Abstract: This disclosure provides a cooperative path planning method and device for automatic control aerocraft and aerocraft system. The method includes: determining the current evaluation index of each selected point according to its current position, the target position of the aerocraft and the position of obstacles in the selected area; updating the adjustment displacement of each selected point according to its adjustment displacement, current position and historical optimal position, as well as the global optimal position; updating the current position of each selected point according to its current position and the updated adjustment displacement; after the current position is updated for a set number of times, selecting the position corresponding to the optimal evaluation index from the current positions and global optimal position of all selected points as the next waypoint of the aerocraft.

Abstract: The present disclosure provides a dense crowd counting method and an apparatus, including: acquiring an image to be detected, where the image to be detected includes images of people; feeding the image to be detected into a convolutional neural network model to obtain a crowd density map of the image to be detected; and determining the number of the images of people in the image to be detected according to the crowd density map. Feature information of an image to be detected may be fully extracted through the above mentioned process, thereby realizing a better performance of crowd counting and density estimation, providing great convenience for subsequent security monitoring, crowd control and other applications.

Abstract: Provided are a network selection method and an apparatus for integrated cellular and drone-cell networks, where the method includes: acquiring a dynamic network model and a dynamic user model, generating a random event vector according to the dynamic network model and the dynamic user model; generating an action vector according to the random event vector; obtaining an individual utility of each user according to the action vector and the random event vector; constructing a first selection model; obtaining the value of the action probability according the first selection model to determine networks that the users choose to access according to the value of the action probability.

Abstract: The invention provides a vectorized representation method of a software source code. The vectorized representation method is an AST-based neural network which is a hierarchical vector representation method comprising the following implementation steps: step 1-1, converting an original software source code into an AST at the lowest layer, and then further dividing the AST according to source code statements to acquire a smaller statement tree sequence, wherein statement trees in the statement tree sequence are different in sequence, and the statement tree sequence is consistent with an original statement sequence; step 1-2, encoding the statement trees into statement vectors e1, e2, . . .

Abstract: This application provides an airspace complexity evaluation method based on deep unsupervised learning for air traffic management, which includes the following parts. A stacked autoencoder is used to establish an airspace complexity evaluation model. Input the airspace complexity factors into the stacked autoencoder to obtain the low-dimensional embedded representations of the airspace complexity factors. Cluster the low-dimensional embedded points to capture the centroids of the airspace complexity data. The application utilizes the soft assignment distribution and real assignment distribution of the embedded representations to construct a training loss function which optimizes the airspace complexity evaluation model by gradient descent algorithm. The trained airspace complexity evaluation model and the three obtained cluster centroids describing the airspace complexity level are used to evaluate the current airspace complexity.

Abstract: A GBAS integrity risk allocation system based on key satellites is used to perform a GBAS integrity risk allocation method, including: reading data from an ephemeris at a certain time, and determining numbers of key satellites, key satellite pairs and key satellite groups at a certain time; under H2 hypothesis, allocating the integrity risks by using the fault probability of satellites in key satellite pairs or key satellite groups, where the integrity risks allocated by using the fault probability of satellites in key satellite pairs or key satellite groups include integrity risks caused by dual-receiver fault and integrity risks caused by ranging source fault; under H0 and H1 hypotheses, allocating the integrity risks by using the fault probability of non-key satellites; making an integrity allocation table according to the integrity risk allocation under the H0, H1 and H2 hypotheses.

Abstract: A power supply and distribution device for solar-powered aircraft includes at least two power supply and distribution sub-systems having same configurations. A disconnection of an electrical connection between a plurality of components of each power supply and distribution sub-system can be controlled through a first switch. An electrical connection between the same components of the power supply and distribution sub-systems can be established by controlling a second switch. The power supply and distribution device for solar-powered aircraft has a centralized-distribution design. Specifically, each power supply and distribution sub-system is designed in a centralized mounting manner and has separated power supply and power distribution functions that can work separately.

