97 results about "Intelligent vehicle technologies" patented technology

The invention provides a warning method and system of an intelligent tripod warning lamp, and relates to the technical field of intelligent vehicle-mounted technologies. When a vehicle is in danger, vehicle state information is collected to automatically generate a warning trigger instruction, and a rear target projection point is determined based on a road type and a vehicle position; projection parameters are calculated in combination with vehicle postures, a vehicle-mounted projection light source is driven to generate a triangular warning graph on the ground at the target distance, meanwhile, light beam output is adjusted in a self-adaptive mode according to environment illumination and visibility, and it is guaranteed that the graph is clear and visible and conforms to human eye safety; the projection position and parameters are dynamically updated to maintain stable warning during the duration of the dangerous state, and the system is automatically closed and reset when the danger is relieved or manual termination is performed, so that the risk of manual arrangement is avoided, and long-distance stable warning is realized.

The invention relates to the technical field of intelligent automobiles, in particular to an intelligent cabin multi-AI Agent cross-domain collaborative super-brain system and an interaction method, and the system comprises a sensor cluster, a central decision AI Agent, a five-domain AI Agent and a cross-domain synchronization mechanism. The sensor cluster is used for collecting multi-dimensional data and transmitting the multi-dimensional data to the central decision AI Agent; the central decision AI Agent is used for processing the data, including analyzing fused data to establish a mapping relation corresponding to scenes and services, performing cross-domain priority arbitration and realizing inter-domain data synchronous scheduling; the five-domain AI Agent comprises a cabin domain AI Agent, a power domain AI Agent, a vehicle body domain AI Agent, a chassis domain AI Agent and an automatic driving domain AI Agent and is used for executing specific functions. According to the invention, the problem of function islands of a traditional intelligent cabin is effectively solved, deep coupling and dynamic linkage of cross-domain functions are realized, the function utilization rate is increased from less than 20% in the prior art to more than 78%, and the utilization rate of system resources is remarkably improved.

The invention discloses a multi-view perception method for 3D point position coding and memory queue time sequence modeling based on depth priori, and belongs to the technical field of intelligent vehicles. According to the method, continuous multi-frame multi-view images of a nuScenes data set and camera parameters are used as input, the whole process comprises the steps that an image backbone network, a depth prediction module, a 3D position coding module and a 3D Transform decoder cooperatively operate, and perspective view features are generated firstly; converting the 3D point coordinates into 3D point coordinates with depth priori, converting the 3D point coordinates into embedded features, fusing the embedded features with image features, and inputting the fused features into a lightweight 3D Transform decoder; and finally outputting target classification and 3D bounding box parameters. According to the method, the consistency and expression ability of position features are effectively enhanced, efficient time sequence modeling is realized, the detection precision is improved, dense feature calculation overhead is avoided, the model convergence speed is increased, and the long-distance small target detection performance is improved.

The invention discloses an evaluation method and device for a vehicle-mounted control unit and a vehicle, and relates to the technical field of automatic testing technologies and intelligent vehicles, and the evaluation method for the vehicle-mounted control unit comprises the steps: obtaining vehicle use scene data corresponding to the vehicle-mounted control unit, the vehicle using scene data is used for representing scene working condition characteristics of the vehicle-mounted control unit in a whole vehicle using process, and the whole vehicle using process comprises a travel preparation stage, a travel advancing stage and a travel ending stage; driving a vehicle-mounted control unit to execute control operation by using the vehicle use scene data to obtain test data; and performing function evaluation on the test data to generate an evaluation result which is used for representing whether the function performance of the vehicle-mounted control unit meets the release standard or not. According to the method and the device, the technical problem of poor accuracy of an evaluation result caused by a method for evaluating the vehicle-mounted control unit based on a modular function case in related technologies is solved.

