159results about How to "Improve navigation performance" patented technology

The present invention relates to a road traffic sign identification method with multiple-camera integration based on the DS evidence theory, belonging to the technical field of image processing. According to the method, five types of road traffic indication signs which are going straight, turning left, turning right, going straight and turning left, and going straight and turning right are mainly identified, and the method is divided into two parts which are training and testing. In a training stage, the direction gradient histogram feature of a training sample is extracted, thus a sample characteristic and a category label are introduced into a support vector machine to carry out classification training. In a testing stage, an interested region is obtained through image pre-processing, the direction gradient histogram feature of the interested region is extracted and is sent into a classifier to carry out classification, according to the credibility of the sign to be identified obtained by the classifier belonging to each category, and combined with a DS evidence theory data integration method and a maximum credibility decision rule, a final sign identification result is determined. According to the invention, a multiple-camera data integration method based on the DS evidence theory is employed, the information of multiple cameras are integrated to obtain a final identification result, and the road traffic signs can be stably and efficiently identified.

The invention provides a non-trace switch method for an AUV integrated navigation system. In the method, general navigation equipment is used, so that under the condition of not increasing the cost of a strapdown intertial measuring system, by utilizing the advantages of good mobile effect of a DR(dead-reckoning) system, in the switch mode, the AUV adopts the compass/DVL output; meanwhile, the SINS/DVL integrated navigation system adopts a switch mode self-adapting Kalman filtering model to accelerate the filtering convergence; under the condition of direct sailing, the AUV adopts the navigation method of the SINS/DVL integrated navigation system; and when the AUV works underwater, position speed information outputted by the comprehensive navigation system is utilized to make the closed loop correction of the strapdown inertial navigation, thereby inhibiting the Kalman filtering oscillation due to the mode change and better improving the AUV navigation effect.

An autonomous positioning navigation method for a mobile detection robot belongs to the field of robot vision navigation. In the early stage of the existing robot positioning, a traditional wavelet transform method is used to extract the features of a target image, which is susceptible to noise and affects the positioning accuracy of a robot. The method of the invention comprises the following steps of: reading image information by a sensor, preprocessing the image information, and transmitting the preprocessed information to a V-SLAM system; predicting a transformation matrix of two adjacentframe images through an improved RCNN network, estimating pose information of a camera motion and building a local model of an environment; passing to a backend and optimizing to obtain an accurate camera trajectory and a map; determining whether the robot has reached a certain position before by the received sensor information, a visual odometer, and local backend information; passing the correction information to the backend for optimization and calculation when a correct loop is detected; and building a map so that the established map corresponds to the task requirements.

The invention relates to a mobile-robot route planning method based on an improved genetic algorithm. A raster model is adopted to preprocess a working space of a mobile robot, in a rasterized map, an improved rapid traversing random tree is adopted to generate connections of several clusters between a start point and a target point, portions for the mobile robot to freely walk on in the working space are converted into directed acyclic graphs, and a backtracking method is adopted to generate an initial population which is abundant in diversity and has no infeasible path on the basis of the directed acyclic graphs. Three genetic operators, namely a selection operator, a crossover operator and a mutation operator, are adopted to evolve the population, wherein the selection operator uses a tournament selection strategy, the crossover operator adopts a single-point crossover strategy, and the mutation operator adopts a mutation strategy which displaces an aberrance point with an optimal point in eight-neighbor points of the aberrance point. A quadratic b-spline curve is adopted to smooth an optimal route, and finally, a smooth optimal route is generated. According to the method, the route planning capability of the mobile robot under a complex dynamic environment is effectively improved.

The invention discloses an autonomous mobile fire-fighting robot capable of automatic detection and fire extinguishment, and a control method thereof. The autonomous mobile fire-fighting robot comprises a robot body, wherein a mobile chassis and an image-video acquisition module are arranged on the robot body, the front, rear, left and right parts of the mobile chassis are provided with wheels, a control system is arranged inside the robot body, the control system comprises a fire extinguishing system, an inertial navigation module, a laser navigation module, a core controller, a data storage module, a power supply module, a sensor unit, a video processing module, a motion control unit and an intelligent instrument, and the core controller is connected with the fire extinguishing system, the inertial navigation module, the laser navigation module, the data storage module, the sensor unit, the video processing module and the motion control unit. The control method of the autonomous mobile fire-fighting robot realizes autonomous starting and autonomous moving functions, is used for detecting temperature, sparks and fire situations in real time during the patrol process, and implements the autonomous fire extinguishing function immediately once a fire is discovered.

