60results about How to "Improve situational awareness" patented technology

A method for planning or updating a travel route for a vehicle based on a potential affect of environmental conditions on a particular vehicle and displaying environmental conditions information on a display.

The invention discloses a sensor module of an automatic driving system, an automatic driving system and an automatic driving method. The sensor module comprises a front camera, a rear camera, a millimeter-wave radar group and an ultrasonic-wave radar group, and is characterized in that the front camera is used for recognizing lane lines, traffic marking lines, traffic signs and obstacles in front of a vehicle; the rear camera is used for recognizing lane lines and obstacles in rear of the vehicle; the millimeter-wave radar group comprises a plurality of short-range millimeter-wave radars and one or more middle-range millimeter-wave radars, the short-range millimeter-wave radars can cover all areas around the vehicle within 360 degrees and are used for detecting obstacles within the coverage scope and judging the position and the speed of the obstacles, and the middle-range millimeter-wave radars are used for detecting obstacles in front of the vehicle and judging the position and the speed of the obstacles; and the ultrasonic-wave radar group comprises a plurality of ultrasonic-wave radars, can cover all areas around the vehicle within 360 degrees and are used for detecting obstacles. The sensor module disclosed by the invention improves the reliability of the automatic driving system and reduces the security risk.

An imaging and display system provides helicopter pilots with an unobstructed display of a landing area in a brownout or whiteout condition by capturing a high resolution image of the landing area prior to obscuration. Using inertial navigation information from the aircraft or an independent system, the system transforms the image to a desired viewpoint and overlays a representation of the helicopter's current position relative to the landing area. The system thus greatly improves orientation and situational awareness, permitting safe and effective operation under zero visibility brownout conditions.

The invention is a curve control system for an automobile self-adaptive cruise control system, comprising a data acquisition module for acquiring the signals of each sensor from the CAN bus of the automobile in real time; Whether it is in the state of entering a curve; the road curvature calculation module of the vehicle's driving trajectory, used to calculate the road curvature of the vehicle's driving trajectory; the effective target screening module, used to filter the effective targets ahead; the maximum cornering speed calculation module of the vehicle , which is used to calculate the maximum cornering speed that the vehicle can reach through the curve under the turning radius of the vehicle; the vehicle speed control module is used to make reasonable control of the vehicle according to the driving conditions of the vehicle, and improve the adaptive cruise control system. Environmental awareness in cornering conditions.

A hostile intention assessment system and method wherein a tracking sensor subsystem (e.g., radar) tracks targets relative to a critical asset. Determinations are made to assess if a first target is approaching a second target, and to assess if the second target is approaching the critical asset. If the first target is approaching the second target to hide in the radar shadow thereof and the second target is approaching sufficiently close to the critical asset, an alert is generated.

The invention discloses an environment sensing system and method based on a coordinated USV group. The environment sensing system comprises single-vessel sensing modules, a coordinated control system, wireless communication modules, GPS / IMU modules and single-vessel control modules. Each single-vessel sensing module comprises a camera and a laser radar, the laser radar obtains position and motion information of an object, and the camera identifies the object. The coordinated control system comprises a coordinated control unit and a coordinated sensing unit, the coordinated control unit carries out a coordinated control algorithm to command motion of the USV group, and the coordinated sensing unit coordinates states of the single-vessel sensing modules. The wireless communication modules upload state information and environment sensing information of vessels to the coordinated control system, and also transmits instructions of the coordinated control system. Each GPS / IMU module obtains position and attitude information of the corresponding vessel, and assists in normal operation of other systems. The environment sensing system is reasonable in design, high in system hierarchy, and is easy to realize in the aspects of hardware and software.

The embodiment of the invention provides an intelligent visual ship perception system based on a cloud platform and a data processing method. The system comprises an information acquisition module, afirst information sending module, a local cloud platform data fusion processing module; a second information sending module and an information visualization module, Video information and AIS information acquired by the information acquisition module are sent to the local cloud platform data fusion processing module through the first information sending module. The local cloud platform data fusionprocessing module can carry out target ship identification and target ship and ship AIS information matching tracking on ship operation video information so as to obtain matched target ship information, and the matched target ship information is sent to the information visualization module through the second information sending module to be displayed. According to the invention, the method achieves the accurate perception of the actual state of the ship, and improves the recognition and matching accuracy.

A device for displaying the number of rounds remaining in a firearm magazine is disclosed. The device may include a digital counter with a voltage source. A voltage may flow from the from the digital counter, through a magazine connection, and to a follower conductor in the magazine. The follower conductor may contact binary coded conductive strips, which may return a binary representation of the number of rounds in the magazine to the digital counter.

