489 results about "Perception system" patented technology

A situational awareness system includes a first local network having a plurality of digital communication devices, each device capable of gathering information pertinent to an area in proximity of the device and providing information to a control station capable of collaborating the information and provide such information to the devices on the local network; a first regional network having a plurality of local networks, including the first local network, within an area of responsibility, the first regional network having a regional control station capable of collaborating information from the devices and provide said information to devices on the local network; and a central network having a plurality of regional networks including the first regional network, the central network having a central control station capable of collaborating information from the regional control stations and provide the information to devices on a local network.

The illustrative embodiments provide an apparatus for processing sensor data and controlling the movement of a vehicle. In an illustrative embodiment, an operating environment around the vehicle is identified and sensor data is selected from a set of sensors. The movement of the vehicle is controlled based on the operating environment identified. In another illustrative embodiment, a sensor system has some sensors that are more accurate in a particular environment than other sensors. A dynamic condition is identified by the sensor system and commands are sent to the steering system, the propulsion system, and the braking system to move the vehicle using the sensor data detected by the sensor system. The environment is identified using the plurality of different types of sensors on the vehicle.

The invention provides a parking navigation and finding system based on object networking wireless sensing and video perception, comprising a main control computer. The main control computer is connected with a plurality of park control systems with number plate automatic identification and a plurality of integrated LCD displays with players and wireless stall sensors through a network; the wireless stall sensor is installed at each stall; the park control system comprises a number plate identification system, an RFID (Radio Frequency Identification Device) reader-writer and a matched radio frequency identification electronic tag; and the LCD display comprises a navigation screen at the garage entrance and the LCD display arranged on a client forwarding path. The parking navigation and finding system has the advantages of actively informing a related internal part or a common platform of characteristic vehicle information and having a remote maintenance system transmitted through 3G and is a typical object networking perception system. The parking navigation is precise through an object networking wireless perception technique and a number plate identification technique, a vehicle owner finds a stall efficiently and the identity identification is in advance.

The invention discloses an automatic driving system based on enhanced learning and multi-sensor fusion. The system comprises a perception system, a control system and an execution system. The perception system high-efficiently processes a laser radar, a camera and a GPS navigator through a deep learning network so as to realize real time identification and understanding of vehicles, pedestrians, lane lines, traffic signs and signal lamps surrounding a running vehicle. Through an enhanced learning technology, the laser radar and a panorama image are matched and fused so as to form a real-time three-dimensional streetscape map and determination of a driving area. The GPS navigator is combined to realize real-time navigation. The control system adopts an enhanced learning network to process information collected by the perception system, and the people, vehicles and objects of the surrounding vehicles are predicted. According to vehicle body state data, the records of driver actions are paired, a current optimal action selection is made, and the execution system is used to complete execution motion. In the invention, laser radar data and a video are fused, and driving area identification and destination path optimal programming are performed.

The invention discloses an unmanned perception based unmanned aerial vehicle route planning method for rapidly planning the vehicle driving route. According to the invention, based on the unmanned flight perception system, road video images around a target vehicle are photographed by utilizing an unmanned flight to be sent to a ground station; the ground station receives the video images and processes the video images so as to obtain the vehicle and road messages, route planning is carried out according to the vehicle position, and the route is transmitted to the unmanned aerial vehicle; and a computer module of the ground station calculates a flight control signal to control the unmanned aerial vehicle to follow the vehicle to proceed, and corrects the route in real time. According to the invention, based on an unmanned flight platform, the operation state is stable; and the road environment around the vehicle is photographed from a great height, the coverage area is wide, and the observed road traffic information is distinct and clear, so that the road distribution condition and the traffic condition around the target vehicle can be obtained rapidly, the reasonable route planning can be obtained, the route is more precise, and the road condition analysis is more timely and accurate.

Aspects of the disclosure relate generally to maneuvering autonomous vehicles. Specifically, the vehicle may determine the uncertainty in its perception system and use this uncertainty value to make decisions about how to maneuver the vehicle. For example, the perception system may include sensors, object type models, and object motion models, each associated with uncertainties. The sensors may be associated with uncertainties based on the sensor's range, speed, and / or shape of the sensor field. The object type models may be associated with uncertainties, for example, in whether a perceived object is of one type (such as a small car) or another type (such as a bicycle). The object motion models may also be associated with uncertainties, for example, not all objects will move exactly as they are predicted to move. These uncertainties may be used to maneuver the vehicle.

