the vehicle to the entrance. v Let t be the vehicle's current speed. end The time it takes for a vehicle to complete crossing the taxiway, where W is the width of the taxiway, and v is the distance between the two sides. max Speed ​​limits are set for vehicle taxiways;

[0016] Aircraft position prediction function: sp(τ)=sp+v·dir·τ,τ≥0,where sp is the real-time position of the aircraft, v is the aircraft taxiing speed, dir is the direction of the aircraft's movement, and τ is the aircraft's time offset in seconds;

[0017] Restricted area coverage conditions:

[0018] When dir = +1: sp(τ) - Lrear ≤ S cross ≤sp(τ)+Lfront;

[0019] When dir = -1: sp(τ) - Lfront ≤ S cross ≤sp(τ)+Lrear;

[0020] Conflict determination: When τ_min, τ_max] ∩ [t_start, At that time, a conflict is determined, indicating that there is overwriting.

[0021] Furthermore, the decision-making process after entering the slide is specifically as follows:

[0022] Calculate the current restricted area for each aircraft:

[0023] Z = [min(s)] p -L rear ·dir,s p +L front ·dir), max(s) p -L rear ·dis,s p +L front ·dir)],

[0024] Where Z represents the restricted area, sp represents the aircraft's real-time position, dir represents the aircraft's direction of movement, Lrear represents the aircraft's taxiing front, and Lfront represents the direction of the aircraft's tail.

[0025] Collision detection: When the vehicle position s v When ∈Z, a conflict is determined, indicating that a cover exists.

[0026] Furthermore, the Lrear value of the aircraft restricted area is 50 meters, and the Lfront value is 200 meters.

[0027] Furthermore, it also includes a dynamic speed control mechanism for early warning, specifically, based on the aircraft's real-time position sp and the crossing point S. cross The range of differences corresponds to the vehicle's speed.

[0028] Furthermore, it also includes dynamically summarizing the aircraft's real-time latitude and longitude into warning zones based on the detection information reported by the roadside and the aircraft no-entry zones required by the conflict area, and redundantly sending them to the autopilot control unit.

[0029] The beneficial effects of this invention are as follows: This invention uses an integrated roadside device and millimeter-wave radar to continuously detect both sides of the taxiway to be traversed. If an aircraft is detected within the detection range, the information is transmitted to the autonomous vehicle via LTE-V, controlling the autonomous vehicle to stop and wait, thus avoiding the safety risk of a collision between the aircraft and the car. Attached Figure Description

[0030] Figure 1 This is a flowchart of the method of the present invention.

[0031] Figure 2 This is a system architecture diagram in the embodiment.

[0032] Figure 3 This is a diagram of the equipment installation.

[0033] Figure 4 This is a diagram of the model algorithm for detecting aircraft.

[0034] Figure 5This is an auxiliary decision-making map of the three-layer early warning area in the embodiment. Detailed Implementation

[0035] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. 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 are within the scope of protection of the present invention.

[0036] Example 1: Refer to Figure 1 This invention provides a method for assisted autonomous driving to cross a taxiway based on sensor-based computing, comprising:

[0037] Step 1: The roadside unit detects the aircraft using millimeter-wave radar and integrated sensing, communication, and computing roadside equipment, and reports the inspection information to the cloud platform;

[0038] Step 2: Upon detecting and identifying an aircraft, the detection information is formatted into a standard message and broadcast.

[0039] Step 3: After receiving the standard message, the onboard unit, based on its own positioning, sends control commands to the autonomous driving control unit through a control algorithm; simultaneously, it reports its own location information and control commands to the cloud platform; the control algorithm includes pre-entry decision-making and post-entry decision-making, wherein the pre-entry decision-making predicts the crossing point S using a conflict detection model. cross Whether the vehicle is covered by an aircraft restricted area; if covered, a stop command is generated; if not covered, a continue command is generated. The decision after entering the taxiway is to detect in real time whether the vehicle's position is within any aircraft restricted area after the vehicle has entered the taxiway. If covered, a stop command is generated; if not covered, a continue command is generated.

[0040] Step 4: The autonomous driving control unit operates the vehicle to safely cross the skid track according to the control instructions.

[0041] I. In this embodiment, the system architecture used in the method is as follows: Figure 2 As shown, the system includes a management platform, a roadside unit, and an onboard autonomous driving unit. The roadside unit detects the aircraft using millimeter-wave radar and integrated sensing, communication, and computing roadside equipment, reports the detection information to the cloud platform, and formats the detection information into standard RSI or RSM messages for broadcast. After receiving the broadcast roadside messages, the onboard unit combines its own positioning and uses control algorithms to give the autonomous driving control unit a stop or start command, while simultaneously reporting its own location information and control commands to the platform.

[0042] II. Equipment deployment, such as Figure 3As shown, a detection device is installed at the intersection fence, consisting of two millimeter-wave radars, one integrated sensing, communication, and computing roadside device, a 6-meter-high pole, and a switch. The two millimeter-wave radars are back-to-back, detecting the left and right taxiways of the crossing lanes respectively. The integrated sensing, communication, and computing roadside device supplements the "blind spots" and also performs redundant detection. The platform control unit also dynamically summarizes the detection information reported by the roadside and the aircraft no-entry zones required by the conflict area into a warning zone according to the real-time latitude and longitude of the aircraft.