Abstract: The present invention provides a BeiDou-based grid augmentation autonomous driving multi-level warning system comprising a Beidou Satellite Ground-based Augmentation system, user terminals and a Vehicles internet system, wherein the Beidou Satellite Ground-based Augmentation system comprises Beidou grid reference stations, a data processing system and a data broadcast system; the user terminal comprises an in-vehicle receiver and a calculating chips. The present invention can reduce the occurrence of traffic accidents and reduce the loss of life and property.

Abstract: An acceleration sensor with differential graphene resonant beams comprises a substrate (1), a sensitive mass plate (2), a first insulating layer (3), a second insulating layer (4), a first excitation electrode pair (1), a first graphene resonant beam (6), a second graphene resonant beam (7), a third insulating layer (8), a second excitation electrode pair (9), and a vacuum cover (10). An indirect acceleration-sensitive mode is adopted, so that the sensitive mass block directly senses acceleration to be measured, and converts the acceleration to be measured into a concentrated force to cause axial displacement of the sensitive mass block and then to cause a change in the axial stress of the graphene resonate beams, thereby causing a change in the resonant frequency of the beams. By measuring the resonant frequency of the beams, acceleration can be measured.

Abstract: An ultrasonic peening-type integrated machining method for cutting and extrusion includes: applying transverse ultrasonic vibration or a vibration component, which is vertical to a cutting speed direction to a cutting tool on a machine tool; setting a cutting parameter and an ultrasonic vibration parameter such that a dynamic negative clearance angle is generated in a cutting procedure and a flank face of the cutting tool conducts ultrasonic peening extrusion on the surface of the workpiece; setting an extrusion overlap ratio; setting a wear standard of flank faces extruded by the cutting tool; controlling a vibration cutting trajectory phase difference of the cutting tool during two adjacent rotations; and turning on the machine tool in order to ensure that cutting and surface extrusion strengthening of the workpiece are completed in one procedure without separate strengthening procedures. The method conducts extrusion strengthening on the surface of the workpiece while cutting the workpiece.

Abstract: Disclosed is an aircraft environmental control and fuel tank inerting coupling system based on a membrane separation method. The dehumidification of gas in an aircraft environmental control system and the separation of oxygen and nitrogen in a fuel tank inerting system are realized respectively, based on the selective permeability of a membrane to water vapour/air and oxygen/nitrogen. In the coupling system, part of drying gas passing through a membrane dehumidification heat exchanger (5) enters a membrane air separator (9), and the other part thereof is cooled through a large expansion turbine (8) and then directed into a cockpit for refrigeration; and nitrogen-rich gas generated by the membrane air separator (9) is directed into a fuel tank for inerting. Oxygen-rich gas is mixed with gas supplied by the environmental control system, thus increasing the oxygen content of gas supplied by the aircraft cockpit.

Abstract: A dynamic baseline position domain monitoring system based on satellite navigation and inertial navigation is used to perform a method, including: a) determining a coordinate system and a transformation matrix; b) calculating a theoretical coordinate value of an antenna baseline vector in a earth-centered earth-fixed coordinate system during the movement of a base station carrier; c) determining the number of antenna baseline vectors to be monitored; d) solving the measurement values of the antenna baseline vectors; e) calculating the position domain error of an antenna baseline vector change rate in three directions of x, y and z at epoch k, and normalizing the position domain errors to obtain a normalized value of the position domain errors; f) obtaining the a cumulative sum; g) comparing the cumulative sum with an error monitoring threshold value, and issuing an integrity risk alarm.

Abstract: Embodiments of the present disclosure provide a method and an apparatus for eye movement synthesis, the method including: obtaining eye movement feature data and speech feature data, wherein the eye movement feature data reflects an eye movement behavior, and the speech feature data reflects a voice feature; obtaining a driving model according to the eye movement feature data and the speech feature data, wherein the driving model is configured to indicate an association between the eye movement feature data and the speech feature data; synthesizing an eye movement of a virtual human according to speech input data and the driving model and controlling the virtual human to exhibit the synthesized eye movement. The embodiment makes the virtual human to exhibit an eye movement corresponding to the voice data according to the eye movement feature data and the speech feature data, thereby improving the authenticity in the interaction.

