88results about How to "Guaranteed intelligence" patented technology

The invention relates to the technical field of artificial intelligence, and discloses an artificial intelligence calculator, which includes an instruction input unit, the instruction input unit includes a voice input module and a key input module, and the output end of the voice input module is electrically connected to the input end of a signal amplifier , the output end of the signal amplifier is electrically connected to the input end of the voice recognition module, the output end of the voice recognition module is electrically connected to the input end of the A / D converter, and the output end of the A / D converter is electrically connected to the input end of the single-chip microcomputer; The output end of the voice recognition module is electrically connected to the input end of the voice prompt module; the output end of the button input module is electrically connected to the extrusion device. In this artificial intelligence calculator, by setting up a voice input module, users can use a microphone to input data, which can prevent input errors and greatly improve input efficiency compared with manual input, which is convenient for users to input data. input of.

The invention discloses a method for judging the behavior of freshwater cultured fish in a pond to the state of fish culture. The invention uses image processing technology to monitor the behavior of fish schools in real time and can monitor the living conditions of fish at any time. Monitoring to detect changes in the living environment of fish in a timely manner. Once an abnormal phenomenon occurs in the fish school, the abnormal information can be sent to the breeder in a timely manner, effectively avoiding serious economic losses in fish farming. Compared with traditional farming , can not only liberate laborers from heavy work, but also ensure the safety of the production process. At the same time, it can more accurately reflect the living conditions of fish schools, and take effective measures against emergencies in breeding, reduce losses, and improve breeding quality. Yield, the present invention carries out real-time monitoring from different parts of the body of the fish school, which ensures the all-round monitoring of the fish school, and ensures the safety and intelligence of aquaculture.

The invention provides an expressway unmanned vehicle formation method based on multi-agent reinforcement learning, the method regards a vehicle formation problem as a multi-agent cooperation problem, and each vehicle has an independent decision-making capability. The method can achieve flexible formation on the premise of safe and rapid driving, namely, safe obstacle avoidance is achieved when the traffic flow is large while the formation does not need to be kept, and the formation is recovered when the traffic flow is small; an end-to-end mode of directly mapping image input to vehicle control quantity is large in training difficulty due to large action search space, so that a lane changing strategy is learned only by using a multi-agent reinforcement learning method, the accurate control quantity is calculated in combination with an S-T graph trajectory optimization method, so that control constraints are increased, the kinematics principle is respected, safety guarantee is achieved, and human driving habits are met.

The invention provides a mixed type double-layer optical intelligent sensor network with bidirectional expandability. The mixed type double-layer optical intelligent sensor network comprises a double-layer structure including a terminal node layer and a sensor network layer. The terminal node layer produces a modulating signal and generates spectrum, conducts wavelength conversion and broadens the spectrum, decodes an optical code diversion multiple access signal, demodulates and displays in real time. The sensor network layer comprises n sensor network sublayers, codes the optical code diversion multiple access signal, returns to a wavelength router, and then transmits to a receiver. Separated type and distributed type sensor units or sensors in the sensor network sublayers are mixed and networked. The wavelength router is increased and the number of the sublayers is expanded longitudinally; various topological structures are selected by the sensor units or the sensors so as to achieve expansion of the sensor units or the sensors and have the bidirectional expandability. A mixed type double-layer network coordinates and works, and demodulation information is displayed on a computer in real time. A threshold value is set, and if a demodulation valve reaches the threshold value, alarm is conducted. Meanwhile, the mixed type double-layer optical intelligent sensor network can be connected to other terminal equipment to remind operators of removing hidden danger and nip in the bud.

The invention discloses a smart home wardrobe, which comprises a base, a sleeve is arranged on the top surface of the base, a bottom plate is matched with the top of the sleeve, a controller is arranged inside the sleeve and on the top surface of the base, and one end of the controller runs through the sleeve. and extend to the outside of the sleeve, a power supply is provided on the side of the controller and inside the sleeve, a first rotating shaft is arranged between the power supply and the controller and on the top surface of the base, and on the side of the first rotating shaft is located on the top surface of the base A first motor is provided, a first gear is provided on the output shaft of the first motor, a second gear meshes with the first gear, the second gear is arranged on the first rotating shaft, the top of the first rotating shaft is fixedly connected to the bottom surface of the base plate, and the base plate A top cover is arranged on the top, and the top cover and the bottom plate are connected by two symmetrical fixed columns, and side plates are symmetrically arranged on both sides of the two fixed columns. The beneficial effects of the present invention are: the wardrobe is intelligent, simple and practical, can help users store or fetch clothes quickly and neatly, and is suitable for popularization.

The invention belongs to the fields of industrial robots, intelligent control, and edge computing, and discloses an edge computing-based intelligent control system, method, and device for a manipulator, aiming at realizing low-latency, high-security intelligent control of the manipulator. The system includes robotic arms, sensors, central cloud, edge cloud, and edge nodes; the central cloud is equipped with an algorithm file library; the edge cloud obtains the corresponding algorithm files from the central cloud to configure the algorithm program, and obtains the control law model based on the training data. Or construct a 3D model of a virtual scene based on industrial site images; edge nodes obtain sensor information and send it to the edge cloud for calculation; based on the deployed control law, calculate the control amount of the robotic arm. The present invention uses the edge cloud as the core processing platform, cooperates with the central cloud and the device end, and realizes the low-latency, high-security intelligent control of the industrial robot arm on the edge side of the factory.

The invention discloses an ROV remote communication system. Including surface controller, surface communication module, surface control module, underwater communication module, ROV depth information detection module, ROV attitude information detection module, ROV thruster status detection module, ROV components detection module, ROV thruster execution module, ROV The operating system execution module and ROV camera and lighting control module, the system can upload the underwater ROV system detection signal and the status of each component in real time according to the working needs of the ROV system, and at the same time ensure that the water surface control commands are sent to the underwater execution system in real time. The invention has the advantages of high reliability and good real-time performance.