The invention provides a vehicle trajectory prediction method and system, and relates to the technical field of intelligent vehicles, and the method comprises the steps: obtaining the current trajectory data of all vehicles in a target road section; performing driving intention classification on the current trajectory data of the target vehicle through an intention prediction model constructed based on LSTM to obtain intention features; according to the current trajectory data of all vehicles, through a feature aggregation mechanism of a graph convolutional neural network, feature information of the target vehicle and neighbor vehicles is aggregated, and spatial interaction features are extracted; and based on the intention features and the spatial interaction features, generating future trajectory coordinates of the target vehicle in the target road section by using Transform. According to the method, the prediction precision and robustness are improved, meanwhile, it is ensured that the generated trajectory conforms to the driving intention and the real traffic dynamics constraint, the high-accuracy and high-rationality vehicle trajectory prediction precision in different scenes is remarkably improved, and more reliable environment perception and decision support is provided for an automatic driving vehicle.

An interaction method and device, a terminal and a storage medium are applied to the technical field of interaction technologies and intelligent vehicles. The control object can be selected based on the voice information input by the user, and the state of the control object is adjusted based on the hand movement of the user. Wherein the voice can directly determine a control object, the gesture can enable a user to freely express quantitative meaning, interaction is jointly completed through combination of the voice and the gesture, and efficient interaction can be achieved. Moreover, the user does not need to get close to the operation equipment (such as a touch screen and a key) in voice and gesture operation, so that the user can complete direct selection and free adjustment of the operation object at a relatively low cost under a comfortable condition, and the use experience of the user is remarkably improved.

This application discloses a vehicle control method, system, electronic device, and storage medium, belonging to the field of intelligent vehicle technology. In this method, when the in-vehicle terminal recognizes a keyword for starting the vehicle based on voice data, and if a driver is present in the driver's seat, it sends the voice data and a video feed from the driver's seat to the server for further security verification. Once the server confirms that the voice data and the driver match the relevant information provided by the target user, it notifies the in-vehicle terminal to control the vehicle start. This method, while enabling voice-controlled vehicle start, ensures the security of vehicle starting and avoids situations where the user forgets their car key or the key malfunctions, thus improving the user experience.

The invention discloses a security situation awareness method based on an intelligent networked automobile, and relates to the technical field of new energy intelligent automobiles. S2, establishing a vehicle real-time communication link; s3, early warning communication of adjacent vehicles; and S4, protecting the driving operation. According to the security situation awareness method based on the intelligent networked automobile, a vehicle-mounted external sensor network is constructed through a Sudoku topology, the awareness range of a single vehicle is expanded to the whole domain covered by the Sudoku, and information interaction is performed between the vehicle in the Sudoku and the adjacent vehicle through a communication link. Therefore, the sensing range is greatly expanded, the sensing blind area is effectively eliminated, and the early warning information is transmitted through V2X, so that the vehicle in the middle lane can respond in time when the vehicle in the side lane encounters the ghost probe condition, and the vehicle in the middle lane does not need to respond when sensing the ghost probe condition. Therefore, the advanced response time is greatly prolonged according to the early warning information of the surrounding vehicles.

The invention discloses an unmanned vehicle obstacle sensing method and system for a complex cross-country environment, and belongs to the technical field of intelligent vehicles. The method comprises the following steps: acquiring terrain parameters and vehicle control parameters, and constructing a deep network model; obtaining maneuverability indexes of the vehicle based on the terrain parameters, the vehicle control parameters and a deep network model; the uncertainty and the risk of the maneuverability index are quantified; acquiring image data based on a binocular camera stereoscopic vision system, processing the image data, and performing non-standard obstacle identification and trafficability risk probability assessment based on the processed image data; and performing global path planning and local dynamic planning on the off-road vehicle. According to the method, the precision and adaptability of dynamic modeling can be remarkably improved, real-time identification and risk assessment of non-standard obstacles are effectively realized, the intelligence, reliability and real-time performance of a planning and decision-making mechanism are enhanced, and the viability and task completion rate of off-road vehicles in a complex non-structural environment are improved.