The invention provides a combined navigation method applicable to an unmanned aerial vehicle in a glide landing stage, and aims to provide a combined navigation method which is low in cost and simple in engineering implementation. According to the technical scheme, the method comprises the following steps of: (1) in an airport for glide test or flying, inputting a precise positioning measurement data point serving as reference data into calculation software of a differential global positioning system (GPS) ground station; (2) when an onboard differential GPS antenna receives GPS signals of three or more satellites, intersecting a position information coordinate of the unmanned aerial vehicle by the onboard differential GPS antenna, correcting the coordinate information of the unmanned aerial vehicle, which is measured by the onboard differential GPS antenna in real time, according to pseudo-range information emitted by the differential GPS ground station in real time, and eliminating a common error; and (3) sending the corrected coordinate information of the real-time position of the unmanned aerial vehicle to an independent inertia navigation system on an airplane through an RS232 signal, correcting state data such as the position, the speed and the attitude angle of the airplane, which are measured by the inertia navigation system in real time, by the inertia navigation system, sending the precise position information to a flying control computer through RS422, and performing precise control over glide landing of the airplane.

Systems and methods are disclosed herein to use a vehicle back-up camera as a cost-effective dead-reckoning sensor in satellite-based vehicle navigation systems. Since the back-up camera may already use a display of the navigation system for display, the data from the back-up camera may be easily obtained and integrated into the navigation system. The data from the camera is received by a navigation receiver wirelessly or through a wired connection. The image is processed to determine the speed, heading, turn-rate of the vehicle to aid the satellite-based navigation system if the satellite signals are inadequate. Thus, enhanced vehicle navigation- performance can be obtained without adding new sensors and/or connecting to a vehicle data bus.

The invention discloses an agricultural unmanned aircraft controlled by a Beidou satellite and a GPS (global positioning system). The agricultural unmanned aircraft comprises an aircraft body and a ground control system, wherein the ground control system comprises a task planning and control station, a power supply cart and an antenna system; the aircraft body comprises an airplane body, a propelling device, a chemical spraying device, a flight manipulating device, a power supply system, an airplane-borne navigation device and a flight data terminal; the task planning and control station comprises a task planning device, a control and display control platform, an image and remote measuring facility, a computer, a signal processor, a ground data terminal and a communication device; the airplane-borne navigation device comprises a GPS receiver, a Beidou receiver and a navigation control system; the GPS receiver comprises a GPS receiver antenna unit, a GPS receiver host unit and a power supply; the Beidou receiver comprises a receiving antenna, a transmitter and a Beidou receiver host unit; the navigation control system is used for preprocessing the GPS navigation information and Beidou navigation information and uniformly changing a coordinate system and a datum point.

The invention provides a spectrum red shift antimonous navigation method for spacecraft. The method includes: directly using solar celestial bodies as light emitters in the solar system; allowing a spacecraft to receive spectral information by spacecraft-carrying spectrum red shift measurement sensors; acquiring speed parameter of the spacecraft according to spectrum red shift measured parameters and spacecraft attitude information measured by spacecraft starlight sensors; and acquiring location parameters of the spacecraft by integration. The principle of the method is simple, the method is novel and is new breakthrough in spacecraft autonomous navigation methods, the means of spacecraft navigation is expanded, navigation capacity is increased, and true autonomous spacecraft navigation is realized. The method is directly applicable to autonomous navigation tasks for deep space exploration in China, has promising application prospect in the field of deep space exploration, and provides references for antimonous navigation in near-earth spacecraft.