An artificial intelligence (AI) combination platform or orchestration module is described that orchestrates and automates the processes of selecting, building, testing, and delivering new or integrated computer vision, detection, sensor and perception algorithms that can be published or leveraged in near real time by sensors, hardware or applications. The AI combination platform includes one or more of the following engines: algorithm mixer engine, retrospective search engine, algorithm recommendation engine, quality assurance engine, certification engine, and perception engine.

The invention discloses a forward safety monitoring and warning device for an automobile. The forward safety monitoring and warning device comprises a decision-making system, a perception system, a laser radar module, an ultrasonic radar module, a driving system, an intelligent remote control unit, and a man-machine interactive system, wherein the decision-making system syncretises data collected by perception system and processes it according to the decision algorithm, and acquires decision-making data to control the vehicle and control the vehicle to execute the control task; the perception system connected with the decision-making system comprises a differential GPS module used to provide vehicle position information and heading attitude; the laser radar module is used for acquiring barrier information of the front of the automobile; the ultrasonic radar module is used for sensing environmental information around the automobile; the driving system is connected to the decision-making system through an intelligent remote control unit and the intelligent remote control unit is also connected with an actuating mechanism in the bottom of the automobile for controlling the automobile and switching automatic driving mode and traditional mode; the man-machine interactive system is used to display vehicle status, command information, conduct performance and geographic information. The adoption of drive-by-wire chassis and modular design reduces the cost of debugging, improves the efficiency of developing and facilitates expansion.

The invention relates to a sensor and unmanned aerial vehicle intelligent perception control technology, so as to realize the intelligent perception of an unmanned aerial vehicle to the surrounding environment. The system can verify other autonomous localization algorithms and target recognition algorithms to improve the research efficiency of the intelligent perception technology. According to the unmanned aerial vehicle intelligent perception system and method based on multiple sensors, the system comprises a laser radar, an RGB-D visual sensor, an IMU inertial measurement unit, an embedded airborne processor and a flight controller; the laser radar is used to measure the distance information of the surrounding environment; the RGB-D visual sensor collects the distance information and image information of the surrounding environment; the laser radar collects 2D point cloud data, while the RGB-D visual sensor collects 3D point cloud data; the IMU inertial measurement unit is a device which measures the three-axis attitude angle and the acceleration of the device; and the embedded airborne processor comprises two independent modules of autonomous positioning and target recognition. The unmanned aerial vehicle intelligent perception system and method based on multiple sensors are mainly used for unmanned aerial vehicle control.

The invention provides an automatic driving system based on a pure electric logistics vehicle and a control method thereof. The system comprises an automatic driving control system, a human-computer interaction system, an automatic driving system gateway and an execution system. The method comprises the steps that step one, an environment perception system acquires the surrounding environment dataof the vehicle and performs fusion, perceives the surrounding obstacle information and passable area information and also acquires the high precision position information of the vehicle and the roadinformation and then generates a driving situation map according to the primary planning path result planned by the lane level navigation system; step two, an intelligent decision system performs secondary planning of the local driving route in real time according to the driving situation map generated by the environment perception system and decomposes the secondary planning result into the transverse control instruction and the longitudinal control instruction; and step three, the execution system receives the executes the transverse control instruction and the longitudinal control instruction from the intelligent decision system so as to complete full-automatic driving. Automatic driving can be realized and the intelligent level of the complete vehicle can be enhanced.