The application provides a calibration method and device of a vehicle-mounted surround view system, and relates to the technical field of intelligent vehicles. The method comprises the following steps: acquiring an image of a calibration object collected by a vehicle-mounted camera, the calibration object comprising multiple regions, at least one region comprising a pattern containing identification information, identifying the identification information of the pattern and the two-dimensional coordinates of the corner points of the pattern, and determining the calibration external parameters of the camera according to the identification information of the pattern and the two-dimensional coordinates of the corner points. Thus, the external parameter calibration of the camera is performed by identifying the corner points of the pattern of the calibration object, the distortion generated when the edge region of the image is identified is reduced, the requirement for ambient light and the arrangement difficulty of the calibration object are reduced, the identification rate of the corner points is improved, and the efficiency and accuracy of the calibration are improved.

The invention discloses a network attack detection system and a network attack detection method for a digital-aware-fused intelligent connected automobile, and relates to an intelligent vehicle technology. The system comprises a vehicle end data generation module, a road side unit data acquisition module, a cloud end attack detection module and a detection result display module. The method comprises the two steps of online real-time detection and offline training, during offline training, a training database containing multiple attack types is firstly constructed, then a data driving model is constructed based on a hierarchical vector Transformer model, and finally constraints in vehicles, between vehicles and between vehicles and lanes are fused, so that the data driving model is constructed. Weak, medium and strong constraints are divided according to the relevance between the constraints and the attacks, and a differential fusion scheme is designed. According to the method, deep fusion of data driving and knowledge guiding is realized, spatio-temporal features are extracted in a layered manner, high-precision map information is fused, attack detection precision and interpretability are improved, various network attacks can be effectively detected, and safe and efficient operation of an intelligent networked automobile is guaranteed.

This invention belongs to the field of intelligent vehicle technology, specifically a method for generating key scenarios for intelligent vehicles based on a personalized interactive car-following model. It includes the following steps: Step 1, selecting and preprocessing a natural driving dataset; Step 2, constructing a personalized interactive car-following model; Step 3, generating key scenarios; and Step 4, evaluating the key scenarios. This invention constructs a personalized car-following model with highly realistic interactive characteristics. Based on this model, through multi-weight allocation, it diversifies the interaction features between vehicles and expands the coverage of scenario parameters. This reduces the difficulty of scenario generation while achieving high coverage, high rationality, and high diversity in key scenario generation, solving the problems of low scenario coverage, poor scenario rationality, and limited scenario types in current methods when generating key scenarios based on natural driving data.

The embodiment of the present application provides a kind of single-layer planar dipole antenna, wherein the antenna is applied to intelligent vehicle technical field, wherein the single-layer planar dipole antenna includes: base material, planar dipole antenna, planar balun, differential double-wire transmission line and band ground coplanar waveguide;Wherein, planar dipole antenna, planar balun, differential double-wire transmission line and band ground coplanar waveguide are arranged on the same layer of base material surface;Band ground coplanar waveguide includes center signal conductor and left and right two side reference ground, two metal arms of planar balun are connected to left and right two side reference ground of band ground coplanar waveguide respectively, and the upper end of differential double-wire transmission line is respectively connected to two radiation arms of planar dipole antenna, while the lower end of differential double-wire transmission line two transmission lines are respectively connected to one of center signal conductor and left and right two side reference ground of band ground coplanar waveguide.The embodiment of the present application can realize the integrated molding of antenna by the structure of single surface arrangement antenna, and reduce the integration difficulty of antenna.

The invention discloses a pet emotion recognition method, device and equipment and a storage medium, and relates to the technical field of intelligent vehicles, and the method comprises the steps: obtaining the local state information and behavior state information of a pet leaving a vehicle; constructing a local feature vector according to the local state information and the local weight matrix, and constructing a behavior amplification coefficient according to the behavior state information and the amplification coefficient matrix; constructing a state analysis quantity based on the local feature vector and the behavior amplification coefficient; and determining whether the emotion of the car-leaving pet is in an abnormal state according to the state analysis quantity. According to the method and the device, whether the current emotion of the car-leaving pet is in the abnormal state or not can be determined by comprehensively identifying the body local state and the behavior state of the car-leaving pet, and the user is notified to pay attention in time when the current emotion is in the abnormal state, so that the user only needs to pay attention to the corresponding notification without worrying about anxiety all the time.

