536 results about "Local environment" patented technology

The invention discloses a three-dimensional environment reconstruction optimization method based on multi-sensor fusion data, and relates to the field of three-dimensional environment reconstruction optimization, and the three-dimensional environment reconstruction optimization method based on the multi-sensor fusion data comprises the following steps: S1, collecting multi-source sensor data, and constructing a data set under a unified coordinate system; s2, generating dense visual point cloud, and extracting laser point cloud features to construct a model; s3, establishing a local three-dimensional model, and generating a local environment image; s4, shadow parameters are extracted through shadow geometric analysis, and time sequence optimization is carried out; s5, consistency verification and correction are carried out, and three-dimensional reconstruction data are output; and S6, comparing the reconstruction data with the navigation map database, and carrying out map optimization updating. According to the method, time synchronization and space calibration are carried out on data acquired by the depth camera and the laser radar, complete and accurate three-dimensional information modeling of the target environment is realized, and the geometric precision of environment reconstruction and the image detail reduction capability are improved.

The invention relates to a refined energy consumption analysis and optimization management method and system based on rail transit, and solves the problems that a regulation and control mode based on overall energy consumption data cannot accurately adapt to actual energy consumption requirements of all regions, and energy waste or reduction of local environment comfort is easily caused. The method comprises the following steps: according to the optimal illumination brightness and air conditioner output combination of each micro-area obtained by a multi-target particle swarm optimization algorithm, sending a control instruction to related equipment of each micro-area; acquiring energy consumption data of each micro-area, and analyzing and determining whether the energy consumption of the micro-area is higher than an expected range or not according to a preset energy consumption reference value and an expected fluctuation range of each micro-area; if not, maintaining the original setting; and if yes, adjusting the weight of the energy consumption objective function in the multi-objective particle swarm optimization algorithm according to a preset weight adjustment strategy. The method has the advantages that the overall energy consumption of the rail transit is effectively reduced, and fine management is achieved.

The invention, which belongs to the technical field of intelligent breeding equipment, discloses an underwater bionic robotic fish school cooperative breeding environment dynamic monitoring and regulation system comprising a bionic robotic fish body core module, a group cooperative control core module and an intelligent regulation core module. The bionic robotic fish module simulates a real fish swimming mode and carries various water quality sensors to autonomously cruise, so that interference to cultured fishes is reduced; the group cooperation module utilizes a cluster intelligent algorithm and an underwater acoustic communication technology to realize coordinated movement of multiple robotic fishes and full coverage of a monitoring area; the intelligent adjusting module is based on an abnormal detection algorithm, and integrates a miniature oxygenation device, a pH adjusting device and the like to achieve precise regulation and control of the local environment. By the adoption of the system, dynamic sensing and active regulation and control of the culture environment are achieved, a bionic monitoring regulation and control solution is provided for modern aquaculture through intelligent cooperation of the robot fish school and the management system, and the system has the important value of improving the culture efficiency and improving the growth environment.

The invention provides a collaborative decision-making system based on multi-agent reinforcement learning, and the system comprises a global decision-making coordination module, an agent local decision-making module, a state information sharing module, a conflict detection and solution module, and a security and privacy protection module. Each agent realizes autonomous decision making and real-time learning in a local environment, the dependence of the system on centralized control is reduced, the communication burden of the system during data interaction is effectively reduced in a distributed manner, the agents can directly respond based on local data, and the data interaction efficiency is improved. The state information of each agent is collected and analyzed in real time through a global decision coordination module, and the overall strategy of the system is adjusted based on a reinforcement learning algorithm, so that global target implementation in a complex environment is ensured, and the limitation that a traditional system cannot be adaptively adjusted in a dynamic environment is effectively avoided through global optimization; and the global optimization of the multi-agent cooperative system on the basis of each agent target is ensured.

The invention relates to the technical field of battery thermal management, and provides a dynamic thermal management method and system for a battery module, and the method comprises the following steps: carrying out the local environment heat dissipation capability evaluation when a preset triggering condition is satisfied, and generating an evaluation result; generating a heat dissipation adjustment parameter of the heat dissipation system based on the evaluation result and the current thermal state of the local battery; carrying out data monitoring and recording, and generating reported data information; the reported data information comprises data related to local environment heat dissipation capability evaluation, evaluation result data, heat dissipation adjustment parameter data of a heat dissipation system and battery thermal state change data after the heat dissipation system executes adjustment; and uploading the reported data information to a cloud platform, so that the cloud platform executes continuous learning and optimization operation of the thermal management strategy based on the reported data information. The method has the advantages that the adaptability and safety of heat management are improved, and continuous optimization of a cloud strategy is supported.