An electromagnetic type multi-degree of freedom virtual roaming platform comprises a moving platform, a platform tilt actuating mechanism, a platform tilt perception system, two mats, a foot motion perception system, a corresponding flotation structure, a pressure sensor and the like, wherein the moving platform is composed of an array magnetic-driven unit, and the two mats are suspended on the platform and allow a user to directly tread. By means of the virtual reality technology, forward road situations and surrounding panoramic environments are displayed in real time on a helmet displayer or specific glasses of the user, and the user can select and move forward according to the situation. A control system can precisely control the mats so that the mats can bear the feet of the user to equivalently finish walking, running and other motions in the range of the platform, corresponding virtual scenes are changed synchronously according to the specific forwarding situations of the user to achieve the roaming effect. The user can move linearly on site on the platform and can turn left and right, particularly, real ground slope experience can be obtained through proper tilt of the platform.

The invention discloses a crop growth information monitoring system and method based on internet of things. The system comprises an information perception system, a wireless transmission system and anintelligent management system, wherein the information perception system includes a soil moisture content monitoring module, a plant disease and insect pest monitoring module, a crop nutrition statemonitoring module, a weed monitoring module and a crop condition monitoring module. After crop planting, relevant information and threshold values of a crop growth environment are set through an intelligent management system interface, the soil moisture content, diseases and insect pests, nutritional status, weed growth and growth vigor information of growing crops are acquired through the perception system in real time and are sent to a server for data storage, analysis and display, if the information exceed threshold values, workers are remind of corresponding processing, plants are helped to accurately judge the crop growth conditions, real-time effective decision information is provided for accurate operation, the problem is solved that the crop growth conditions in planting field pieces need to be checked regularly in traditional planting process and accordingly the labor intensity is high, the labor cost is reduced, and the operating efficiency and accuracy are improved.

The invention discloses a network security perception system comprising multiple probes respectively deployed on switches or routers of monitoring network areas and used for dynamically obtaining mirror image traffic of the respective monitoring network areas, collecting specific traffic information from the mirror image traffic, and uploading the collected mirror image traffic to an analysis platform through an encrypted communication channel; the analysis platform used for dynamically receiving the traffic information uploaded by the probes, performing multi-dimensional correlation analysisto identify the security threats in the entire network, and displaying an analysis result in a visible manner. The invention further discloses an implementation method of the network security perception system and a computer storage medium. The network security perception system provided by the invention can monitor the entire network in mesh network form in all directions, perceive the potentialsecurity threats in the network and protect the information security in the entire network.

The invention provides a big data acquisition and processing system and an electric vehicle endurance estimation method based on the same; the system includes a vehicle-mounted sensor, a GPS positioning system, a road information perception system, a cloud data receiving system, a data transmission processing system and an online computing system. Real-time road, traffic, weather and other information are obtained from a cloud server, and then a future driving state of an electric vehicle is forecasted based on the data. According to the vehicle real-time data under an actual driving state, a vehicle dynamic model and a battery model obtained from calculation are more accurate than a traditional vehicle dynamic model obtained based on a physical equation in an electric vehicle driving process. The estimation method can improve the estimation accuracy of the remaining endurance mileage of the networking pure electric vehicle to a great extent. In addition, according to the real-time data obtained from the cloud, a vehicle use strategy is better planned, and the control strategy of the electric vehicle is optimized, so as to improve the service life of the electric vehicle.

The invention provides an intelligent traffic behavior perception method and an intelligent traffic behavior perception system based on microwaves. The intelligent traffic behavior perception method comprises the steps of traffic parameter setting, road traffic background learning, road background noise suppression, calculation, coordinate system establishment, vehicle classification, tracking processing and alarm triggering. The beneficial effects are that the method and the system provided by the invention are based on a microwave (millimeter wave) mode, can operate in an all-weather mode, have the advantages of high precision, high reliability, large area detection, high economic benefit cost ratio and simple and convenient installation, and can carry out comprehensive traffic behavior analysis on various types of vehicles in a detection area from multiple dimensions, and meanwhile, background noise suppression is carried out through a two-dimensional radar image method in allusion to a circumstance that the radar performance is affected by an isolation zone, a metal barrier or the like existing on the road.

The technology relates to actively looking for an assigned passenger prior to a vehicle reaching a pickup location. For instance, information identifying the pickup location and client device information for authenticating the assigned passenger is received. Sensor data is received from a perception system of the vehicle identifying objects in an environment of the vehicle. When the vehicle is within a predetermined distance of the pickup location, authenticating a client device using the client device information is attempted. When the client device has been authenticated, the sensor data is used to determine whether a pedestrian is within a first threshold distance of the vehicle. When a pedestrian is determined to be within the first threshold distance of the vehicle, the vehicle is stopped prior to reaching the pickup location, to wait for the pedestrian within the first threshold distance of the vehicle to enter the vehicle.