The invention belongs to the technical field of artificial intelligence, and discloses a multi-purpose teaching and training intelligent vehicle based on machine vision. The specific use steps of the multipurpose teaching and training intelligent vehicle in a training field given by a user are as follows: S1, initialization and starting, S2, track tracking operation, S3, detection of sidewalks or upslopes, S4, operation in a deceleration zone, S5, acceleration to pass through roundabout, S6, detection of a yellow square frame and traffic light identification, and S7, arrival at a destination: a run6 is started for acceleration in a green light, and the vehicle continuously drives to a terminal point to complete a driving task. Through theoretical pushing and field verification, the rotating speed of the motor of the intelligent vehicle is successfully optimized to 300 revolutions per minute, perfect matching of the speed and the torque is achieved, the running stability of the intelligent vehicle is remarkably improved through the adjustment, the intelligent vehicle can steadily turn at different curves, stable and smooth racing track performance is ensured, and the running safety of the intelligent vehicle is improved. The innovation not only overcomes the centrifugal force problem of the original motor at a high speed, but also enhances the controllability of the vehicle, and establishes a new benchmark for the technical development of the intelligent vehicle.

The application relates to the technical field of intelligent vehicles and discloses an intelligent reconnaissance propaganda vehicle adapted to a plateau extreme environment, which comprises a propaganda vehicle body, a multi-modal data acquisition module used for acquiring data, a fusion processing module used for performing weighted fusion on the multi-modal data and generating comprehensive state information, a fault state simulation module used for generating abnormal state parameters related to the plateau extreme environment, a decision control module used for generating vehicle operation control instructions according to the comprehensive state information containing the abnormal state parameters, a propaganda control module used for determining the priority and distribution strategy of propaganda content according to the vehicle operation state and task demand, and a cooperative communication and parameter updating module. Through the multi-modal data acquisition module, the fusion processing module and the stability evaluation and feedback adjustment mechanism, the comprehensive state information can truly reflect the vehicle operation state under the plateau extreme environment, so that the state determination deviation caused by environmental mutation is reduced.

A communication method and related apparatus are disclosed, applicable to the fields of vehicle networking and intelligent vehicle technology. In this application, a first terminal requests a first credential from a first server to prove its identity to a first vehicle. Interaction information sent from the first terminal to the first vehicle is signed with a first private key corresponding to the first public key in the credential to prevent tampering and forgery. Information exchanged between the first terminal and the first vehicle is forwarded through a second server. This application designs the first and second servers as different servers, remotely implementing secure verification of the identity and permissions of the vehicle control terminal and remote communication between the vehicle control terminal and the vehicle through dual servers. This provides a high level of security protection for remote interaction between the terminal and the vehicle, ensuring convenience while enhancing security.

The application discloses a kind of panoramic image calibration method and system based on algorithm fusion, it is related to intelligent vehicle technical field.The method includes the following steps: obtaining the image sequence to be calibrated, pre-processing image sequence;Parameter calibration model is constructed using expert network, according to different calibration algorithm, multiple sub-networks are constructed, and the image sequence is calibrated using sub-network respectively, the calibration results of all sub-networks are scored, and the image with the highest score is used as the preliminary calibration image;Parameter correction model is constructed using deep learning network, and the preliminary calibration image is corrected according to the remaining calibration results except the preliminary calibration image using parameter correction model, to obtain the final calibration image.The application combines expert network model and deep learning model, not only can evaluate multiple calibration algorithms, but also can learn the advantages in the calibration process of multiple algorithms, and can obtain more accurate panoramic image.

The invention discloses a vehicle anti-slip control method, device and equipment, a vehicle, a storage medium and a program, and is applied to the technical field of intelligent vehicles. The method comprises the steps that it is determined that the vehicle enters a driving state, and a slip position point is obtained according to the current vehicle position; determining an anti-slip adjustment strategy according to the relative position distance between the current vehicle position and the slip position point; and adjusting the driving state parameters of the vehicle before the vehicle passes through the slip position point according to the anti-slip adjustment strategy. According to the embodiment of the invention, active skid resistance can be realized, the vehicle driving state is adjusted before the vehicle slips, the influence of a wet and slippery road surface on vehicle driving is reduced, and the vehicle driving safety can be improved.

