1153results about How to "Adaptable" patented technology

The application discloses an application interface rendering method and apparatus. An SDK package is arranged in a client of an application. The SDK package comprises a rendering engine. A first correspondence between component information defined in interface data and a native component in a current terminal device is stored in the rendering apparatus. The method comprises: completing the following operations through the rendering engine: when a request of displaying a specified interface of the application is received, requesting for interface data of the specified interface of the application from a server; after the interface data returned by the server are received, analyzing the interface data to obtain the component information defined in the interface data; according to the first correspondence, mapping the component information defined in the interface data into the native component in the current terminal device; and rendering the native component. Through the application interface rendering method and apparatus, users can be enabled to use latest functions of applications more timely, and various defects of a hybird scheme are avoided.

A system for detecting fatigue driving in a real-time manner comprises a camera used for capturing a facial image of a driver and a processor used for detecting fatigue; the processor comprises an image acquisition module used for acquiring the facial image of the driver captured by the camera, and an image preprocessing module used for preprocessing the acquired image; the processor further comprises an image processing module used for analyzing the image after being preprocessed by using an AdaBoost algorithm, detecting the left eye and the right eye of the driver, calculating respectively the curvature of the upper eyelid and the goggle-eyed area of the left eye and the curvature of the upper eyelid and the goggle-eyed area of the right eye, blending the curvatures of the upper eyelid and the goggle-eyed areas to obtain the degree to which the eye closes and opens, and detecting whether the driver is with fatigue by a p80 measurement method according to PERCLOS, and an alarm control module used for giving an alarm signal when the image processing module judges that the driver is with fatigue. The system has high reliability, low cost and high applicability.

The invention discloses a method for automatically adjusting speed loop control parameters of an alternating-current servo system based on inertia identification, which comprises the following steps: firstly, a current loop and a servo motor are used as generalized objects, and estimated values of the servo motor and the rotary inertia loaded on the servo motor are obtained by the inertia identification based on a disturbance torque observer; and then a pole collocation method is adopted to adjust proportion parameters and integral parameters of a speed loop proportion integration differentiation (PID) controller automatically. In method for automatically adjusting the speed loop control parameters of the alternating-current servo system based on inertia identification provided by the invention, by combining the inertia identification algorithm based on the disturbance torque observer with the characteristics of an alternating-current servo system, auto-adjustment of the speed loop PID parameters for the alternating-current servo system can be realized under different rotary inertias. Engineers do not need to set and adjust the controller parameters manually according to the experience and the system can automatically carry out the auto-adjustment of the speed loop parameters. Compared with the prior art, the method for automatically adjusting the speed loop control parametersof the alternating-current servo system based on inertia identification is simple in design principle, and has the advantages of good adaptability under the condition that the inertia change of the external load equipment is obvious, and the like.

The invention provides a tool abrasion monitoring method based on wavelet denoising and Hilbert-Huang transformation. According to the method, on the basis of wavelet denoising, the Hilbert-Huang transformation method is used for analyzing signals acquired in the machine tool operating process; according to an amplitude average value, obtained through EMD, of each IMF component and a time-frequency spectrum and a marginal spectrum which are obtained through Hilbert transformation, a normal state of a tool and an abrasion state of the tool are compared, and obvious characteristics are obtained. The self-adaptability of the method is much higher than that of other characteristic extraction methods; according to the method, the defects of high-frequency resolution are overcome, and meanwhile signal characteristics further retain all physical significances contained in original signal characteristics.

The invention relates to an ROS based service robot and indoor navigation method thereof. The service robot includes a mobile chassis, a housing, a support frame, an upper layer PC and a bottom layer PC, wherein the mobile chassis includes a wheel unit, a motor, a motor control panel, a gyroscope, an encoder, an electronic compass, a power source, an anti-collision module and a data collection module. The housing is equipped with a touch screen. The upper layer PC and the bottom layer PC are both equipped with a robot operation system ROS. The navigation method includes that the service robot acquires indoor environment information and creates an indoor two-dimensional map; a target position is set after the map is loaded in a visible window and the position of the robot itself is determined; an overall path is planned by utilizing an overall path planning interface provided by ROS and unknown barriers which are namely movable objects or unknown areas appearing in a navigation process are avoided by utilizing a partial path planning interface provided by ROS.

