Method and system for intelligent driving perception based on LoRa communication

Abstract

The invention provides an intelligent driving perception method and system based on LoRa communication, and the method comprises the steps: calculating the cooperative perception radius of a vehicle based on the motion state of the vehicle and a road environment; according to the cooperative sensing radius, the LoRa broadcast communication distance is adjusted, and when the motion state of the vehicle is angular velocity increase and / or the road environment is a mountain road area, the LoRa transmitting power level is automatically compensated to enlarge the LoRa broadcast communication distance; within the coverage distance of the LoRa broadcast communication, receiving a first message package of other vehicles; and on the basis of the first message packaging packet, predicting future driving behaviors of the other vehicles and generating a corresponding driving control strategy of the vehicle. According to the technical scheme of the invention, low-cost, low-power-consumption, wide-coverage and high-interference-resistance communication and cooperative sensing can be realized, the sensing blind area of a vehicle-mounted sensor is compensated, and the overall understanding and intelligent driving capability of a dynamic traffic environment is improved.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and more specifically to a method and system for intelligent driving perception based on LoRa communication. Background Technology

[0002] In traditional intelligent driving systems, vehicles mainly rely on onboard sensors (such as cameras, millimeter-wave radar, lidar, ultrasonic sensors, etc.) to autonomously perceive the surrounding environment and build a local environment model through the fusion of multi-source sensor data, thereby supporting key functions such as path planning, behavior decision-making and vehicle control.

[0003] However, this intelligent model has several inherent limitations that severely restrict the reliability and safety of intelligent driving systems in complex and dynamic traffic scenarios: Onboard sensors are generally limited by physical line of sight and detection range. In high-density urban traffic environments, the perception capabilities of a single vehicle cannot cover the overall traffic situation. Especially in scenarios such as cooperative driving, platooning, or emergency obstacle avoidance, the lack of real-time information interaction with other vehicles (V2V), infrastructure (V2I), and even pedestrians (V2P) leads to prominent perception island problems. This not only reduces overall traffic efficiency but also increases potential safety risks.

[0004] Furthermore, as intelligent driving levels evolve towards L4 / L5, the system places higher demands on the integrity, continuity, and robustness of environmental perception. Relying solely on single-vehicle perception is insufficient to meet the safety redundancy requirements across all scenarios, weather conditions, and operating conditions.

[0005] Therefore, a technical solution is needed that can achieve low-cost, low-power, wide-coverage, and interference-resistant communication and collaborative perception, make up for the perception blind spots of vehicle sensors, and improve the overall understanding of the dynamic traffic environment and intelligent driving capabilities. Summary of the Invention

[0006] This invention aims to provide a method and system for intelligent driving perception based on LoRa communication, which can achieve low-cost, low-power, wide-coverage and strong anti-interference communication and collaborative perception, make up for the perception blind spots of vehicle sensors, and improve the overall understanding of the dynamic traffic environment for intelligent driving.

[0007] According to one aspect of the present invention, a method for intelligent driving perception based on LoRa communication is provided, the method comprising: Based on the vehicle's motion state and the road environment, calculate the vehicle's cooperative perception radius; Based on the cooperative sensing radius, the LoRa broadcast communication distance is adjusted, wherein when the vehicle's motion state is characterized by an increase in angular velocity and / or the road environment is a mountainous area, the LoRa transmission power level is automatically compensated to extend the LoRa broadcast communication distance; Within the LoRa broadcast communication coverage distance, receive the first message packet from other vehicles; Based on the first message encapsulation packet, predict the future driving behavior of the other vehicles and generate a corresponding driving control strategy for this vehicle.

[0008] According to some embodiments, based on the vehicle's motion state and the road environment, the cooperative perception radius of the vehicle is calculated, including: The safe visibility distance is calculated based on the vehicle's current speed using the following formula: , in, The safe field of view distance, This is the current speed of the vehicle. For the braking response delay of this vehicle, This is the braking distance of this vehicle.

[0009] According to some embodiments, the calculation of the vehicle's cooperative perception radius based on the vehicle's motion state and road environment also includes: The cooperative perception radius is calculated based on the safe field of view distance and the vehicle response delay, using the following formula: , in, Let be the radius of the collaborative sensing. This is the current speed of the vehicle. This is the total system response delay for this vehicle. The safe field of view distance is defined as such.

[0010] According to some embodiments, adjusting the LoRa broadcast communication distance based on the cooperative sensing radius further includes: When the vehicle's motion state is characterized by increased angular velocity and / or the road environment is a mountainous area, the signal bandwidth is reduced.