The invention discloses an airport unmanned luggage tractor path planning method and system, and belongs to the technical field of unmanned vehicle autonomous navigation, and the method comprises the steps: obtaining an initial path and a final path of an airport unmanned luggage tractor; matching the global electronic map of the airport and the path information of the final path with the actual environment information, and judging whether abnormity exists or not; a local environment in an airport is divided into a plurality of two-dimensional grid units, various obstacles are identified in the two-dimensional grid units, potential energy values are given to the grid units corresponding to the obstacles respectively, when the potential energy values are larger than a preset potential energy maximum value, it is judged that abnormity occurs, and a driving path of the unmanned luggage tractor is re-planned and serves as a final path. The operation of judging whether the abnormity exists or not is executed again, and when the abnormity does not exist, the driving path of the unmanned luggage tractor is generated. The method can avoid local path planning of sudden dynamic obstacles.

Embodiments include a system, method, and computer program product that enable secure access to cameras in smart buildings. Some embodiments control outbound video from an environment such as a local network through an intelligent on-event video pushing mechanism. The local intelligent on-event video pushing mechanism hides the IP address of a source video camera, transcodes the video to a reduced size for wide area distribution, and pushes video to a recipient upon an event triggered received within the local environment (e.g., the local network.) Embodiments enable a remote video client on the far-side of the local network firewall to view the video streams of cameras on the near-side of the local network firewall when an event or trigger occurs.

The invention provides a control method and system for automatic carrying equipment of a special transportation line. The method comprises the following steps: constructing a local environment model based on micro-gridding to collect and transmit equipment state information; performing task allocation and path planning on the automation equipment according to the micro-grid environment model; dynamically optimizing task allocation and path planning in a global range according to the task allocation and path planning in each micro-grid; the execution conditions of optimized task allocation and path planning are monitored in real time, the execution sequence of tasks and path planning are dynamically adjusted through an intelligent scheduling algorithm, and flexible adaptive adjustment is made according to resource states and environment changes. Through combination of the micro-grid network and the ant colony algorithm, the problems of single-point fault risk, poor path planning adaptability, inflexible task scheduling and the like in a traditional automatic transportation system are solved, and a brand new solution is provided for efficient, reliable and flexible operation of an automatic transportation special line.

The invention relates to the technical field of robot control, in particular to a robot motion control method, a robot and a system. The method comprises the following steps: acquiring depth information and color information of a current scene and visual textures and geometric features of a target object through an RGB-D camera, and generating a local environment map; introducing a motor current sampling value, correcting the material category of the target object, and determining an initial set value of the clamping force; the corrected joint torque estimated value is converted into a tail end force corrected value through a mechanical arm jacobian matrix; and on the basis of the force control weight and the position control weight, position control output and impedance force control output are calculated respectively, and a final control instruction is generated in combination with the clamping force initial set value and the tooth space compensation item. A harmonic compensation function based on the joint position, the speed and the current is constructed, periodic torque disturbance caused by the cogging effect of the servo motor is effectively restrained, the tail end force estimation is closer to the real acting force, and the clamping control stability is improved.

The invention discloses a robot dynamic obstacle avoidance trajectory planning method, which comprises the following steps: determining the position of a workpiece by taking a global camera as guidance, and acquiring a global path from a starting point to a target point by taking a Bi-RRT algorithm as a global planner in a motion planning process; when a moving obstacle is detected in the operation area, a depth camera on a robot manipulator is turned on to capture depth information of a local environment in real time; an obstacle in a local environment is simplified into an AABB bounding box, a mechanical arm connecting rod of the robot is simplified into space line segments, and whether the mechanical arm connecting rod collides with the obstacle or not is pre-judged by judging whether all the line segments intersect with the bounding box or not; and when the mechanical arm connecting rod collides with the obstacle, local motion planning is carried out based on the SAC algorithm, and a corresponding obstacle avoidance action instruction is generated. According to the method, the global optimal path can be quickly planned, and accurate dynamic obstacle avoidance can be realized. Correspondingly, the invention further provides a robot dynamic obstacle avoidance trajectory planning system, electronic equipment and a storage medium.