The invention provides an obstacle type recognition method and device and an electronic device, and relates to the technical field of automatic driving. The method comprises the following steps of acquiring the detection data of a radar in a vehicle; judging whether an obstacle exists in front of the vehicle according to the detection data of the radar; if it is detected that the obstacle exists in front of the vehicle, tracking the detection data of the obstacle to generate the tracking information of the obstacle; and performing identification processing on the tracking information by usinga target classification model to determine the type of the obstacle. Therefore, through the obstacle type identification method, the virtual obstacle in the detection result is effectively filtered, and the detection precision of the radar and the overall environment perception capability of the automatic driving vehicle are improved.

The invention discloses a road-vehicle coordination high-precision sensing method based on 5G. Transverse and longitudinal distance measurement of a target vehicle on a road is realized through roadside equipment; GPS information of the vehicle is obtained, the position of the target vehicle is converted into the GPS information through coordinates so as to be output, and therefore accurate positioning of the vehicle is achieved. According to the technical scheme, the problem that a satellite is easily shielded by high-rises in an urban road is solved, and the requirement for an automatic driving function is met; the limitation of single vehilce perception is broken through, and more comprehensive operation environment information is obtained.

A low-power consumption, talk-through system comprising: a headset worn by a user on his head, the headset further comprising: an array of at least 2 sets of 2 ambient sound microphones, each set positionable on each side of the head; a signal processing subsystem adapted to process respective electrical signals from the microphones and to provide respective outputs having acoustical source distance and intensity information; at least 4 acoustical output devices connectable to the signal processing subsystem, the respective acoustical output devices driven by the respective outputs of signal processing subsystem; and no on-board power source, wherein the user is provided with enhanced situational awareness and near human sound localization by the system.

The invention discloses a multi-sensor target fusion method and device, a vehicle and a storage medium. The method comprises the following steps: acquiring original radar signals acquired by a plurality of forward millimeter wave radars and original camera signals acquired by a camera, wherein the forward millimeter wave radars and the camera are arranged in front of a vehicle; comparing the original radar signal with the original camera signal, and screening out a radar matching signal and a camera matching signal matched with a target; and fusing the radar matching signal and the camera matching signal, and outputting target fusion information. The problem that the vehicle cannot correctly judge the surrounding environment condition due to redundancy and contradiction of different information collected by multiple sensors on the vehicle is solved, complementation and fusion of the information collected by the multiple sensors of the vehicle are achieved, the environmental perceptioncapacity of the vehicle is improved, and correct response can be made accurately in real time in a complex environment.

The invention relates to a distributed sound source detection method and a sound detection robot based on the method. Compared with a traditional single-robot sound source detection system, a distributed sound source localization technology-based multi-robot cooperative sound source detection system has the advantages of large detection range, high detection accuracy, high environmental adaptability, fault-tolerance and the like and can be adopted as a new group robot environment sensing means. Thus, the environment sensing capability of the robot can be greatly improved, and a solid foundation can be laid for the formation and cooperation of intelligent robots.

The embodiment of the invention provides a point cloud data processing method. The method comprises steps: point cloud data are obtained, wherein the point cloud data comprise position information ofa plurality of sampling points; a reference surface is divided into a plurality of grids, and sampling points corresponding to the grids are determined, wherein the reference surface is a plane whichis not parallel to the gravity direction, and the sampling points corresponding to the grids are all sampling points of which the orthographic projections are located in the grids; an effective pointcorresponding to each grid is determined, wherein the effective points corresponding to the grids are at most one sampling point with the maximum height larger than a first threshold value in the sampling points corresponding to the grids, and the heights are increased in the direction deviating from the gravity; and an environment corresponding to the point cloud data is determined based on the position information of each effective point. The embodiment of the invention further provides a point cloud data processing device, a vehicle, electronic equipment and a computer readable medium.

The present invention discloses a parking method, device and system. The parking method comprises the steps that a parking auxiliary controller generates an expected parking trajectory of a vehicle and controls the vehicle to travel along the expected parking trajectory; a parking auxiliary system obtains first detection information in real time and transmits the first detection information to the parking auxiliary controller; the parking auxiliary controller calculates first collision reference information according to the first detection information; a detection system obtains second detection information in real time and transmits the second detection information to a detection controller; the detection controller obtains second collision reference information according to the second detection information in real time and sends the second collision reference information to the parking auxiliary controller; and the parking auxiliary controller controls the vehicle according to the first collision reference information and the second collision reference information. According to the parking method, the detection range of the parking auxiliary system can be expanded, and the load of all the controllers can be reasonably distributed.