[0011] According to some embodiments, adjusting the LoRa broadcast communication distance based on the cooperative sensing radius further includes: When the vehicle's motion state is characterized by an increase in angular velocity and / or the road environment is a mountainous area, the LoRa spreading factor is adjusted by setting the LoRa data transmission rate level.

[0012] According to some embodiments, the root mean square value, peak count, and standard deviation of the vehicle's angular velocity within a preset time window are calculated. If any of the calculated values ​​of the root mean square value, peak count, and standard deviation is higher than the flat road threshold, it is determined that the vehicle is in a mountain road area.

[0013] According to some embodiments, before obtaining the first message package, the vehicle's position, speed, and heading angle are obtained via GPS and / or IMU, and encapsulated into a second message package, which is then continuously broadcast via LoRa.

[0014] According to some embodiments, based on the first message encapsulation packet, the future driving behavior of the other vehicles is predicted and a corresponding driving control strategy for the current vehicle is generated, including: The positions and speeds of the other vehicles in the first message encapsulation packet are converted to the coordinate system of this vehicle to construct a cooperative perception target; Based on the position, speed, heading angle, and turn signal status of the target sensed collaboratively, control commands are generated to decelerate, stop, or maintain the current speed.

[0015] According to another aspect of the present invention, a system for intelligent driving perception based on LoRa communication is provided, the system comprising: The calculation module is used to calculate the vehicle's cooperative perception radius based on the vehicle's motion state and the road environment; The communication setting module is used to adjust the LoRa broadcast communication distance according to the cooperative sensing radius. When the vehicle's motion state is characterized by an increase in angular velocity and / or the road environment is a mountainous area, the LoRa transmission power level is automatically compensated to extend the LoRa broadcast communication distance. The message receiving module is used to receive the first message packet from other vehicles within the LoRa broadcast communication coverage distance; The behavior prediction module is used to predict the future driving behavior of the other vehicles and generate a corresponding driving control strategy for the vehicle based on the first message encapsulation packet.

[0016] According to another aspect of the present invention, a computing device is provided, comprising: Processor; and A memory that stores a computer program, which, when executed by the processor, implements the method as described in any of the preceding methods.

[0017] According to an embodiment of the present invention, based on the vehicle's motion state and road environment, the cooperative sensing radius of the vehicle is calculated, and the LoRa broadcast communication distance is adjusted according to the cooperative sensing radius. Specifically, when the vehicle's motion state involves an increase in angular velocity and / or the road environment is a mountainous area, the LoRa transmit power level is automatically compensated to extend the LoRa broadcast communication distance. Within the LoRa broadcast communication coverage distance, first message packets from other vehicles are received, the future driving behavior of other vehicles is predicted, and a corresponding driving control strategy for the vehicle is generated. This invention enables low-cost, low-power, wide-coverage, and highly interference-resistant communication and cooperative sensing, compensating for the perception blind spots of onboard sensors and improving the overall understanding of the dynamic traffic environment for intelligent driving.

[0018] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit the invention. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below.

[0020] Figure 1 A flowchart illustrating a method for intelligent driving perception based on LoRa communication according to an example embodiment is shown.

[0021] Figure 2 A schematic diagram illustrating the setting of LoRa transmit power levels according to an example embodiment is shown.

[0022] Figure 3 A schematic diagram illustrating the setting of LoRa data transmission rate levels according to an example embodiment is shown.

[0023] Figure 4 A schematic diagram of a LoRa-based perception system for intelligent driving, according to an example embodiment, is shown.

[0024] Figure 5 A block diagram of a computing device according to an exemplary embodiment is shown. Detailed Implementation

[0025] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the embodiments set forth herein; rather, they are provided so that the invention will be thorough and complete, and the concept of the exemplary embodiments will be fully conveyed to those skilled in the art. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted.

[0026] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a full understanding of embodiments of the invention. However, those skilled in the art will recognize that the technical solutions of the invention can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of the invention.

[0027] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0028] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0029] It should be understood that although the terms first, second, third, etc., may be used herein to describe various components, these components should not be limited by these terms. These terms are used to distinguish one component from another. Therefore, the first component discussed below may be referred to as the second component without departing from the teachings of the present invention. As used herein, the term "and / or" includes all combinations of any one and more of the associated listed items.

[0030] Those skilled in the art will understand that the accompanying drawings are merely schematic diagrams of exemplary embodiments, and the modules or processes in the drawings are not necessarily essential for implementing the present invention, and therefore cannot be used to limit the scope of protection of the present invention.