The invention discloses an automatic driving decision planning method based on deep reinforcement learning and an A-Star algorithm, and the method comprises the steps: carrying out the global path planning through the A-Star algorithm, processing local environment perception information through a deep reinforcement learning model, and making a real-time decision; a neural network model is trained by setting a reward function, so that a complex traffic environment can be effectively processed on the premise of ensuring safety, and good real-time performance and flexibility are achieved; a dynamic safe vehicle distance calculation mechanism based on the vehicle speed and a reward and punishment mechanism for behaviors such as deviating from a global path and approaching a front vehicle are introduced, so that the driving safety is improved; through simulation environment training, the intelligent agent can learn an optimal driving strategy, and more efficient and more intelligent automatic driving is realized. According to the method, the driving decision can be efficiently and accurately provided for the automatic driving vehicle, and the method has good generalization ability and adaptability so as to adapt to complex and changeable traffic environments.

An embodiment relates to a system of a vehicle comprising a first vehicle ecosystem module comprising a first communication system and a first vehicle ecosystem unit comprising a local environment matrix, and a global governance module that is internal or external to the system, wherein the global governance module comprises a learning agent and a second communication system comprising a protocol unit, wherein the learning agent is configured to learn continuously and update rules for an outcome of the first vehicle ecosystem module when power in the vehicle is turned on, wherein the system is configured for autonomous communication between the first vehicle ecosystem unit and a second vehicle ecosystem unit, wherein the second vehicle ecosystem unit is either internal or external to the system.

The invention relates to the technical field of substation operation and maintenance, in particular to a robot inspection path optimization method and system applied to an extra-high voltage substation, and the method comprises the steps: triggering the dynamic optimization of an inspection path in response to the detected equipment operation state change or inspection environment change of the extra-high voltage substation; based on a preset transformer substation environment space model and real-time equipment states and environment parameters collected in real time, a first target inspection path is generated through path cost analysis, and simulation verification and fine adjustment are carried out; when interference risks, positioning deviation overrun and / or multi-machine conflicts exist in execution of the first target inspection path, path planning is updated based on local environment information collected by the robot in real time, and a second target inspection path is generated; and executing the second target inspection path. According to the invention, the equipment state and the environment change can be responded in real time, the inspection path can be automatically adjusted, key inspection tasks are prevented from being omitted, and the continuity of the inspection process is ensured.

The invention provides an unknown target collection-oriented mobile robot motion planning method. The method comprises the following steps of S1, synchronously constructing a grid map in a moving process of a mobile robot; s2, extracting a boundary region and a passable region; s3, the mobile robot continuously explores the environment; s4, the exploration degree of the local environment is judged according to the balance function; s5, if the exploration of the local environment is completed, the mobile robot collects targets in the task area; s6, the mobile robot completes ascertainment of the sub-regions and region coverage collection; step S7, when all unknown environments are detected and all task area targets are collected, the unknown target collection task is completed; the unknown target collection motion planning method of the mobile robot is good in performance, the mobile robot can rapidly complete exploration of an unknown environment and collection of targets in a task area, and task requirements can be effectively met.

The invention relates to a DRL-based AUV (Autonomous Underwater Vehicle) path planning and obstacle avoidance method in a partially observable environment, which comprises the following steps of: firstly, executing an AUV path planning and obstacle avoidance task under the condition that marine environment information is partially observable; secondly, constructing an underwater environment model and an AUV kinetic model, and constructing a dynamic and static separated dual-channel adaptive sensing model through local environment information acquired by detection equipment; then, path planning is modeled as a Markov decision process, and a multi-objective optimization reward function is designed for collaborative optimization; finally, an improved maximum entropy SAC algorithm is combined with a priority experience playback mechanism to train a strategy network, a gliding mode is dynamically triggered through a physical constraint layer, attitude angle and thrust output is corrected in real time, and the safety boundary condition is monitored in real time. According to the method, the real-time performance of path planning, the dynamic and static obstacle avoidance success rate and the ocean current utilization rate under the complex sea condition can be remarkably improved, and a high-robustness autonomous navigation solution is provided for ocean exploration.

The invention provides an unmanned ship intelligent hunting control method, device and equipment, and relates to the technical field of unmanned ship intelligent control, and the method comprises the steps: obtaining the state information of a current unmanned ship and the local environment data sensed by the current unmanned ship, and obtaining the sensing state information corresponding to the current unmanned ship; based on the sensing state information, constructing a structured state input vector by adopting a distance sorting and filling cutting mechanism; inputting the structured state input vector into a hierarchical strategy network, generating a task role and behavior decision by a high layer, and generating a navigation speed and direction control instruction by a low layer in combination with the high-layer output and structured state input vector; wherein the hierarchical policy network is obtained by optimizing a preset policy network by adopting reinforcement learning through a structured reward mechanism; and controlling the current unmanned ship to execute a hunting task on the target ship according to the navigation speed and direction control instruction. According to the scheme, the stability and flexibility of a multi-boat cooperation strategy and the success rate of a hunting task are effectively improved.