The invention relates to a humanoid-head robot and a behavior control method thereof, in particular to a humanoid-head robot device with human-computer interaction function and the behavior control method thereof, solving the problems that the prior humanoid-head robot can not completely realize the reproduction of human facial expressions, has limited perceptive function and does not have manual feeling models and the human-computer interaction function. The behavior control method comprises the following steps: a sensor perceptive system outputs perceived information to a main control computer for processing; control system software in a robot behavior control system obtains the relative control quantity of a corresponding motor according to the manual feeling models, executes a motion control instruction to output a PWM pulse by a motion control card to drive the corresponding motor to move to an appointed position and realize the human-computer interaction function and various feeling reactions of a robot; and the sensor perceptive system perceives external feeling signals, recognizes corresponding feeling signals and utilizes the manual feeling models to realize the behavior control of the robot. The invention realizes the reproduction of the human facial expressions and has anthropopathic multi-perception function, such as smell, touch, vision, and the like.

The invention relates to a positioning system, in particular to an indoor positioning system which comprises a radio frequency signal emitter, a controller, an ultrasonic receiver and a microprocessor, wherein the radio frequency signal emitter, the controller and the ultrasonic receiver are respectively and electrically connected with the microprocessor; and wireless communication is adopted between the radio frequency signal emitter and the controller as well as between the controller and the ultrasonic receiver. The system is simple in structure, low in cost and high in positioning precision and can be widely applied to various indoor positioning fields.

The invention discloses a road surface construction robot environment perception system and method based on a multi-source sensor. A camera and a laser radar are arranged on a robot body; an embedded industrial control computer is arranged in the robot body; the embedded industrial control computer is used for obtaining and fusing class information of picture data and distance information of the laser radar based on a data fusion multi-target detection ranging algorithm, then, tracking a target by adopting a particle filter algorithm in the two directions of an image and point cloud, obtaining dynamic estimation change of an obstacle target in continuous time, and finally, obtaining the advancing speed and the motion direction of an obstacle in a construction area through the dynamic estimation change; road surface environment perception on the construction area is realized by drawing a risk graph; therefore, the adaptive capacity of the system for different environments is obviously improved; furthermore, the shielding condition between obstacles has some improvements on multi-target detection and a tracking algorithm; therefore, the effective operation of the construction robot is ensured; and thus, the system and the method have good application prospect.

Aspects of the disclosure relate generally to maneuvering autonomous vehicles. Specifically, the vehicle (101) may determine the uncertainty in its perception system and use this uncertainty value to make decisions about how to maneuver the vehicle. For example, the perception system may include sensors (310-311, 321-323, 330-331), object type models, and object motion models (146), each associated with uncertainties. The sensors may be associated with uncertainties based on the sensor's range, speed, and / or shape of the sensor field (421A-423A, 421B-423B). The object type models may be associated with uncertainties, for example, in whether a perceived object is of one type (such as a small car) or another type (such as a bicycle). The object motion models may also be associated with uncertainties, for example, not all objects will move exactly as they are predicted to move. These uncertainties may be used to maneuver the vehicle.

The invention discloses a method and a system for preventing fraudulent auction in a group intelligent perception system. The method comprises the following steps that each intelligent mobile phone user registers in an auction part platform, and the platform sends all perception task lists and auction modes to the user; each intelligent mobile phone user makes a bid document and submits the bid document to the auction part platform; the platform selects a group of intelligent mobile phone users according to the bid documents submitted by all the intelligent mobile phone users, so that the group of user can finish all the perception tasks, the sum of quoted price is the smallest, and meanwhile, the platform calculates the payment which should be paid to each selected intelligent mobile phone user and informs the selected users of starting executing corresponding perception tasks; each selected intelligent mobile phone user executes the corresponding perception tasks and feeds a result to the platform; the platform pays corresponding payment to each participant user according to the calculated payment. The auction method which can efficiently finish the perception tasks and can prevent cheat is realized.