[0031] In traditional intelligent driving systems, vehicles primarily rely on onboard sensors (such as cameras, millimeter-wave radar, lidar, and ultrasonic sensors) to autonomously perceive their surroundings and construct local environmental models through the fusion of multi-source sensor data. This supports key functions such as path planning, behavioral decision-making, and vehicle control. However, this "single-vehicle intelligence" model has several inherent limitations, severely restricting the reliability and safety of intelligent driving systems in complex and dynamic traffic scenarios.

[0032] First, vehicle-mounted sensors are generally limited by physical line-of-sight and detection range. For example, cameras are susceptible to strong light, backlight, low-light conditions at night, or severe weather (such as rain, snow, fog, and dust storms), leading to decreased image quality or even failure. While millimeter-wave radar has a certain penetration capability, it is prone to false alarms or missed detections in high-density target scenarios. Although lidar has high accuracy, its performance degrades significantly under conditions such as rain, snow, and dense fog, and it is also expensive. Ultrasonic sensors are only suitable for specific scenarios such as close-range parking. These limitations make it difficult for vehicles to effectively perceive areas where their line of sight is obstructed (such as behind large vehicles, road curves, blind spots at intersections, etc.), and also prevent them from anticipating sudden traffic events such as traffic accidents, construction areas, or abnormal parking at a distance (such as hundreds of meters away).

[0033] Secondly, in high-density urban traffic environments, the perception capabilities of a single vehicle cannot cover the overall traffic situation. Especially in scenarios such as cooperative driving, platooning, or emergency obstacle avoidance, the lack of real-time information interaction with other vehicles (V2V), infrastructure (V2I), and even pedestrians (V2P) leads to prominent perception silos. This not only reduces overall traffic efficiency but also increases potential safety risks.

[0034] Furthermore, as intelligent driving levels evolve towards L4 / L5, the system places higher demands on the integrity, continuity, and robustness of environmental perception. Relying solely on single-vehicle perception is insufficient to meet the safety redundancy requirements across all scenarios, weather conditions, and operating conditions.

[0035] Therefore, breaking through the perception boundaries of single-vehicle intelligence has become a critical technical problem that urgently needs to be solved. LoRa, as a wireless communication technology with long-distance transmission, low power consumption, strong penetration capabilities, and good anti-interference characteristics, provides a new technical path for achieving low-cost, high-reliability vehicle cooperative perception. However, effectively integrating LoRa communication into the intelligent driving perception system, overcoming challenges such as bandwidth limitations, uncertain latency, and insufficient positioning accuracy, and designing information fusion and semantic understanding mechanisms adapted to dynamic traffic scenarios still face many theoretical and engineering challenges.

[0036] To this end, this invention proposes a method for intelligent driving perception based on LoRa communication, which can achieve low-cost, low-power, wide-coverage and strong anti-interference communication and collaborative perception, make up for the perception blind spots of vehicle sensors, and improve the overall understanding of the dynamic traffic environment for intelligent driving.

[0037] The following description, in conjunction with the accompanying drawings, illustrates exemplary embodiments of the present invention.

[0038] Figure 1 A flowchart illustrating a method for intelligent driving perception based on LoRa communication according to an example embodiment is shown.

[0039] See Figure 1 In S101, the cooperative perception radius of the vehicle is calculated based on the vehicle's motion state and the road environment.

[0040] According to some embodiments, the safe visibility distance is calculated based on the vehicle's current speed, using the following formula: , in, The safe field of view distance, This is the current speed of the vehicle. For the braking response delay of this vehicle, This is the braking distance of this vehicle.

[0041] Then, the cooperative perception radius is calculated based on the safe field of view distance and the vehicle response delay, using the following formula: , in, Let be the radius of the collaborative sensing. This is the current speed of the vehicle. This is the total system response delay for this vehicle. The safe field of view distance is defined as such.

[0042] In S103, the LoRa broadcast communication distance is adjusted according to the cooperative sensing radius.

[0043] According to some embodiments, LoRa transmission over long distances can lead to information overload, and long-distance signals may cause interference, affecting the core communication quality. Therefore, this invention solves the information overload problem and improves communication quality by dynamically controlling the broadcast distance of LoRa.

[0044] According to some embodiments, the LoRa broadcast communication distance is adjusted by setting LoRa transmit power levels. A higher LoRa transmit power level results in a shorter LoRa broadcast communication distance, which does not exceed a broadcast communication distance threshold. The LoRa transmit power levels include first-level, second-level, third-level, fourth-level, fifth-level, sixth-level, seventh-level, and eighth-level transmit power. The broadcast communication distance threshold is set to 1000 meters.