The invention provides a path planning method and device, a storage medium and electronic equipment, and relates to the field of automatic driving. The path planning method comprises the steps that a global environment corresponding to a driving task of a target vehicle is acquired, the global environment is divided into a plurality of local environments, and the global environment comprises obstacles; for each local environment, calculating the number of sampling points matched with the environment characteristics of the local environment, and generating a corresponding number of passing points in the local environment based on the number of the sampling points; generating a plurality of global paths based on the passing points corresponding to the plurality of local environments; and determining a target driving path of the driving task from the plurality of global paths. According to the invention, the number of sampling points and the calculation complexity are reduced, and more efficient path planning is realized.

The invention relates to the technical field of automatic agricultural equipment, in particular to an orchard plant protection robot cluster operation system which comprises a central scheduling module, a cluster communication module, an environment modeling module and an updating module. The central scheduling module communicates with a robot through a communication technology, and the cluster communication module constructs a robot cluster communication network by using a communication network configuration strategy; the environment modeling module evaluates the complexity of a local environment through a sensor assembly, and generates a local map containing orchard terrain, vegetation density and obstacle information. The updating module splices the local maps to generate an operation map, updates a communication network according to the environmental complexity, and optimizes task allocation and path planning of the robot cluster; the system has the functions of task scheduling, communication network optimization and map updating, and efficient collaborative operation of a robot cluster in a complex orchard environment is achieved.

The invention belongs to the technical field of farm environment regulation and control, and discloses a farm environment regulation and control system and method, and the system comprises a multi-source sensing module, a data analysis module, an intelligent decision module, and a regulation and control execution module. According to the method, the dynamic environment coupling model is constructed, the environment state is comprehensively evaluated in combination with the multi-source sensing data, and the internal conflicts and cooperative relationships among the regulation and control parameters are accurately identified, so that the cooperative regulation and control instruction set considering multiple targets is formulated. Therefore, the problem of linkage environment imbalance caused by single regulation and control in traditional control is avoided, and the overall stability and comprehensive comfort of the breeding environment are remarkably improved. According to the invention, animal behavior perception is taken as a core feedback and feedforward signal, and conversion of a regulation strategy from passive response to active prediction is realized. The system can pre-judge the change of a local environment in advance according to the moving trend of animals and perform fine adjustment, so that stress events such as ammonia peak value or violent fluctuation of temperature and humidity are effectively avoided.

The invention discloses an office chair cushion temperature and humidity multi-stage regulation and control method and system. The method comprises the steps that the contact state of a cushion and a human body contact interface, the local environment, human body physiological response and external environment multi-dimensional parameters are collected in real time; the parameters are matched with a dynamic reference model constructed by multi-user historical comfort data, the matching degree is calculated, and multi-level discomfort levels of all contact areas of the cushion are divided; in combination with the discomfort level and the environmental condition, generating a personalized strategy corresponding to the multi-level regulation intensity through a multi-objective optimization algorithm; and the temperature and humidity adjusting device is driven to execute multi-stage cooperative regulation according to a strategy, and feedback data is collected to update the model. The system integrates a multi-parameter acquisition module, a data processing module, an execution regulation module and the like, and can realize automatic damp-proof management of the seat cushion after the seat is separated from the seat. The problems that existing regulation and control are single, the dynamic comfort requirement cannot be met, and the hidden danger of moisture after the cushion is separated from the seat is solved, and the comfort, sanitation and durability of the cushion are remarkably improved through full-period and multi-stage precise regulation and control.

The invention relates to the technical field of video recognition, in particular to a construction safety real-time high-precision detection method and system based on environmental characteristics. Arranging a plurality of sensors in a to-be-detected area to collect field environment data in real time; analyzing the illumination change of the to-be-detected area through the light and shadow analysis model, calculating a light-safety misjudgment index, and identifying a potential light misjudgment area; a visual processing model is utilized to analyze the worker video, human skeleton key points are recognized in real time, personnel behavior safety indexes are obtained, and potential dangerous behaviors are detected; detecting local wind speed and turbulence conditions and vibration and resonance phenomena of a to-be-detected area in real time through a local breeze and vibration detection model, and evaluating a local environment stability index; and the safety level of the to-be-detected area is calculated in real time by using the light-safety misjudgment index, the personnel behavior safety index and the local environment stability index, so that multi-dimensional and real-time construction safety risk assessment is realized.