The invention provides a fault location method based on single-terminal location. The method is characterized by using a transmission line travelling wave fault location device to measure the power frequency quantity of a home terminal bus of a transmission line when short circuit happens to the transmission line, determining the fault point range by an impedance method and estimating the transition resistance; then analyzing the transient voltage/current travelling waves through wavelet transform and adopting a single-terminal travelling wave method combined with the length of line to directly compute the positions of the fault points if the faults are judged to be common short circuit faults; and adopting a transmission line single-terminal fault location method combining the impedance method and the travelling wave method to compute the positions of the fault points if the faults are judged to be special short circuit faults. The method has the following beneficial effects: the accuracy of fault location is ensured by utilizing the single-terminal travelling wave method, can be within 500m and is not affected by such factors as the length of line and the like; and the method can adapt to fault location under the condition of different fault types and is basically not affected by such factors as the transition resistance, the line structure, the system operation mode and the like.

The invention relates to a depth intensive learning-based train running scheduling method and system. The method comprises the steps of first, collecting information about all schedulable trains of one station in a real scene and timetable of the schedulable trains and information about all schedulable drivers, so as to form original information; regularizing the collected original information; building a train depth intensive learning model by using the regularized data information; performing offline training and learning by using the depth intensive learning model, so as to obtain a trained train depth intensive learning model; and performing train running scheduling by the depth intensive learning-based train running scheduling system by using the trained depth intensive learning model. The depth intensive learning-based train running scheduling method and system make scheduling more intelligent, the technological processing process is simple and highly flexible, and the optimization efficiency is high.

The present invention provides poly vinyl alcohol polar foam. Water is used as foamer and plasticizer. According to weight, water is 15 portion to 55 portion, and poly vinyl alcohol is 45 portion to 85 portion. The material are dissolved for expansion, melted and processed for foaming. The melting and processing foaming comprises a melting and extruding continuous foaming method and a molding foaming method. The poly vinyl alcohol polar foam is a plate material, sheet material, membrane or bead or square block. The poly vinyl alcohol polar foam of the present invention can be added with crosslinker, molecular composite agent, processing aid, nucleating agent and functional additive. According to the weight portion, the crosslinker is 0 portion to 2 portion, the molecular composite agent 0 portion to 10 portion, the processing aid 0 portion to 10 portion, the nucleating agent 0 portion to 5 portion and the functional additive 0 portion to 30 portion. When the poly vinyl alcohol polar foam of the present invention is used as heavy metal particles, adsorption, filtration and separation material of organic pollutant, the poly vinyl alcohol polar foam has the characteristics of rapid adsorption, easy desorption and capacity of being repeatedly washed.

An all-ground-anchor type single-tower double-span cable-stayed bridge system comprises a main beam, a stay cable, a main tower and an anchor. The main beam is composed of a side span main beam body and a main span main beam body. The length of the side span main beam body is far smaller than that of the main span main beam body, and the side span main beam body and the main span main beam body are asymmetrically distributed. The side span main beam body is supported by a support arranged on a side span buttress main tower lower beam and fixedly connected with the main span main beam body and the anchor. The stay cable comprises a main span stay cable body and a side span stay cable body. The main span stay cable body supports the main span main beam body. The upper end of the side span stay cable body is anchored to the main tower and corresponds to the main span stay cable body in position. The lower end of the side span stay cable body is anchored to the anchor. The main tower provides anchorage for the main span stay cable body and the side span stay cable body and meanwhile transmits the vertical force of the side span stay cable body to a foundation through a main tower bearing table and a main tower foundation. The anchor provides anchorage for the whole side span stay cable body and meanwhile balances the horizontal force transmitted by the side span main beam body. The invention further discloses a construction method of the cable-stayed bridge system. The cable-stayed bridge system is high in adaptability, reasonable in structural system, easy and convenient to construct, short in construction period, low in manufacturing cost and small in safety risk in the construction period.

The invention provides a remote sensing image registration method and system fusing SIFT features and CNN features, which comprises extracting feature points of an input reference image and an image to be registered, using SIFT mode to carry out feature expression on a neighborhood area of the feature points, and obtaining SIFT features; the neighborhood region of feature points being used as theinput of convolution neural network (CNN), and the CNN model trained by transfer learning strategy being used to express the high-level features, and the CNN features being obtained. The SIFT featureand CNN feature are fused, similarity is calculated, geometrical transformation parameters between reference image and the image to be registered are estimated, geometrical transformation and resampling are performed on the image to be registered, and the registered image is obtained. The invention combines the bottom feature extracted by the traditional feature and the advanced feature extractedby the convolution neural network, and the combined feature can more accurately express the remote sensing image content, greatly improves the remote sensing image registration accuracy and has strongadaptability.