[0045] According to some embodiments, setting the transmit power level can directly reduce the output power of the RF front-end, thereby narrowing the effective communication range. This method is simple to operate, adjustable in real time, and suitable for scenarios requiring dynamic adjustment of communication distance. LoRa transmit power levels are typically set to 0-7 (see...). Figure 2 For a comparison of the power levels and output power corresponding to the 470MHz band, please refer to Table 1.

[0046] Table 1

[0047] According to some embodiments, adjusting the LoRa broadcast communication distance by setting the LoRa transmit power level is simple, requiring only the addition of a power level setting to the device firmware. The power level can be dynamically adjusted based on environmental requirements during device initialization or communication, avoiding unnecessary signal coverage and reducing overall power consumption. For example, a higher power level can be set for mountain roads, covering 500-1000 meters; a medium power level for urban roads, covering 200-300 meters; and a very low power level for parking lots, covering 50 meters.

[0048] According to some embodiments, the LoRa spreading factor is adjusted by setting the LoRa data transmission rate level to ensure the anti-interference capability of the LoRa broadcast communication distance. The higher the LoRa data transmission rate level, the smaller the LoRa spreading factor.

[0049] According to some embodiments, when the vehicle's motion state is characterized by an increased angular velocity and / or the road environment is a mountainous area, the signal bandwidth is reduced.

[0050] Bandwidth is the third most crucial and configurable radio frequency parameter in LoRa, after transmit power and spreading factor. It, along with the LoRa spreading factor (SF) and code rate, determines the actual data transmission rate. Common LoRa bandwidth settings are 125kHz, 250kHz, and 500kHz. A larger bandwidth results in a faster data rate and reduces transmission time.

[0051] According to some implementations, with the same SF (First Format), doubling the bandwidth almost doubles the data rate, and halving the airtime for transmitting the same data packets. Conversely, with the same bandwidth, increasing the SF by one level significantly reduces the data rate and greatly increases the transmission time.

[0052] According to some embodiments, when the vehicle's motion state is characterized by an increased angular velocity and / or the road environment is a mountainous area, the LoRa spreading factor is adjusted by setting the LoRa data transmission rate level.

[0053] According to some implementations, the LoRa spreading factor (SF) is positively correlated with communication distance and interference immunity, and negatively correlated with data transmission rate. Reducing the SF can significantly improve the rate, but it will weaken the receiver sensitivity and propagation distance. When the LoRa data transmission rate level (DR) is set to 5, corresponding to SF=7 and bandwidth=125kHz, this represents the highest rate configuration with the same bandwidth, but also the shortest communication distance (see [link]). Figure 3 The relationship between data rate and spreading factor is shown in Table 2.

[0054] Table 2

[0055] According to some implementations, it is recommended to use SF=7 in close-range scenarios with minimal interference, and to use mechanisms such as forward error correction (FEC) to ensure data integrity. It is important to note that Adaptive Data Rate (ADR) must be disabled when modifying the DR value; otherwise, ADR will adaptively adjust the DR.

[0056] According to some embodiments, the method of the present invention actively introduces attenuation to achieve controllable signal energy loss. It is connected in series in the RF link. Type-T or T-type resistor attenuators can achieve controllable signal energy loss. The method of this invention is based on mature passive network theory and possesses good broadband characteristics and impedance matching. It has the ability to maintain a stable attenuation value, unaffected by frequency drift. See Table 3 for standard resistor attenuation network parameters.

[0057] Table 3

[0058] According to some embodiments, the distance to the transmitting source is estimated based on the Received Signal Strength Indicator (RSSI) value. If the distance to the transmitting source exceeds the LoRa broadcast communication distance threshold, the corresponding message is discarded.

[0059] In some implementations, dual distance verification is achieved by combining RSSI and timestamps, setting a distance threshold (e.g., 500m), and automatically discarding signals beyond the range. Signals at close range (e.g., within 300m) are assigned a higher processing priority.

[0060] According to some embodiments, the farthest distance of the other vehicle within the LoRa broadcast communication range is calculated in real time, and the LoRa transmit power level is adjusted to just cover the sum of the farthest distance and the safety margin. For example, a vehicle obtains its precise latitude and longitude using GPS / BeiDou, receives BSM messages broadcast by surrounding vehicles containing their locations, calculates the farthest relevant distance, finds the distance D_max of the farthest relevant vehicle within the communication range, and then dynamically adjusts the power to just cover "D_max + safety margin (e.g., 50 meters)". This process is repeated continuously as the vehicle moves. This adaptively maintains the communication range at the minimum necessary level, efficiently utilizing the spectrum.