The invention provides a multi-modal fire-fighting robot cluster cooperation method and system, a medium and a product, and relates to the technical field of fire-fighting robots, and the method comprises the steps: obtaining own multi-modal sensing data collected by a fire-fighting robot cluster in real time, and generating a corresponding local environment model for each robot in the cluster; the working state of the current master control fire-fighting robot is monitored, if abnormity is found, the master control performance of a non-master control robot cluster (except the current master control robot) is analyzed according to the local environment models, and a new master control fire-fighting robot is determined; acquiring associated multi-mode sensing data collected by a new master controller from the local environment model of the slave robot cluster through a wireless ad hoc network, and generating a new global collaborative operation strategy according to the associated multi-mode sensing data; and distributing the new global collaborative operation strategy to each robot of the non-master-control robot cluster, and controlling the robots to carry out fire-fighting operation according to the strategy. The technical problem that a fire-fighting robot cluster is difficult to collaboratively carry out fire-fighting operation under the condition that a master control node fails in the prior art is solved.

The invention discloses a multi-unmanned aerial vehicle cooperative formation method in a complex dynamic environment based on an MASAC algorithm. The method comprises the following steps: firstly, establishing a mathematical model of multi-unmanned aerial vehicle cooperative formation, and initializing model parameters; then calculating a dynamic target of each unmanned aerial vehicle by adopting a multi-unmanned aerial vehicle cooperative control method combining a dynamic virtual target and pilot following, and interacting with the environment to move to a new position; converting a multi-unmanned aerial vehicle cooperative formation problem into a distributed partially observable Markov model, and training the model by using an MASAC algorithm to obtain a convergent strategy model; and finally, carrying out a multi-unmanned aerial vehicle cooperative formation task by using the trained strategy model. According to the invention, the accuracy of autonomous navigation and adjustment of the multi-unmanned aerial vehicle formation in a complex environment is improved, the adaptability of the multi-unmanned aerial vehicle task is improved, the unmanned aerial vehicles can quickly respond to the change of a local environment without depending on a central node, and the efficiency and safety of task execution of the multi-unmanned aerial vehicle cooperative formation are improved.

The invention relates to the technical field of dust concentration detection, in particular to an online detection method and system based on limited space dust concentration, and the method comprises the following steps: based on each detection area, analyzing scattered light signals, classifying the scattered light signals into different particle size categories according to angles and coordinates, and performing signal compensation in combination with real-time humidity; adjusting the irradiation direction of the LED array to optimize illumination distribution, comparing light intensity differences, dynamically scheduling uniform illumination areas, subdividing detection points, analyzing layering signals, and obtaining particle size layering concentration data. According to the invention, distribution mapping with distinct particle size category difference is realized by using a spatial multi-dimensional layered structure, signal adaptability is improved by fusing a humidity dynamic response mechanism, particle size, humidity and illumination multi-source data are dynamically fused, local environment interference is eliminated through layering and compensation linkage, and the accuracy of the system is improved. The continuity of data expression and the response speed of concentration monitoring are improved, and continuous dynamic tracking of the dust state in a limited space complex environment is supported.

The invention provides an unmanned ship cluster confrontation game method and system based on situation information. The survival ability and combat efficiency of an unmanned ship cluster in a complex confrontation environment are improved. The method comprises the following steps: firstly, collecting threat data of the enemy unmanned surface vehicle and quantitatively evaluating the threat degree, collecting performance data of the our unmanned surface vehicle and quantitatively evaluating the adaptability, and fusing the threat data and the performance data by using an analytic hierarchy process to obtain a comprehensive situation evaluation result; then, sub-task targets are determined according to the comprehensive situation assessment and the overall task target, and tasks are reasonably allocated to the unmanned surface vehicles by adopting an improved Hungary algorithm; and finally, performing local path planning on each unmanned ship by adopting an improved A * algorithm in combination with a local environment, and performing global path planning based on multi-agent collaborative consideration of cluster collaborative requirements and enemy threat distribution. According to the method, comprehensive situation assessment, reasonable task planning and scientific path planning are realized, and the unmanned ship cluster confrontation capability is improved.