[0043] Specifically, the detection of aircraft presence on the runway using cameras and radar involves: using data collected by cameras to identify aircraft through an aircraft recognition model, and combining this with aircraft wave data collected by radar to improve recognition accuracy. The specific process is as follows: Figure 4 As shown.

[0044] III. Sensing, Communication, and Radar Detection: The integrated roadside equipment combines cameras, V2X, and edge computing units into one device, overcoming the drawbacks of traditional split-type sensing systems, such as high cost, difficult operation and maintenance, and large latency. It enables ultra-low latency sensing, calculation, and transmission of abnormal targets, greatly improving drivers' confidence in abnormal situations on highways and ensuring detection reliability.

[0045] Millimeter-wave radar is suitable for aircraft detection at night and in harsh environments.

[0046] Neither of them has a model or algorithm for detecting aircraft, so both require data collection and processing to obtain a model and clustering algorithm for aircraft identification. The specific process is as follows: Figure 3 As shown.

[0047] IV. Vehicle Control Algorithm

[0048] 1) Establishing a coordinate system

[0049] Taxiway coordinate system: Establish a one-dimensional coordinate system S∈[0,200], where 0 and 200 represent the endpoints of the taxiway, respectively.

[0050] Aircraft status:

[0051] sp: Real-time location (longitude / latitude conversion value)

[0052] v: Gliding speed (m / s)

[0053] dir: Direction of movement (+1: S increases in direction; -1: S decreases in direction)

[0054] Vehicle status:

[0055] sv: Position in the taxiway coordinate system

[0056] vv: Speed ​​(m / s)

[0057] Definition of restricted area:

[0058] Lfront = 200m (in the direction of movement)

[0059] Lrear = 50m (rear direction of movement)

[0060] Restricted zone boundary: [sp-Lrear*dir,sp+Lfront*dir];

[0061] 2) Decisions made before entering the taxiway (when the vehicle is outside the taxiway)

[0062] Decision objective: Predict whether the crossing point Scross is covered by any aircraft's no-entry zone during the vehicle's crossing time period [tstart,tend].

[0063] Conflict detection model:

[0064] 1. Calculation of time window for travel:

[0065] Among them, t start t is the time when the vehicle begins to cross the skid track. now Where is the current time, D is the distance from the vehicle to the entrance, and v is the distance from the vehicle to the entrance. v Let t be the vehicle's current speed. end The time it takes for a vehicle to complete crossing the taxiway, where W is the width of the taxiway, and v is the distance between the two sides. max Speed ​​limits for vehicle coasting lanes (generally 30 km / h (8.33 m / s) can be set);

[0066] Aircraft position prediction function: sp(τ)=sp+v·dir·τ,τ≥0,where sp is the real-time position of the aircraft, v is the aircraft taxiing speed, dir is the direction of aircraft movement; and τ is the aircraft's time offset in seconds.

[0067] Restricted area coverage conditions:

[0068] When dir = +1: sp(τ) - Lrear ≤ S cross ≤sp(τ)+Lfront;

[0069] When dir = -1: sp(τ) - Lfront ≤ S cross ≤sp(τ)+Lrear;

[0070] Conflict determination: (Treat the aircraft as stationary when v≈0) When τ_min, τ_max]∩[t_start, At that time, a conflict is determined, indicating that there is overwriting.

[0071] Control output:

[0072] By transforming location conflicts into time window conflicts through spatiotemporal joint detection, the problem of dynamic target prediction is effectively solved. Coordinate system dimensionality reduction optimization: The one-dimensional linear coordinate system significantly reduces computational complexity (reducing computation by 87% compared to three-dimensional space).

[0073] Early warning dynamic speed adjustment mechanism: based on the aircraft's real-time position (sp) and the crossing point (S) cross The difference range corresponds to the vehicle speed. Preferably, in this embodiment, a three-layer warning zone is set to assist decision-making. Figure 4 As shown, it achieves triple protection: "pre-emptive access prediction → real-time blocking during the event → dynamic distance buffer".

[0074] 3) Decision-making while crossing the taxiway (within the taxiway)

[0075] Decision objective: To detect in real time whether the vehicle's current location (SV) is within the immediate restricted area of ​​any aircraft.

[0076] Real-time collision detection: Calculates the current restricted area for each aircraft.

[0077] Z = [min(s)] p -L rear ·dir,s p +Lx ront ·dir), max(s) p -L rear ·dir,s p +L front ·dir)],

[0078] Conflict condition: s v ∈Z,

[0079] Control output: (Keep v while moving) v ).

[0080] In the description of the embodiments of the present invention, it should be understood that the terms "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "center," "top," "bottom," "top," "bottom," "inner," "outer," "inner side," and "outer side," etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the accompanying drawings and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. "Inner side" refers to the interior or enclosed area or space. "Outer perimeter" refers to the area surrounding a specific component or specific area.