[0061] According to some embodiments, when the vehicle's motion state is characterized by an increased angular velocity and / or the road environment is a mountainous area, the LoRa transmission power level is automatically compensated to extend the LoRa broadcast communication distance.

[0062] According to some implementation methods, mountain roads typically feature frequent changes in direction (continuous curves), large changes in turning radius, and undulating slopes, requiring vehicles to turn frequently. Therefore, changes in the vehicle's angular velocity are used to determine whether the vehicle is in a mountainous area.

[0063] According to some embodiments, the root mean square value, peak count, and standard deviation of the vehicle's angular velocity within a preset time window are calculated. If any of the calculated values ​​of the root mean square value, peak count, and standard deviation is higher than the flat road threshold, it is determined that the vehicle is in a mountain road area.

[0064] According to some embodiments, based on the vehicle's GPS trajectory curvature and accelerometer data, high-precision map data is used to match road types to determine whether the vehicle is in a mountainous area.

[0065] According to some implementations, power is automatically compensated when a large angular velocity is detected by the IMU or when the road is identified as a curve or mountain road from the map. This is because non-line-of-sight obstructions and mountain barriers are present at the road, requiring stronger diffraction capabilities to penetrate these obstacles. Diffraction loss is related to frequency and the geometry of the obstruction; since the LoRa frequency is fixed, this loss is compensated for by increasing the link budget.

[0066] According to some implementations, on ordinary road sections, a smaller spread factor (SF) (such as SF7) and a larger bandwidth (such as 250kHz or 500kHz) can be used to obtain the highest data rate, reduce air interface time, and prevent congestion. On curved road sections, an enhanced mode is entered. When the vehicle itself is detected entering a curve (by the rate of change of heading angle or map data), it actively switches to a high-gain mode, i.e., increasing the spread factor to improve receiver sensitivity. Increasing from SF7 to SF10 can provide approximately 7.5dB-10dB of additional link gain, sufficient to compensate for losses caused by diffraction at mountain edges. Alternatively, the bandwidth can be reduced, which lowers thermal noise levels and further improves sensitivity.

[0067] In S105, within the LoRa broadcast communication coverage distance, the first message packet of other vehicles is received.

[0068] According to some embodiments, the first message encapsulation packet is continuously broadcast via LoRa, and the first message encapsulation packet includes the position, speed, heading angle, acceleration, turn signal status, vehicle length and width, and encapsulation timestamp of the other vehicles.

[0069] According to some embodiments, before obtaining the first message package, the vehicle's position, speed, and heading angle are obtained via GPS and / or IMU, and encapsulated into a second message package, which is then continuously broadcast via LoRa.

[0070] According to some embodiments, the data content of the first and second message encapsulation packets includes: vehicle ID, longitude, latitude, speed, heading angle, acceleration, turn signal status, vehicle length / width, and transmission timestamp. The first and second message encapsulation packets are approximately 50 to 100 bytes long, making them well-suited for communication via LoRa, which typically operates at a communication frequency of 1-2 times per second.

[0071] In S107, based on the first message encapsulation packet, the future driving behavior of the other vehicles is predicted and a corresponding driving control strategy for the vehicle is generated.

[0072] According to some embodiments, due to differences in data acquisition times, transmission delays, and processing sequences between different sensing sources, it is necessary to first align the sensing events in the two encapsulation packets in the time dimension, i.e., time alignment. Specifically, this includes: using a high-precision global clock to assign a unified time tag to the sensing data in each message encapsulation packet to achieve timestamp synchronization; and based on the motion state of the vehicle or target (such as speed, acceleration, and heading angle), performing kinematic extrapolation or interpolation on the sensing results at asynchronous times to correct them to the same reference time, thereby achieving motion compensation.

[0073] According to some embodiments, the first message encapsulation packet and the second message encapsulation packet also need to undergo event alignment. This involves identifying and associating semantic information describing the same traffic event in the two encapsulation packets, ensuring that the aligned content has the same physical meaning, thus achieving event semantic matching and event alignment.