The invention discloses a zero-velocity/course correction application online calibrating method for optical fiber strapdown inertial measuring unit, and belongs to the field of inertial technology. A carrier erection two-position aligning process is utilized sufficiently, main error sources including drift errors, scale errors, mounting errors and the like of the optical fiber inertial measuring unit are calibrated by a filtering method on the basis of zero-velocity correction and heading correction, and the actual use precision of the optical fiber inertial measuring unit is improved. Output data of an optical fiber gyro and output data of a quartz accelerometer are acquired by determining parameters of the initial position of a carrier; the gesture of the carrier is determined by means of coarse alignment; and online calibration is realized by precise alignment for a horizontal position and a vertical position. The method is used for calibrating main error items of the optical fiber inertial measuring unit, so that the parameter identification precision of a system and an actual navigation performance of the optical fiber strapdown inertial measuring unit are improved.

The invention relates to an AUV navigation method based on sonar-assisted autonomous navigation, belongs to the technical field of seabed detection, and mainly solves the problem that the ideal detection track of a conventional mapping system is different from an actual value. According to the method, by utilizing an strategy that iSAM (incremental Smoothing and Mapping) algorithm runs at a constant term step number, an object region is partitioned, so that AUV at a local mapping region makes an intelligentized decision on choices of going on exploring unknown regions or performing return visit on the previous seabed environment, two competition appeals about seabed navigation performance and object-region covering rate are both considered, and a feasible plan is provided for solving the key technology problem about position error accumulation when seabed kinetic observation is performed.

The invention discloses a ship navigation radar system and a ship navigation method, which solve the problem of unfavorable navigation effect of a radar in the prior art. The ship navigation radar system comprises an analog-to-digital conversion module, a coordinate transformation module and a superposition output module, wherein the analog-to-digital conversion module is used for converting an analog-quantity video signal collected by a radar into a digital-quantity radar image signal; the coordinate transformation module is used for carrying out the coordinate transformation of the digital-quantity radar image signal to obtain a signal of a radar image in a plane rectangular coordinate system; and the superposition output module is used for superposing and outputting the signal of the radar image in the plane rectangular coordinate system and information of an electronic chart.

The invention discloses a distributive navigation unit based on inertia network and an information fusion method thereof, belonging to the technical field of inertia navigation location. The distributive navigation unit is of a network topology structure consisting of n inertia network nodes, wherein n is a natural number larger than or equal to 2. The information fusion method comprises the following steps of: obtaining inertia sensor information through a data acquisition unit, obtaining a rotation transformation matrix through a rotation transformation matrix calculation and updating unit, carrying out distributive inertia measurement fusion treatment on measurement information of SRIMU to obtain local inertia state vectors, and carrying out distributive navigation state fusion treatment according to the inertial state vectors, as well as inertia measurement information of other nodes and the same type of local navigation states of other nodes so as to obtain local navigation state estimation with higher performance. The distributive navigation unit based on inertia network and the information fusion method can not only meet requirements of a high-performance navigation system, but also can provide accurate local inertia information and are applied to stabilization and compensation of local movement.

The invention provides an AR-based navigation method and device, an electronic device and a medium. The method comprises the steps that a 3D live-action image is displayed on an AR scene; map route information to be navigated is determined in the displayed 3D live-action image; at least one target place is determined according to the map route information; a preset navigation control is configuredat each target place for navigation. By adopting the AR-based navigation method, the 3D live-action image of the current scene to be navigated can be displayed on the AR scene, more visual navigationimpressions are brought to a user, and a navigation effect is improved.

The invention provides a navigation method and terminal. The navigation method includes the steps of receiving a Beidou satellite navigation signal, receiving internal radio frequency and base band chip data, and obtaining Beidou satellite navigation preprocessed data after position, speed and time resolving processing; obtaining external observation information and original inertia measurement data; calculating error data according to the external observation information and the original inertia measurement data, wherein the external observation information includes the temperature and the starting time; resolving the original inertia measurement data with a strapdown inertial navigation algorithm to obtain the resolving result; carrying out combined navigation filtering according to the Beidou satellite navigation preprocessed data, the error data and the resolving result, and outputting the filtering result. By means of the navigation method and terminal, satellite navigation and inertia navigation are organically combined, and the navigation accuracy and the navigation reliability which are superior to the navigation accuracy and the navigation reliability of any single navigation system are achieved.