The invention provides a multilevel backtracking unmanned aerial vehicle path planning method based on a neighborhood extension algorithm, aiming at the problems that the traditional A * algorithm is low in efficiency and easy to fall into dead angles in unmanned aerial vehicle path planning. The method comprises the following steps: firstly, generating a random two-dimensional grid map simulation task environment; secondly, grids in eight neighborhoods of the current position of the unmanned aerial vehicle are scanned in real time, and local environment information is dynamically updated; and finally, a neighborhood extension planning algorithm is adopted, the unmanned aerial vehicle is allowed to perform diagonal motion, the planning flexibility and efficiency are improved, and redundant nodes and unnecessary curves are reduced. According to the method, a multi-stage backtracking strategy is designed, and a key backtracking point is preset in a path planning process, so that the unmanned aerial vehicle can quickly identify and return to a preset optimal backtracking point when entering a dead angle due to the limitation of a local environment, thereby quickly returning to a safe area and re-planning a path. According to the strategy, local optimal solution and infinite loop search are effectively avoided, and the task execution efficiency is remarkably improved in a complex environment containing a large number of dead angles.

The invention discloses an animal house environment intelligent monitoring management system, and belongs to the technical field of environment supervision. The method is used for solving the technical problems of poor active multi-dimensional supervision processing effect and poor self-adaptive optimization management effect of growth environments of animals of different categories in an existing scheme. The method comprises the following steps: respectively screening and classifying a feeding monitoring processing sequence and a local environment index processing sequence which are subjected to early-stage digital processing combination, and respectively carrying out data processing on abnormal feeding animals and abnormal environment animals which are obtained by classification to obtain a corresponding local environment anomaly degree and an overall environment anomaly degree; the local overall abnormal influence values of different dimensions in the early stage are integrated and calculated to obtain living state identifiers corresponding to different animals, the living state identifiers are subjected to data analysis to obtain living states corresponding to different animals, and targeted environment optimization management is implemented.

The invention provides a system and a method for real-time development, debugging and deployment of a server-free application, which are used for solving the problems of separation of a local environment and a cloud environment, difficulty in debugging and the like in the development process of the server-free application. The system comprises a local integrated development environment, a cloud server-free execution environment, a real-time synchronization module, a remote debugging module, a connection agent module and a deployment module. Wherein the real-time synchronization module realizes real-time increment synchronization of a local code and a cloud code through an increment synchronization algorithm, a Hash index algorithm and an encrypted transmission protocol; the remote debugging module supports debugging operations such as breakpoint debugging, variable checking and single-step execution on the cloud application in the local IDE; the connection agent module is used for establishing two-way communication between the local IDE and the cloud instance; the deployment module can execute the construction and deployment of the application at the cloud, and the deployment process is simplified. According to the invention, seamless integration of a local development environment and a cloud operation environment is realized, the debugging limitation of a server-free architecture is overcome, and the development efficiency and the application quality are improved.

Smart sensors, platforms for smart sensors, and associated systems and methods, are disclosed herein. In some implementations, the platform includes hardware interfaces that are abstracted and / or standardized as defined by various common group types. The abstracted interfaces allow numerous different sensors to be connected and integrated into the smart sensor as desired for a specific application. Further, the platform can reuse a standardized software backbone as a sensor platform as sensors are varied, as well as across multiple smart sensors. In some implementations, the standardized sensor platform can include an on-board resident user interface (RUI) with an internet-accessible portal, allowing users to connect to the RUI on the sensor platform through any network accessible device. The platform can also include an artificial intelligence and / or machine learning engine to turn raw sensor data into real-time automation and inspection information within the sensor within the local environment.

The invention discloses a vehicle track prediction method and system for a complex traffic scene, and the method comprises the following steps: S1, obtaining the historical track information of a target vehicle and surrounding vehicles in the traffic scene, and extracting the track time sequence characteristics of a prediction target and the historical track information of the surrounding vehicles through a hierarchical graph neural network; s2, acquiring environment information in a traffic scene where the target vehicle is located, and extracting environment multi-scale features in global and local environment information around the target vehicle by using a hierarchical graph neural network and an attention feature fusion module; s3, performing interactive fusion on the vehicle track time sequence features and the environment features by using multiple attention blocks to obtain interactive features between the scene and the vehicle; and S4, decoding the fusion features of the scene and the vehicle, and outputting a multi-modal future trajectory of the prediction target. The method can ensure that the model can adapt to a complex and changeable traffic environment while the prediction accuracy of the model is improved and the complexity is not increased.