The invention relates to a measuring system of a three-dimensional shape of a strong reflecting surface based on a high dynamic strip projector. The measuring system comprises a computer, the high dynamic strip projector and an image acquisition unit. Projection control information is sent to the high dynamic strip projector by the system through the computer, strip images in different light intensities and gray levels are controlled to be projected, meanwhile, control information is sent to the image acquisition unit by the computer, and the image acquisition unit is controlled to carry out photographing in different time periods of exposure; collected image information is transmitted to the computer by the image acquisition unit, the image is processed by the computer, and three-dimensional information of a to-be-detected object is acquired by image fusion, dephasing, phase unwrapping and stereo matching. According to the measuring system of the three-dimensional shape of the strong reflecting surface based on the high dynamic strip projector, saturation and/or excessive darkness of a collected strip image caused by the strong reflecting surface can be overcome, high-precision non-contact optical measurement of the three-dimensional shapes of the strong reflecting surfaces of metals and the like can be realized, and the measuring system of the three-dimensional shape of the strong reflecting surface based on the high dynamic strip projector can be applied to high-precision non-contact optical measurement of the three-dimensional shapes of the strong reflecting surfaces and mirror-similar surfaces of various metals.

The invention provides a method for preparing a self-thermal-insulation concrete building block, and belongs to the technical field of preparation of building materials. The main body of the self-thermal-insulation concrete building block is a thermal insulation concrete structural frame; a plurality of sandwich cavities are enclosed on the outer wall and the inner wall of the frame; and organic light materials, inorganic light materials or organic-inorganic composite light materials are packed or filled in the cavities to form a thermal insulation core layer. The self-thermal-insulation concrete building block prepared by the method has high self-thermal-insulation performance, high shock resistance and high tenacity, is a structural material and a thermal insulation material and has remarkable effects of energy conservation, environment friendliness and reduction in building cost after being used.

The invention relates to a fine S-wave impedance access technology based on a logging and prestack channel set seismic data. The technology is characterized by calculating an elastic modulus of a dry rock matrix and a modulus of saturated fluid rock by a Xu-White equation; taking a conventional sound wave and a density logging as a datum curve based on the estimation of initial S-Wave speed, and correcting and inputting elastic parameters to obtain the initially corrected S-wave impedance information; and establishing an iterative inversion model via an error obtained by comparing the change rule changing with offset distance of amplitude of the prestack channel set and an actual outdoor seismic channel set synthesized by a P-wave and a S-wave and density information with a wave group by a rotation orthogonal direction-based method to finally obtain a S-wave impedance curve. The technology has strong adaptability, convenient operation, simple and easy calculation, strong anti-noise capability, stable S-wave parameters and the like, and position change of a plurality of main in-phase shafts between a synthetic channel set and the actual seismic channel set obtained by initial inversion parameters is consistent with the amplitude change.

The invention relates to a method for executing the phasor correcting for a synchronous phasor measuring apparatus, used for guaranteeing the accuracy of phasor calculating. In the method in the prior art, the hardware is adopted to measure the frequency and a method for adjusting a data window is adopted to guarantee the accuracy of the phasor measuring. In the method of the invention, a circuit positive sequence voltage is adopted to calculate the circuit frequency, after the offset deltaf of the system frequency relative to 50 Hz is calculated out, a least-squares method is adopted to fit the a series of amplitudes and angle error curve in 45 to 55 Hz, then the phasor is corrected by a look-up table. The method of the invention has fast computational speed, strong adaptability and high accuracy.

The invention discloses an AC/DC compatible vehicle-mounted charger pre-stage circuit and a vehicle-mounted charger. The pre-stage circuit consists of a rectifier circuit, an alternating-current voltage detection circuit, a direct-current voltage detecting circuit, a PFC circuit, a DC/DC boost circuit and a pulse width modulation integrated circuit. The input terminal of the rectifier circuit is connected with an external alternating-current input port; and the output terminal is respectively connected with the input terminal of the PFC circuit and the input terminal of the DC/DC boost circuit. An external direct-current input port is connected with the output terminal of the rectifier circuit; and the output terminal of the PFC circuit and the output terminal of the DC/DC boost circuit are connected with a post-stage power conversion circuit. A first PWM driving terminal of the pulse width modulation integrated circuit is connected with the PFC circuit; and a second PWM driving terminal of the pulse width modulation integrated circuit is connected with the DC/DC boost circuit. According to the technical scheme, compatibility of alternating-current and direct-current voltage inputs is realized; the improvement cost is low; the operation is stable; and the power grid interference and waveform distortion can be reduced.