This application provides a vehicle defogging control method, apparatus, device, and storage medium, relating to the field of intelligent vehicle technology. By monitoring the interior temperature and the inner surface temperature of the windshield of the target vehicle, and when the inner surface temperature of the windshield is lower than the interior temperature, a fogging risk type is determined based on the interior temperature and humidity. Further, when the fogging risk type is a first fogging risk type, the target vehicle is controlled to perform dehumidification operations based on the ambient humidity or ambient temperature to reduce the fogging risk. When the fogging risk type is a second fogging risk type, the target vehicle is controlled to perform dehumidification operations based on the inner surface temperature of the windshield and the dew point temperature to reduce the fogging risk. The fogging probability corresponding to the first fogging risk type is greater than that corresponding to the second fogging risk type. This application reduces the fogging risk and improves driving safety by implementing different dehumidification operations on the vehicle according to different fogging risk types.

This invention discloses a multifunctional lightweight intelligent four-wheeled vehicle, relating to the field of intelligent vehicle technology. It includes a cleaning mechanism comprising two movable plates connected by a connecting plate. A mounting base has upper-opening grooves on both sides that mate with the movable plates. A spring is connected to the bottom of each groove, and a force-measuring module is installed at the connecting end. The other end of the spring is connected to the bottom of the movable plate. Side plates are connected to both ends of the connecting plate, and a long rod is fixed to each side plate. A second spring is sleeved on the other end of the long rod, and a sleeve is fitted around the outer side of the second spring. One end of the second spring is connected to the long rod and has the force-measuring module installed thereon; the other end of the second spring is connected to the sleeve. Connecting rods are fixed to both sides of the sleeve, and a shaft is fixed to the end of each connecting rod. A brush is fitted around the shaft. This invention provides strong controllability and adaptability for tire cleaning operations.

This invention provides a resource occupancy control method for large-scale vehicle-mounted applications, belonging to the field of intelligent vehicle technology. The method includes: real-time collection of CPU and memory usage data from the vehicle; determining dynamic CPU and memory thresholds based on vehicle hardware configuration information and the scenario priority of the current large-scale application; and performing resource control operations on the inference task of the large-scale application when CPU or memory usage data reaches or exceeds its corresponding dynamic threshold, or when a resource request signal triggered by a high-priority application is received. This invention achieves refined resource management for large-scale vehicle-mounted inference tasks through dynamic threshold adjustment and resource preemption mechanisms, effectively solving the resource preemption problem that may occur when deploying large-scale applications on the vehicle, and ensuring the real-time response of critical vehicle control functions and user experience.

This invention relates to an angle module for a variable-attitude amphibious intelligent vehicle, belonging to the field of mobile intelligent vehicle technology. It solves the problems of poor environmental adaptability, low mobility, high power consumption, and poor functional expandability in existing intelligent vehicles. The module includes: a hub drive motor assembly, an eccentric motor assembly, a steering motor assembly, and an attitude adjustment motor assembly. The hub drive motor assembly includes: a wheel rim, a hub, a paddle, a hub drive motor, and an eccentric disc. The eccentric motor assembly includes: an eccentric rotating platform, an eccentric motor, and an eccentric motor housing. The steering motor assembly includes: a steering rotating platform, a steering motor, and a steering motor housing. The attitude adjustment motor assembly includes: an attitude adjustment rotating platform and an attitude adjustment motor.

This application relates to the field of intelligent vehicle technology, and provides a method for transmitting information in a vehicle and a vehicle in general. The method includes: when a first sub-device in the vehicle needs to send a device signal to a central control device, the sub-device sends the device signal to a master device via a target path, where there are N second sub-devices on the target path, N≥0; the master device receives the device signal and sends a device signal to the central control device. In this application, when a sub-device transmits a device signal to the central control device, it must first transmit the signal to the master device, and then the master device sends the signal to the central control device. The central control device only needs to receive and process the device signal sent by the master device, reducing the load on the central control device and making the signal transmission between peripheral devices and the central control device more stable.