The invention discloses an unmanned intelligent sweeper trajectory tracking control method and system, which are mainly used for trajectory tracking of an intelligent sweeper on an input map. The method comprise the following steps: giving an expected driving path; acquiring actual position and attitude information of the vehicle, and establishing a kinematic model of the vehicle; on the expectedpath, selecting an appropriate preview point in real time, and calculating a preview angle; establishing a steering dynamic linearization data model only related to the input preview deviation angle and the output front wheel rotation angle; calculating a steering angle control rate, adding a time-varying proportion control item, and establishing a new steering angle control rate; and outputting afront wheel rotation angle and tracking an expected track. The invention relates to an MFAC trajectory tracking method added with a time-varying proportional control item. Only the I / O data of the system is utilized, the model information of the vehicle is not included, the limitations that the unmanned vehicle is difficult to model and the system information is uncertain are avoided, the improved steering control rate plays a role in preview angle change and reference input change, and the tracking speed and the system flexibility are improved.

The invention belongs to the unmanned aerial vehicle technical field and relates to a monocular optical flow-based potential obstacle detection method. According to the method, an unmanned aerial vehicle is adopted to carry a sensor; an optical flow detection environment is simplified through a global adaptive iterative threshold and a frame difference method; the accuracy and real-time performance of target detection and tracking are improved through a pyramid model optical flow algorithm; a relative distance between the unmanned aerial vehicle and a detection angular point is estimated through optical flow FOE (Focus Of Expansion) and optical flow TTC (Time To Contact) calculation formulas. Compared with an existing visual ranging technology, the method of the invention can assist in reducing the number of cameras and saving cost. Compared with a traditional optical flow depth information detection algorithm, the method of the invention can assist in improving ranging accuracy and the environmental perception capacity of the unmanned aerial vehicle in an autonomous line inspection process, and can be widely applied to electric unmanned aerial vehicle line inspection.

The invention discloses a night vision augmented virtual reality head-up display system and method. The system comprises a vehicle driving environment data collection unit, a vehicle calibration data collection unit, a vehicle end information processing unit, a cloud end information processing unit, an experience driving computer and a virtual reality head-up display device. A vehicle-mounted terminal constructs a vehicle surrounding environment 3D model by aggregating information of environment sensing equipment or sensors, positioning equipment and the like installed on a vehicle, and multi-dimensional sensing of the vehicle to the environment is achieved; through the autonomous communication function between the vehicle and the cloud information processing unit and between vehicles, the sensor data sharing function between the vehicle information nodes on the same road section is achieved, and the safety of road traffic is further improved. According to the system, the night vision sensor is additionally arranged, so that the intelligent driving assistance of the vehicle and the environment identification capability of a driver in severe environments such as weak light, strong light, rain, fog, smoke, haze and raised dust are improved, and the driving safety is enhanced.

The invention discloses an obstacle avoidance method based on the combination of Yolo v4 and a Tof algorithm, and the method comprises the following steps: collecting images of a plurality of types ofto-be-recognized obstacle targets, and marking the positions of the obstacle targets in the images and the types of the targets; training the acquired images by using a Yolo v4 neural network; acquiring a scene image of a to-be-avoided path, and identifying an obstacle target and the type thereof in the scene image by utilizing the trained neural network; solving the relative angle of the obstacle target relative to the center of the camera in the horizontal direction; detecting information of each object in the scene environment by using a laser radar; acquiring distance information of an obstacle target based on the relative angle and the information of each object; and according to the type, angle and distance information of the obstacle target, enabling a mobile platform subjected toobstacle avoidance to carry out path planning to realize obstacle avoidance motion. The Yolo v4 neural network and the Tof ranging algorithm are combined, complete obstacle information can be obtained, and effective obstacle avoidance is achieved.

This invention relates to a security process, performing real time checking on vehicle coming at checkpoint, comprising: a collection phase (1, 2, 3) performed in checkpoint vicinity, an analysis phase (4, 5, 6, 7), including a step of assessing (7) similarity or not between a catalog of predetermined risk situations and coming vehicle global situation aggregating together collected vehicle and person and mobile phone information, a result phase (8) including triggering an alert being representative of at least one of alert triggering motive(s) having triggered this alert, a decision phase (9)transmitting said triggered alert to a human being in charge of security at checkpoint who will decide to stop or not said coming vehicle at checkpoint, based on said triggered alert.

Present novel and non-trivial methods for presenting taxi information to a pilot are disclosed. Each method may generate an image data set from taxi information data and navigation reference and object data. A first image data set may be representative of an image in which one or more first location highlighter(s) highlighting the location(s) of one or more raised surface feature(s) appears within an egocentric or exocentric three-dimensional representation of a scene located outside the aircraft. A second image data set may be representative of an image in which one or more unconventional surface feature(s) highlighting the location(s) of one or more raised surface feature(s) appears within an egocentric or exocentric three-dimensional representation of a scene located outside the aircraft. A third image data set may be representative of an image in which one or more unconventional surface feature(s) appears within an airport surface map.