[0074] According to some embodiments, after completing time alignment and event alignment, it is necessary to transform and fuse the perception data from different coordinate systems (such as the vehicle coordinate system, radar coordinate system, and map coordinate system) into a unified spatial reference frame. This is known as spatial fusion. Specifically, this includes: mapping the target position, speed, category, and other attributes detected by each sensor to a unified coordinate system using pre-calibrated extrinsic parameters and geolocation information; using methods such as multi-target tracking, Kalman filtering, deep learning feature alignment, or graph neural networks to associate, deduplicate, and optimize the state of similar targets from different sources, generating a consistent, complete, and more confident fused target list; and dynamically adjusting the fusion strategy considering the reliability differences of each perception source under different environmental conditions.

[0075] According to some embodiments, by using time alignment, event alignment and spatial fusion mechanisms, local fine perception and remote wide-area information can be effectively integrated to predict the future driving behavior of other vehicles and generate corresponding driving control strategies for the vehicle itself. This not only enhances the perception capabilities of obscured areas, distant targets and sudden traffic events, but also provides a high-dimensional and highly reliable environmental representation for subsequent collaborative decision-making, path planning and safety control.

[0076] According to some embodiments, the positions and speeds of other vehicles in the first message encapsulation packet are converted to the vehicle's coordinate system to construct a cooperative sensing target. Based on the position, speed, heading angle, and turn signal status of the cooperative sensing target, control commands are generated to decelerate, stop, or maintain the current speed.

[0077] According to some embodiments, the vehicle's status data is obtained, and the vehicle's position (x, y) in the global coordinate system is obtained in real time through the vehicle's positioning system. ego ,y ego ), heading angle θ ego and speed v ego ; Parse the first message encapsulation packet and extract the vehicle's global location (x) from the received LoRa broadcast message. other ,y other ), speed magnitude v other and its heading angle θ other .

[0078] Calculate the relative position (△x, △y), △x = x other -x ego , △y=y other -y ego Rotate the coordinate system, and rotate the relative position and velocity vectors in the opposite direction around the vehicle's heading angle, transforming them into a local coordinate system with the vehicle as the origin and the front as the X-axis (x... local ,y local Similarly, by performing a rotation transformation on the velocity vector, we obtain v in the local coordinate system. x,local v y,local .

[0079] According to some implementations, a "cooperative perception target" data structure is instantiated for each vehicle, containing fields such as: vehicle ID, local coordinates, local speed, heading angle, turn signal status (left / right / off), size, and timestamp. A dynamic target list can be maintained, with an aging mechanism based on message timestamps (e.g., deletion if no update is made within 500ms).

[0080] According to some embodiments, if a high-probability trajectory is predicted, the vehicle's behavior is decided and planned. Combined with safety constraints, the vehicle's speed, steering, or path is dynamically adjusted, such as "keeping straight", "preparing to turn left", "changing lanes", or "emergency braking", to achieve safe and efficient cooperative driving.

[0081] According to some embodiments, based on the current state (position, velocity, heading) and intention label, the corresponding kinematic model is selected, or a pre-trained lightweight neural network is invoked to output a sequence of trajectory points for the next 3–5 seconds.

[0082] According to some embodiments, the planned trajectory of the vehicle is spatiotemporally overlapped with the predicted trajectories of all cooperatively perceived targets. If a potential conflict exists, response logic is triggered. For example, if the predicted trajectory of another vehicle indicates that it is about to enter the lane, a "decelerate" command is generated.

[0083] According to some embodiments, the decision results are converted into longitudinal control commands (such as target acceleration and target speed) and sent to the vehicle control unit (VCU) or ADAS controller to achieve automatic adjustment of the vehicle's behavior.

[0084] According to some embodiments, the LoRa used in the inventive method is not a replacement for the main sensor (camera, lidar) and high-bandwidth communication technologies (such as 5G-V2X for transmitting high-definition maps), but it can form a strong complement to them, building a more redundant, reliable and comprehensive sensing system.

[0085] According to some embodiments, the LoRa P2P communication used in the method of the present invention is a valuable, low-cost, and low-latency auxiliary perception means for intelligent driving perception. In particular, it abandons high performance in order to pursue wide coverage, high reliability and low cost in the transmission of key state information with small data volume. It has great potential in specific application scenarios and is a valuable path to promote the commercialization of intelligent driving.

[0086] Figure 4 A schematic diagram of a LoRa-based communication system for intelligent driving perception, according to an example embodiment, is shown.

[0087] See Figure 4 The LoRa-based intelligent driving perception system includes: a calculation module 01, a communication setting module 02, a message receiving module 03, and a behavior prediction module 04.