The invention discloses a self-adaptive modulation and coding method and a device thereof. The method comprises the following steps: obtaining the existing signal-to-noise ratio and service type parameters of a channel transmitting data; determining the modulation mode and coding rate according to the signal-to-noise ratio and the service type parameters; and modulating and coding according to the determined modulation mode and coding rate. The self-adaptive modulation and coding method and the device have strong service adaptability, can perform the modulation and coding according to different service types used by users, which can guarantee the feeling of the users, maximize the frequency spectral efficiency of the system and reduce the error rate.

The invention introduces a manual double-torch double-side TIG welding technology for welding aluminum and aluminium alloy. The welding process comprises the following steps: a vertical upward welding technique is adopted, two manual welding torches simultaneously and respectively initiate arc and weld at the front side and the reverse side of welding joints to be welded; two tungsten electrodes are basically aligned; the two welding torches move simultaneously and share a melting bath; the front side of welding lines are filled with welding sticks while the reverse side is not. Welding parameters such as the reverse side welding torch current and the like are less than the welding parameters of the front side welding torch; once weld penetration is achieved and both sides are shaped; argon shield is adopted in the process of welding; inclination angles Alpha and Beta are controlled within the range of 70-100 degrees, the included angle Theta between the welding sticks and the welding torches is maintained within the range of 80-110 degrees. According to the welding technology of the invention, irregular space curve welding lines of medium wall are welded, the applied technology is flexible and the adaptability is high, thus simplifying production procedures and process steps, greatly improving welding efficiency, avoiding possibility of causing interlayer defects due to multilayer welding and improving interior quality of welding lines and appearance quality thereof.

The invention provides a production method of a low-cost X52 pipeline steel and a pipeline steel. The production method comprises the following steps: desulphurization, converter smelting and continuous casting are conducted on molten iron to prepare a pipeline steel continuous casting billet; the pipeline steel continuous casting billet is soaked to be at 1160-1200 DEG C, and roughly rolled for 3-7 times by a roughing mill to obtain an intermediate billet; the intermediate billet is finely rolled for 4-7 times by a finishing mill; the finely-rolled pipeline steel is quickly cooled to be at 550-610 DEG C at the cooling speed of 50-100 DEG C/s, and is rolled to obtain a pipeline steel finished product. No Nb is added to the low-cost X52 pipeline steel. Through the adoption of the production method of the low-cost X52 pipeline steel, the production cost of the X52 pipeline steel can be lowered, the production technique control is easy, and the adaptability is high.

The invention relates to an extended range electric vehicle energy management method on the basis of fuzzy control, which particularly comprises the following steps that: 1, a vehicle control unit acquires a storage battery SOC (State of Charge) and bus demand power data; 2, the vehicle control unit judges whether the storage battery SOC is less than or equal to 90 percent, the step 3 is executed if yes, and if no, a range extender is controlled to be switched off by a CAN (Controller Area Network) bus; 3, a fuzzy control module carries out fuzzification on the storage battery SOC and the bus demand power data according to a membership function; 4, fuzzy reasoning is carried out on the fuzzified data according to a set fuzzy rule and the membership function; 5, defuzzification is carried out on a reasoning result by utilizing a centroid method and output power distribution values of the range extender and a storage battery are output; and 6, the vehicle control unit sends the output power distribution values of the range extender and the storage battery to the range extender and the storage battery by the CAN bus. Compared with the prior art, the extended range electric vehicle energy management method has the advantages of strong adaptability, capability of promoting the whole vehicle performance and the like.

The invention relates to the technical field of laser processing, in particular to a laser online high-speed notching device based on a galvanometer array. The invention comprises a frame, a transmission belt, the galvanometer array, a laser array, and a control device used for controlling the galvanometer array and the laser array. The galvanometer array and the laser array are arranged right above the transmission belt correspondingly; the control device used for controlling the scanning track and the speed of the galvanometer array is electrically connected with the galvanometer array and the laser array through cables respectively; the invention has the advantages of strong adaptability, fast notching speed, wide scanning breadth, high production efficiency, real-time monitoring, effectively fining domain, reducing the iron loss and obviously improving the quality of oriented silicon steel.