Vehicle window glass, a display control method and related products are applied to the technical field of intelligent vehicles. The window glass includes a first glass layer, a display layer, and a second glass layer. Wherein the display layer is clamped between the first glass layer and the second glass layer, and the display layer comprises a membrane, a plurality of lamp beads and connecting lines of the plurality of lamp beads. The light transmittance of the diaphragm is larger than or equal to a first light transmittance threshold value, and the interval between every two adjacent lamp beads is larger than the maximum length of the lamp beads. In addition, the multiple lamp beads and the connecting wires of the lamp beads are fixedly arranged in the membrane, and each lamp bead is electrically connected with the bus through the corresponding connecting wire. The vehicle window glass can realize stable and clear information display on the premise of not influencing the sight of a vehicle window and ensuring the safety performance of a vehicle, and meets the requirements of a user on information interaction. The invention further provides a display control method for controlling the window glass and other related products.

This application relates to the field of intelligent vehicle technology, proposing a multi-ECU storage sharing method, electronic control unit, and computer program product based on virtual files. The method includes: receiving a file transfer request from an external device, the file transfer request containing the file name, file format, and file size of the file to be transferred; if the file size exceeds the available storage space of the target ECU, then determining a borrowing ECU from among the other ECUs in the vehicle; creating a virtual file according to the file name, file format, and file size, with a portion of the virtual file's storage space located in the target ECU and the remaining portion in the borrowing ECU; receiving the file data of the file to be transferred from the external device and writing the file data into the storage space of the virtual file. This method can solve the problem of ECUs receiving large amounts of data files without requiring cumbersome operations such as disassembling and reassembling the vehicle.

A vehicle control method and a related device relate to the technical field of intelligent vehicles. The method comprises the steps that a vehicle control device obtains state data of a vehicle, wherein the state data of the vehicle comprises space attitude information of the vehicle and / or wheel rotating speed information of the vehicle; the vehicle control device determines the state of the vehicle according to the state data of the vehicle; the vehicle control device suppresses power output of the vehicle when it is determined that the vehicle is in a rolling state. According to the scheme, when the vehicle rolls over, the larger risk of the vehicle-mounted personnel caused by misoperation of a driver can be prevented.

The application relates to the technical field of intelligent vehicles in the technical field of artificial intelligence, and particularly relates to a controller system, which comprises an intelligent driving domain control unit, a man-machine interaction domain control unit, a sensor interface unit connected with the intelligent driving domain control unit and the man-machine interaction domain control unit, the sensor interface unit being used for accessing sensors and transmitting data of the sensors to the intelligent driving domain control unit and the man-machine interaction domain control unit, a third domain control unit, and a network exchange unit connected with the intelligent driving domain control unit, the man-machine interaction domain control unit and the third domain control unit. The third domain control unit is used for accessing one of the following: a chassis system control unit, a power system control unit or a vehicle body system control unit. The application can realize the simplification of external cable connection, reduce the occupation of data flow transfer resources and reduce the vehicle power consumption.

The invention discloses a vehicle-mounted game control method and device, a vehicle and a storage medium, and is applied to the technical field of intelligent vehicles. The method comprises the steps of generating a game control instruction in response to an interaction operation received by input equipment of a vehicle; updating the first game picture based on the game control instruction to obtain a second game picture; the second game picture is displayed in display equipment of the vehicle, the display equipment at least comprises a head-up display device, and at least part of the picture displayed by the head-up display device is located right ahead of a steering wheel of the vehicle. Thus, by keeping part of the second game picture and the interactive operation of the user on the same straight line, the user can watch the clear second game picture without turning the head, and then the immersion sense and the real control sense of the vehicle-mounted game can be improved.

This application provides a control method and control device, relating to the field of intelligent vehicle technology. The method includes: determining target steering angle information based on vehicle speed, yaw moment, and vehicle state information, wherein the target steering angle information includes at least a first target steering angle and a second target steering angle, and the vehicle state information includes at least one of acceleration / deceleration information, slippage information, or steering actuator operating state information; controlling a first axle of the vehicle based on the first target steering angle, and controlling a second axle of the vehicle based on the second target steering angle to suppress vehicle yaw, wherein the first axle is located in front of the second axle. Based on this scheme, the stability of vehicle driving can be effectively improved.