[0088] According to some embodiments, the calculation module 01 is used to calculate the cooperative sensing radius of the vehicle based on the vehicle's motion state and the road environment; the communication setting module 02 is used to adjust the LoRa broadcast communication distance according to the cooperative sensing radius, wherein when the vehicle's motion state is an increase in angular velocity and / or the road environment is a mountainous area, the LoRa transmission power level is automatically compensated to expand the LoRa broadcast communication distance; the message receiving module 03 is used to receive the first message encapsulation packet of other vehicles within the LoRa broadcast communication coverage distance; the behavior prediction module 04 is used to predict the future driving behavior of the other vehicles based on the first message encapsulation packet and generate a corresponding driving control strategy for the vehicle.

[0089] According to some embodiments, the calculation module 01 calculates the cooperative sensing radius based on the real-time vehicle status, providing setting conditions for the subsequent setting of the LoRa broadcast communication distance. The communication setting module 02 sets the LoRa broadcast communication distance in real-time based on the cooperative sensing radius calculated by the calculation module 01, ensuring that it can receive information sent by surrounding vehicles within the LoRa broadcast communication distance. The message receiving module 03 receives in real-time the first message encapsulation packets broadcast from other vehicles within the LoRa broadcast communication distance set by the communication setting module 02, which contain status information such as the position, speed, direction, and acceleration of nearby vehicles. The behavior prediction module 04 infers the future behavior of surrounding vehicles (such as lane changing, braking, and starting) through the fused multi-source information, and dynamically adjusts the vehicle's driving strategy (such as following distance and speed planning) accordingly to improve driving safety and traffic efficiency.

[0090] According to some embodiments, Low Power Wide Area Network (LoRa) offers a highly promising technological approach. LoRa boasts advantages such as long-range transmission (up to several kilometers), low power consumption, strong penetration capabilities, and low-cost hardware, enabling the construction of lightweight, self-organizing vehicle cooperative communication networks without the need for cellular network support. By integrating LoRa modules into vehicles, basic safety messages (such as location, speed, and steering status) can be efficiently broadcast to other vehicles, achieving basic cooperative sensing capabilities with wide-area coverage.

[0091] This invention combines LoRa technology to construct a low-cost, easy-to-deploy, and widely covered lightweight collaborative perception system for intelligent driving. It breaks through the perception boundaries of traditional single-vehicle intelligence while avoiding high cost and economic bottlenecks, providing practical technical support for the large-scale deployment of intelligent driving.

[0092] Figure 5 A block diagram of a computing device according to an exemplary embodiment of the present invention is shown.

[0093] like Figure 5 As shown, the computing device 30 includes a processor 12 and a memory 14. The computing device 30 may also include a bus 22, a network interface card 16, and an I / O interface 18. The processor 12, memory 14, network interface card 16, and I / O interface 18 can communicate with each other via the bus 22.

[0094] Processor 12 may include one or more general-purpose CPUs (Central Processing Units), microprocessors, or application-specific integrated circuits, for executing relevant program instructions. According to some embodiments, computing device 30 may also include a high-performance display adapter (GPU) 20 for accelerating processor 12.

[0095] Memory 14 may include a machine system readable medium in the form of volatile memory, such as random access memory (RAM), read-only memory (ROM), and / or cache memory. Memory 14 is used to store one or more programs containing instructions, as well as data. Processor 12 may read the instructions stored in memory 14 to perform the methods described above according to embodiments of the present invention.

[0096] The computing device 30 can also communicate with one or more networks via a DPU smart network interface card (NIC). The DPU smart NIC is used for data processing or external communication, and the central processing unit (CPU) is used for processing data scheduled by the DPU smart NIC. The DPU smart NIC includes a root system-on-a-chip (SoC) and multiple interfaces, through which the SoC performs data communication. The SoC includes a processor and a memory, on which a computer program is stored. When the processor runs the computer program stored in the memory, it implements the method according to an embodiment of the present invention.

[0097] Bus 22 can include address bus, data bus, control bus, etc. Bus 22 provides a path for exchanging information between components.

[0098] It should be noted that, in specific implementations, the computing device 30 may also include other components necessary for normal operation. Furthermore, those skilled in the art will understand that the device described above may only include the components necessary for implementing the embodiments of this specification, and not necessarily all the components shown in the figures.

[0099] The present invention also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method. The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, as well as magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), network storage devices, cloud storage devices, or any type of medium or device suitable for storing instructions and / or data.

[0100] This invention also provides a computer program product comprising a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments.

[0101] Those skilled in the art will clearly understand that the technical solutions of the present invention can be implemented by means of software and / or hardware. In this specification, "unit" and "module" refer to software and / or hardware capable of independently performing or cooperating with other components to perform a specific function, wherein the hardware may be, for example, a field-programmable gate array (FPGA), an integrated circuit, etc.