Technical solutions are described for controlling an automated driving system of a vehicle. An example method includes computing a complexity metric of an upcoming region along a route that the vehicle is traveling along. The method further includes, in response to the complexity metric being below a predetermined low-complexity threshold, determining a trajectory for the vehicle to travel in the upcoming region using a computing system of the vehicle. Further, the method includes in response to the complexity metric being above a predetermined high-complexity threshold, instructing an external computing system to determine the trajectory for the vehicle to travel in the upcoming region. If the trajectory cannot be determined by the external computing system a minimal risk condition maneuver of the vehicle is performed.

The embodiment of the invention discloses an available frequency spectrum determination method and available frequency spectrum determination equipment. By the technical scheme provided by the embodiment of the invention, the bidirectionality of interference between wireless communication systems is taken into account, and when a perception system is required to be introduced, a corresponding frequency point can be determined as an available frequency point only under the condition of ensuring that an authorization system and the perception system meet corresponding coexistence criterions by the corresponding frequency point and other adjacent frequency points thereof, thereby simultaneously ensuring that the introduced perception system may not be interfered by the authorization system and can normally work at the determined available frequency point under the condition of ensuring that the normal work of the authorization system may not be interfered by the perception system to improve the communication quality of the wireless communication system.

The invention relates to a decision planning method for automatic driving of a special vehicle. The method comprises the steps of: 1) an automatic driving operation module obtaining the current position and pose of a vehicle; 2) projecting environment information sent by a perception system to a grid map, and generating an environment map; 3) the automatic driving operation module obtaining a control instruction of a current work executor and issuing the control instruction; 4) the automatic driving operation module obtaining a task reference route, performing trajectory cluster planning combined with vehicle dynamics constraints by a route-speed decomposed trajectory planning method, obtaining a basic trajectory cluster executable by the vehicle, and fusing the basic trajectory cluster and the task reference route to obtain an executable trajectory cluster; and 5) performing safety and high efficiency selection on the planned executable trajectory cluster, and finally generating a high-gain trajectory. According to the decision planning method for the automatic driving of the special vehicle, compared with the prior art, the method has the advantages of improving obstacle avoidance success rate, automatic decision, multi-mode trajectory decision strategy, achieving automatic driving safety and the like.

The invention discloses an intelligent ship environment threat target perception system and method. The system comprises a sensor module, a target recognition module, a comprehensive control unit, a short-distance recognition system judgment module and a target feature database. The sensor module comprises a navigation radar, a GPS / Beidou positioning navigation device, a marine AIS receiver, a small target radar, a high-definition video camera tracking device, a three-dimensional laser radar, a millimeter wave radar and a marine pickup device. According to the invention, the active and passivesensors from far to near configured by the intelligent unmanned ships are reasonably configured, the radar signals, photoelectric signals and audio and video signals are considered simultaneously torealize the threat target perception, identification and tracking functions, and the threat objects can be quickly, accurately and reliably identified. The system and the method have a continuous andimprovable self-learning capability, and along with the collection and enrichment of a target audio and video feature library, the capability and efficiency of threat target perception and target recognition of the intelligent unmanned ships can be continuously improved.

A drop perception system is disclosed that includes an open housing structure having an internal volume, an open top and an open bottom, and a plurality of perception units positioned to capture perception data within the internal volume at a plurality of locations between the open top and the open bottom of the open housing.

The invention provides an obstacle detection method based on information fusing of a laser radar and a CCD camera. The angle resolution of a two-dimensional image of the CCD camera is high, but the distance information of an obstacle cannot be acquired and the angle resolution is easily affected by external illumination and shadows. The laser radar is capable of acquiring distance information of the surrounding environment, wide in scanning range and less effected by external conditions, but the angle resolution is quite low compared with an image. By fusing the image information of the CCD camera and the distance information of the laser radar, the precise size of the shape of the obstacle can be acquired. According to the invention, problems of low precision and poor robustness of a single sensor in detection of obstacles are solved and the requirement for obstacle detection in the current environment perception system can be met.