Complex business systems based on work flow in the common component of the process scheduling method, the business systems in use database data extraction process is based on the following process, a component of the software, work flow will be introduced to the database data extraction process scheduling engine : workflow is a series of interrelated automatically business activities or tasks; on the basis of components of the system through the implementation process configuration parameters: For a business processes, first of all, is necessary for the definition of packet components: Parameters designated-operation, input data and output data packets between designated the implementation of the order, thereby constituting a component sub-tasks and then select a different component sub-tasks and sub-tasks between designated the implementation of the order, thereby constituting a complete task component; implementation of this task will be to complete the deal with all the necessary business function.

The invention relates to a human body movement recognition system based on an acceleration sensor, comprising a computer, a plurality of information acquisition subsystems and a main control machine, wherein the information acquisition subsystem and the main control machine are respectively worn on a human body; the main control machine controls the information acquisition subsystems to acquire human body acceleration information and transmits the human body acceleration information to the computer for analysis; the information acquisition subsystem and the main control machine carry out data transmission by a communication mode of wireless radio frequency, thus avoiding inconvenience and uncomfortableness of excessive wires caused by electric connection; even under the lightless condition, only a user carries out movement of relevant modes, the movement of the user can be recognized, therefore, the human body movement recognition system is less influenced by the ambient environment, and has stronger adaptability; and the movement in each movement recognition mode can be adjusted dynamically, a certain movement can be deleted or added, therefore, the user can add or delete the movement to be recognized according to his/her own needs, thus improving the adaptability of the product.

The invention is concerned with the controller, the control method and the temperature controlling circuit of the of the self-adapting temperature real-time controlling plastic jetting-moulding machine that for the closed-loop control electric plastic jetting-moulding machine. It is: the controller consists of up-position machine for monitoring and the down-position machine for execution, the up-position machine and the down-position machine connects by communicating line, processes data information processing with central processing unit. The controlling method is: a. the selection of temperature signal; b. the pretreatment of the temperature signal; c. the rule base comparison of the temperature signal; d. the self-adapting adjustment of the control parameter; e. the outputting application of the controlling signal. The advantages are: can inhibit the effect of big lag effectively, with better stability and robustness; can conclude the experience of the temperature control of accumulation and the experience of the operator of the plastic jetting-moulding machine to be the rule base and the knowledge base, add the adaptive control of the parameter at the stage of temperature rise and temperature preservation in order to reduce the difficulty of using; the control precision of the charging basket static state and the working state is high, the produce is high quality and stabilization.

The invention belongs to the technical field of water environmental biological treatment and relates to a separating screen of a bacterial strain CY003 for efficiently degrading trite nitrogen, nitrate nitrogen and ammonia nitrogen, method for testing safety and preparing bacterial solution, and application for treating domestic sewage and cultivating sewage. The bacterial strain CY003 of the invention is preserved in Chinese Type Culture Collection Center and the preserved number is CCTCC No.: M209196. According to morphological observation, physiologic biochemical analysis and 16S rDNA homology analysis, the bacterial strain CY003 is Pseudomonas stutzeri which can rapidly degrade the trite nitrogen, nitrate nitrogen and ammonia nitrogen in water and is not toxic to the animals such as silver carp, crucian, freshwater shrimp, small white mouse, and the like. At normal temperature, the Pseudomonas stutzeri can excellently degrade the nitrite and the ammonia nitrogen in actual sewage. After culturing 75 h, the Pseudomonas stutzeri can degrade 94.7% and 92.7% of trite nitrogen and ammonia nitrogen in cultivating sewage and can degrade 96.2% and 94.6% of trite nitrogen and ammonia nitrogen in domestic sewage. The invention has wide application prospect.

The invention discloses an intelligent household control system. The system comprises at least one intelligent terminal module, an information transfer module and a cloud processing module. The intelligent terminal module comprises information acquisition equipment, information output equipment, information transmission equipment and a local processing system. Intelligent terminal equipment is arranged in different indoor space areas so that the different set indoor space areas have one intelligent terminal module respectively. And the module is responsible for information monitoring and output in the space area where the module is located, and command processing and transmission. The information transfer module is used for receiving information transmitted by the intelligent terminal module, uploading the information to the cloud processing module, receiving a cloud processing module command and dispatching to the corresponding intelligent terminal module. The cloud processing module is used for processing various kinds of information and commands from the information transfer module and sending a processing result to a cloud server so as to control intelligent household equipment.