[0102] 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 the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. 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 the present invention.

[0103] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0104] In the several embodiments provided by this invention, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only 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 coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0105] The units described as separate components may or may not be physically separate. 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 network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0106] 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.

[0107] 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 device. 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 memory 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.

[0108] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0109] Exemplary embodiments of the present invention have been specifically shown and described above. It should be understood that the present invention is not limited to the detailed structures, arrangements, or implementations described herein; rather, the present invention is intended to cover various modifications and equivalent arrangements contained within the spirit and scope of the appended provisions.

Claims

1. A method for intelligent driving perception based on LoRa communication, characterized in that, The method includes: Based on the vehicle's motion state and the road environment, calculate the vehicle's cooperative perception radius; Based on the cooperative sensing radius, the LoRa broadcast communication distance is adjusted, wherein when the vehicle's motion state is characterized by an increase in angular velocity and / or the road environment is a mountainous area, the LoRa transmission power level is automatically compensated to extend the LoRa broadcast communication distance; Within the LoRa broadcast communication coverage distance, receive the first message packet from other vehicles; Based on the first message encapsulation packet, predict the future driving behavior of the other vehicles and generate a corresponding driving control strategy for this vehicle.

2. The method according to claim 1, characterized in that, Based on the vehicle's motion state and the road environment, calculate the vehicle's cooperative perception radius, including: The safe visibility distance is calculated based on the vehicle's current speed using the following formula: ， in, The safe field of view distance, This is the current speed of the vehicle. This is the braking response delay of the vehicle. This is the braking distance of this vehicle.

3. The method according to claim 2, characterized in that, Based on the vehicle's motion state and road environment, the cooperative perception radius of the vehicle is calculated, which also includes: The cooperative perception radius is calculated based on the safe field of view distance and the vehicle response delay, using the following formula: ， in, Let be the radius of the collaborative sensing. This is the current speed of the vehicle. This is the total system response delay for this vehicle. The safe field of view distance is defined as such.

4. The method according to claim 1, characterized in that, Adjusting the LoRa broadcast communication distance based on the aforementioned cooperative sensing radius also includes: When the vehicle's motion state is characterized by increased angular velocity and / or the road environment is a mountainous area, the signal bandwidth is reduced.

5. The method according to claim 1, characterized in that, Adjusting the LoRa broadcast communication distance based on the aforementioned cooperative sensing radius also includes: When the vehicle's motion state is characterized by an increase in angular velocity and / or the road environment is a mountainous area, the LoRa spreading factor is adjusted by setting the LoRa data transmission rate level.

6. The method according to claim 1, characterized in that, Calculate the root mean square value, peak count, and standard deviation of the vehicle's angular velocity within a preset time window. If any of the calculated values ​​of the root mean square value, peak count, and standard deviation is higher than the flat road threshold, then the vehicle is determined to be in a mountain road area.

7. The method according to claim 1, characterized in that, Before acquiring the first message packet, the vehicle's position, speed, and heading angle are obtained via GPS and / or IMU, and then encapsulated into a second message packet, which is continuously broadcast via LoRa.

8. The method according to claim 1, characterized in that, Based on the first message encapsulation packet, predict the future driving behavior of the other vehicles and generate a corresponding driving control strategy for this vehicle, including: The positions and speeds of the other vehicles in the first message encapsulation packet are converted to the coordinate system of this vehicle to construct a cooperative perception target; Based on the position, speed, heading angle, and turn signal status of the target sensed collaboratively, control commands are generated to decelerate, stop, or maintain the current speed.

9. A system for intelligent driving perception based on LoRa communication, characterized in that, The system includes: The calculation module is used to calculate the vehicle's cooperative perception radius based on the vehicle's motion state and the road environment; The communication setting module is used to adjust the LoRa broadcast communication distance according to the cooperative sensing radius. When the vehicle's motion state is characterized by an increase in angular velocity and / or the road environment is a mountainous area, the LoRa transmission power level is automatically compensated to extend the LoRa broadcast communication distance. The message receiving module is used to receive the first message packet from other vehicles within the LoRa broadcast communication coverage distance; The behavior prediction module is used to predict the future driving behavior of the other vehicles and generate a corresponding driving control strategy for the vehicle based on the first message encapsulation packet.

10. A computing device, characterized in that, include: processor; as well as A memory storing a computer program that, when executed by the processor, implements the method as described in any one of claims 1-8.

Images