The invention provides a multi-sensor information fusion method for a mobile robot based on a UKF (Unscented Kalman Filter). The method comprises the following processing steps that milemeter locating information and electronic compass azimuth information of the mobile robot are filtered to obtain robot local rough azimuth information L; WLAN (Wireless Local Area Network) locating information is processed by adopting a trilateration locating method to obtain a robot preliminary overall locating coordinate W; the W and the L are subjected to coordinate transformation to obtain overall azimuth information WL; RFID (Radio Frequency Identification) locating information is processed by adopting the trilateration locating method to obtain locating information, and the locating information is subjected to data layer filtering to obtain overall locating information R; the ultrasonic locating information is filtered to obtain barrier local azimuth information Z; and the W, the L, the R and the Z are subjected to total information fusion to obtain robot and barrier overall accurate azimuth information. According to the method, the independent locating accuracy of the mobile robot can be improved significantly, and the anti-interference independent locating capability and the navigation capability of the mobile robot can be improved.

The embodiment of the invention discloses a method and a device for traffic information navigation. The navigation method comprises the following steps of: determining a navigation path set displayed by a navigation map; and displaying traffic information on navigation paths in the navigation path set, wherein the traffic information comprises at least one of road condition information and traffic event information. According to the method and the device for the traffic information navigation, when a user requires traffic information on the paths, the traffic information is displayed according to the navigation paths displayed by the navigation map, and the navigation effect is improved.

A webpage presentation method for a mobile phone having a limited screen size is provided for efficiently presenting webpages. A webpage presentation of the present invention includes presenting a preset number of webpages including a current and previously visited webpages on a display screen in response to a zoom-out command input during a web browsing session, thereby facilitating search for interested information and improving usability of web browsing function of a handheld device.

The invention relates to a layout optimization method of a planet navigation orbiter based on a prediction track, belonging to the technical field of deep space detection. The layout optimization method provided by the invention has the advantages that a dynamic moving track of a navigation orbiter and a detector in an inlet section in a process that the initial layout of the planet navigation orbiter is optimized is considered, the observability of a Fisher information matrix derivation navigation system is utilized for representing a navigation property, the initial layout of the planet navigation orbiter is optimized based on the integral of the observability to a navigation system, the maximization of the observability of the navigation system is realized, the estimated accuracy of the state when a detector enters is improved, and the optimum of a navigation property is guaranteed.

The invention provides a navigation method for a virtual object in a game and electronic equipment. The method comprises the steps of: in response to a target point setting operation for a virtual object in a game scene, determining a starting point and an ending point corresponding to the virtual object; by starting from a node where the starting point is located, executing a way-finding algorithm on the grid nodes of a walkable area in the game scene to obtain a target node group from the starting point to the ending point; determining a navigation path based on the target node group; and controlling the virtual object to move to the ending point according to the navigation path. In the mode, the grid size of the leaf nodes of the walkable area is large, the problem that grid storage space consumption corresponding to a wide walkable area is large is effectively solved, the grid size of the leaf nodes of an obstacle area is small, accurate positioning of the obstacle area is guaranteed, the way of determining the path points through the path searching operation can ensure that the searched navigation path is more optimal, and the navigation effect of the virtual object is effectively improved.

The invention provides a community security and protection unmanned plane, and the security and protection unmanned plane is characterized in that the security and protection unmanned plane comprises an unmanned plane and an intelligent lifting platform for mounting the unmanned plane; the intelligent lifting platform mounts a brand-new proton exchange membrane fuel cell for charging the unmanned plane landing on the intelligent lifting platform; the unmanned plane employs a visual method for navigation in a flying process. The unmanned plane is good in practicality, and can carry out the modification of conventional equipment. The unmanned plane and an intelligent vehicle cooperate with each other for work. A vehicle-mounted large-capacity fuel cell is used for charging the unmanned plane landing on the vehicle-mounted large-capacity fuel cell, thereby ironing out the defect that a lithium battery of the unmanned plane is not sufficient in power. The endurance of the unmanned plane will be greatly improved through the moving lifting platform cooperating with the unmanned plane. The designed new-generation unmanned plane greatly improves the endurance and navigation performances for the security and protection of a community, and is remarkable in application prospect of security and protection of communities.