The invention discloses a novel synthetic vision display method, which comprises the following steps of: switching a visual angle based on a ground speed and a drift angle of a helicopter, providing asynthetic vision image taking a course as the visual angle when the helicopter is on the ground, providing a synthetic vision image of a transition visual angle when a take-off climb exceeds a set speed value, and providing a synthetic vision image of a transition visual angle when the speed is continuously increased to exceed an optimal climb speed, providing a synthetic visual image taking theflight path as a visual angle; when the drift angle is too large, switching the synthetic view into a transition view angle and a course view angle; when the speed is reduced to approach, switching toa course visual angle; at the moment, if the flight path angle of the helicopter exceeds the standard approach angle, the display position of the horizontal position indicator descends, and the attitude pitch scale display is wider in range. According to the method, the synthetic visual image with a proper visual angle is displayed according to the ground speed and the drift angle of the helicopter, and the display position and the pitching scale display range of the horizontal position indicator are automatically adjusted according to the flight path angle of the helicopter, so that the flight environment is coordinated with the synthetic visual image.

The invention discloses a deep-sea seabed obstacle identification method based on deep learning, and the method comprises the following steps: calibrating a camera, and obtaining the internal and external parameters of the camera; collecting and preprocessing an image data set, and carrying out mold offline training and evaluating; collecting a submarine topographic image, and measuring the distance from the camera to an obstacle; processing the collected image based on a deep learning semantic segmentation technology, and obtaining feature parameters of the obstacle; fusing the internal and external parameters obtained through calibration and the measured distance parameters through a data fusion module, converting the characteristic parameters of the obstacle into actual parameters of the obstacle, and therefore basic information of the obstacle is obtained. According to the identification method, the deep learning technology, camera calibration, laser ranging and other methods are fused to obtain the actual characteristic parameters of the obstacle, so that the mobile deep sea sampling equipment can carry out driving trafficability analysis, automatic obstacle avoidance and path planning research.

An autonomous driving controller predicts future sensory observations of a distance ranging device of an autonomous or semi-autonomous vehicle having such an autonomous driving controller. In a first step, a sequence of previous sensory observations and a sequence of control actions are received. The sequence of previous sensory observations and the sequence of control actions are then processed with a temporal neural network to generate a sequence of predicted future sensory observations. Finally, the sequence of predicted future sensory observations is output for further use.

The present invention relates to an enhanced electronic diving mask with various image enhancement hardware and software integrated with a diving mask, whereby images may be enhanced to enable a diver to achieve greater visibility and clearer vision while underwater. Notably, the present invention combines techniques that have previously been used in connection with internal patient surgical procedures, so that medical instrument imaging technology used inside the human body may for the first time be used to afford divers clearer vision, more visibility and greater safety.

The invention provides an automatic train unhooking robot and system. The robot comprises a mobile platform and an unhooking platform, the mobile platform is used for controlling movement of the mobile platform, and an environment sensing module is used for acquiring relative position information of the mobile platform and a train. The unhooking platform is arranged on the mobile platform and used for executing train unhooking operation, and a stereoscopic vision module is used for obtaining train coupler information. And a processor is connected with the mobile platform and the unhooking platform and is used for acquiring the information of the environment sensing module and the stereoscopic vision module so as to control the mobile platform to move and control the unhooking operation of the unhooking platform. By installing the environment sensing module and the stereoscopic vision module, the environment sensing capacity of the robot is improved, and the intelligent level of the unhooking robot is greatly improved. The robot has the advantages of being good in action completion effect, high in stability and safety, small in station transformation and easy to maintain, workers can be liberated from high-risk manual unhooking work, and the unhooking work is autonomously completed by the robot.

The invention provides a target following method and system applied to a quadruped bionic robot. The method comprises the steps that an image of the environment where the quadruped bionic robot is located is acquired; a following target is recognized, the position coordinates of the following target are obtained, the obstacle is recognized, the convex hull coordinate information of the obstacle is obtained, and therefore the quadruped robot transversely moves to avoid the obstacle while rotating to follow the tracking target. The quadruped robot can effectively avoid obstacles while tracking people, and the intelligence of interaction between the quadruped robot and the environment is improved. And the environment perception capability of the quadruped robot is well improved.

The invention discloses a virtual three-dimensional landing landmark auxiliary landing method. The method comprises a landing point selection module, a landing area guiding module, a three-dimensionallanding landmark module and a data fusion module. The landing point selection module is used for providing a man-machine interaction interface for autonomously selecting a landing point for a pilot in a landing selection stage; the landing area guiding module is used for providing landing area prompts with obvious vision and landing approach path guiding for pilots in a landing guiding stage; thethree-dimensional landing landmark module is used for providing spatial position reference for a pilot in the landing process in the landing stage; and the data fusion module fuses and displays the laser radar data and the three-dimensional landing landmark in the form of 8 * 8 grids, so that the environmental perception ability of the landing area of the pilot under the condition that the visualclue is limited is enhanced. The method is clear, visual and convenient to understand, and assists in safe landing of the helicopter.