The invention belongs to the field of plant nutrition and in particular relates to a method for quantitatively analyzing plant nutrient content index based on leaf image characteristics. The method is characterized by acquiring representative sample leaves to carry out image acquisition on the sample leaves after carrying out culture in lack of nutritional elements on the given plants and obtaining the color characteristic sets and shape characteristic sets of the leaves through conversion; establishing relationship mapping tables between the leaf nutrient content index level and the color and shape characteristic sets and establishing color standards at the corresponding levels; and then analyzing images of the samples after acquiring the images of the leaves to be detected, taking the Euclidean distance as the matching evaluation index and searching the tables to obtain the nutrient index level value according to the corresponding color standards after optimizing matching. The method has the following advantages: the generality and the adaptability are stronger; the accurate nutrient content index value can be given according to the images of the leaves to be detected; and the process is simple, the detection speed is high and the method is easy to popularize.

The invention relates to a preparation method of a Cf-ZrB2/ZrC/SiC composite material, belonging to the technical field of special ceramics. The method comprises the following steps of: (1) putting a carbon fiber prefabricated body in a chemical vapor deposition furnace, and preparing a pyrolytic carbon interface layer on the surface of the carbon fiber by a chemical vapor deposition technology; (2) pressure impregnation: completely immersing the carbon fiber prefabricated body into a precursor solution, discharging gas out of the prefabricated body to be vacuum, immersing the precursor in the prefabricated body by use of high pressure, and finally performing vacuum drying and cross-linking curing; (3) high-temperature cracking: putting the impregnated and cured carbon fiber prefabricated body in a high-temperature cracking furnace, quickly heating to 1,400+/-10 DEG C under the protection of inert atmosphere, and preserving heat for 0.5-2 hours; and (4) densifying treatment: repeating the impregnation cracking process for the carbon fiber prefabricated body after being cracked at a high temperature, until the material density at least reaches 2.0g/cm<3>. The method provided by the invention has the advantages of short period, strong adaptability and excellent material performance.

The invention discloses a machine vision detection device and method for steel rail surface discrete defects. The method includes the following steps that S1, a steel rail surface defect image is acquired; S2, a background smoothing filter is designed; S3, the original image is smoothened to obtain a background image; S4, the original image and the background image are differentiated; S5, dynamicthreshold value segmentation and connected region marking are conducted. According to the method, the smoothing filter is designed with local gray scale and gradient change information in the image asvariables, large-degree smoothing is conducted on the defect region with large gray scale and gradient changes in a local range, weak smoothing is conducted on shadows generated due to non-uniform reflection, rust and other interference regions, and a background image is generated, the original image and the background image are differentiated, differential image threshold segmentation is conducted, and steel rail surface defect detection is achieved. Influences of light changes, steel rail surface non-uniform reflection and rust can be effectively weakened while image defects are highlighted, and good steel rail surface defect detection effects are obtained under different rail environments.

The invention provides a novel AGV visual navigation control method. The method includes a road identification module is used to identify marker lines such as crossroads and bends so as to obtain parameters, which includes position deviation and direction deviation, between an AGV body and a route guide line; a motion control module to perform fuzzy control on the position deviation and direction deviation so as to control the motions of an AGV; a wireless positioning module is used to obtain the current position information of the AGC and display the current position information; a video monitoring module is used to monitor AGV surrounding environments and the information of the AGV; a route planning module is used to plan the shortest route between the AGV and a target. The novel AGV visual navigation control method has the advantages that real-time communication with background is achieved, functions such as visual navigation of multiple branch roads, video monitoring, route planning and wireless positioning are achieved, and high cost performance and adaptability are achieved.

The present invention provides an unmanned vehicle intelligent obstacle avoidance method and system. The system comprises a perception portion, a decision portion, a control portion and an execution portion. The perception portion performs detection of a barrier area through a single-line laser radar to realize barrier information obtaining; the decision portion determines whether the obstacle avoidance of the unmanned vehicle is required at the next moment or not according to the barrier detection condition, if the obstacle avoidance of the unmanned vehicle is required, the control portion inputs the state information of the perception portion to a reinforcement learning model, the model performs trial and error learning to converge to a stable state to calculate the steering wheel corner required by the unmanned vehicle, and the execution portion of the unmanned vehicle is configured for execution so as to realize the obstacle avoidance function.