[0081] In the description of embodiments of the present invention, the terms "first," "second," "third," and "fourth" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first," "second," "third," or "fourth" may explicitly or implicitly include one or more of that feature. In the description of the present invention, unless otherwise stated, "a plurality of" means two or more.

[0082] In the description of embodiments of the present invention, specific features, structures, materials or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0083] In the description of embodiments of the present invention, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Additionally, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0084] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for assisted autonomous driving to cross a taxiway based on sensory communication, characterized in that, include Step 1: The roadside unit detects the aircraft using millimeter-wave radar and integrated sensing, communication, and computing roadside equipment, and reports the inspection information to the cloud platform; Step 2: Upon detecting and identifying an aircraft, the detection information is formatted into a standard message and broadcast. Step 3: After receiving the standard message, the onboard unit, based on its own positioning, sends control commands to the autonomous driving control unit through a control algorithm; simultaneously, it reports its own location information and control commands to the cloud platform; the control algorithm includes pre-entry decision-making and post-entry decision-making, wherein the pre-entry decision-making predicts the crossing point S using a conflict detection model. cross Whether the vehicle is covered by an aircraft restricted area; if covered, a stop command is generated; if not covered, a continue command is generated. The decision after entering the taxiway is to detect in real time whether the vehicle's position is within any aircraft restricted area after the vehicle has entered the taxiway. If covered, a stop command is generated; if not covered, a continue command is generated. The aircraft restricted area is a dynamically moving safety protection space centered on the current position of the aircraft, with its boundary range being: [sp−Lrear*dir, sp+Lfront*dir], where sp is the real-time position of the aircraft, dir is the direction of the aircraft's movement (+1 for movement in the positive direction of the coordinate system, and -1 for movement in the negative direction of the coordinate system), Lrear is the front of the aircraft as it taxis, and Lfront is the direction of the aircraft's tail. The decision-making process after entering the slide is as follows: Calculate the current restricted area for each aircraft: ， Where Z represents the restricted area, sp represents the aircraft's real-time position, dir represents the aircraft's direction of movement, Lrear represents the aircraft's taxiing front, and Lfront represents the direction of the aircraft's tail. Collision detection: When the vehicle position s v When ∈Z, a conflict is determined, indicating that a cover exists; The specific conflict detection model is as follows: Time window calculation: , Among them, t start t is the time when the vehicle begins to cross the skid track. now Where is the current time, D is the distance from the vehicle to the entrance, and v is the distance from the vehicle to the entrance. v Let t be the vehicle's current speed. end The time it takes for a vehicle to complete crossing the taxiway, where W is the width of the taxiway, and v is the distance between the two sides. max Speed ​​limits are set for vehicle taxiways; Aircraft position prediction function: sp(τ)=sp+v·dir·τ,τ≥0,where sp is the real-time position of the aircraft, v is the aircraft taxiing speed, dir is the direction of the aircraft's movement, and τ is the aircraft's time offset. Restricted area coverage conditions: When dir=+1: sp(τ)-Lrear ≤ S cross ≤ sp(τ)+Lfront; When dir=-1: sp(τ)-Lfront ≤ S cross ≤ sp(τ)+Lrear; Conflict determination: When [τ_min, τ_max] ∩ [t_start, t_end] ≠ ∅, a conflict is determined, indicating that there is overwriting. Step 4: The autonomous driving control unit operates the vehicle to safely cross the skid track according to the control instructions.

2. The method for assisted autonomous driving crossing a taxiway based on inductive computing according to claim 1, characterized in that, In step 1, the detection of whether an aircraft is on the runway using cameras and radar specifically involves: identifying the aircraft using the data collected by the cameras through an aircraft identification model, and combining this with the aircraft wave data collected by the radar to improve the identification accuracy.

3. The method for assisted autonomous driving crossing a taxiway based on inductive computing according to claim 1, characterized in that, The millimeter-wave radar and the integrated sensing, communication, and computing roadside equipment are deployed at the intersection fence. It consists of two millimeter-wave radars, one integrated sensing, communication, and computing roadside equipment, a 6-meter-high pole, and a switch. The two millimeter-wave radars are back to back, respectively detecting the left and right lanes of the crossing. The integrated sensing, communication, and computing roadside equipment supplements the dark areas under the lights and performs redundant detection.

4. The method for assisted autonomous driving crossing a taxiway based on inductive computing according to claim 1, characterized in that, The Lrear value for the no-entry zone is 50 meters, and the Lfront value is 200 meters.

5. The method for assisted autonomous driving crossing a taxiway based on inductive computing according to claim 1, characterized in that, It also includes a warning dynamic speed adjustment mechanism, specifically, based on the aircraft's real-time position sp and the crossing point S. cross The range of differences corresponds to the vehicle's speed.

6. The method for assisted autonomous driving crossing a taxiway based on inductive computing according to claim 1, characterized in that, It also includes dynamically summarizing the no-entry zones for aircraft based on the detection information reported by the roadside and the requirements of conflict areas, and redundantly sending them to the autonomous driving control unit.

Images