Abstract: Disclosed are a method and apparatus for adaptively constructing a three-dimensional indoor scenario, the method including: establishing an object association map corresponding to different scenario categories according to an annotated indoor layout; selecting a corresponding target indoor object according to room information inputted by a user and the object association map; generating a target indoor layout according to preset room parameters inputted by the user and the annotated indoor layout; and constructing a three-dimensional indoor scenario according to the target indoor object and the target indoor layout. The disclosed method and apparatus help improving the efficiency in constructing the three-dimensional scenario.

Abstract: The present application provides a multi-frame quality enhancement method and device for a lossily compressed video. The method comprises: performing quality enhancement on the i-th frame of a decompressed video stream using m frames correlated with the i-th frame to play the i-th frame with enhanced quality. The m frames are frames in the video stream. The number of the same pixels or corresponding pixels of each of the m frames and the i-th frame is greater than a preset threshold. m is a natural number greater than 1. In an implementation, a non-peak-quality frame positioned between two peak quality frames may be enhanced using the peak quality frames. The method may mitigate the quality fluctuation across a plurality of frames for providing playback of the video stream and may improve the quality of all frames in the video after the lossy compression.

Abstract: A pixel circuit configured to drive a light-emitting element and a driving method therefor, and a display substrate, the pixel circuit comprising: a first switch sub-circuit configured to input, under the control of a first control signal line, a data signal of a data signal line to a first node; a second switch sub-circuit configured to input, under the control of a second control signal line, a first signal of a first signal line to a second node; a driving sub-circuit configured to drive, under the control of the potential of the first node, the light-emitting element to emit light; and a memory sub-circuit configured to store a threshold voltage of the driving sub-circuit before the second switch sub-circuit is turned on in each work cycle of the pixel circuit.

Abstract: The disclosure discloses an ankle prosthesis hydraulic drive circuit for achieving damping control and energy recovery, belonging to the technical field of prosthesiss and orthotic devices. The hydraulic drive circuit particularly includes a motor, a hydraulic pump, a first check valve, a first high-pressure energy accumulator, a three-position four-way valve, an electromagnetic normally-closed valve, a second high-pressure energy accumulator, a single-rod hydraulic cylinder, an electromagnetic normally-opened valve, a low-pressure energy accumulator, a second check valve, an oil inlet line, an oil outlet line, a first line and a second line. The hydraulic drive circuit provided by the disclosure is capable of outputting enough peak power to meet a normal walking demand, and meanwhile actively controlling the damping of the circuit and recycling energy during the walking.

Abstract: A complementary magnetic memory cell includes: a heavy metal film or an antiferromagnetic film, a first magnetic tunnel junction, a second magnetic tunnel junction, a first electrode, a second electrode, a third electrode, a fourth electrode, and a fifth electrode; wherein the first magnetic tunnel junction and the second magnetic tunnel junction are fabricated above the heavy metal film or the antiferromagnetic film; the first electrode, the second electrode and the third electrode are fabricated under the heavy metal film or the antiferromagnetic film; the fourth electrode is fabricated above the first magnetic tunnel junction, and the fifth electrode is fabricated above the second magnetic tunnel junction; to store one bit of data, the first magnetic tunnel junction and the second magnetic tunnel junction are arranged in a pair of complementary resistance states, wherein one magnetic tunnel junction is set to a high resistance state and the other remains unchanged.

Abstract: A computing in-memory system and computing in-memory method based on a skyrmion race memory are provided. The system comprises a circuit architecture of SRM-CIM. The circuit architecture of the SRM-CIM comprises a row decoder, a column decoder, a voltage-driven, a storage array, a modified sensor circuit, a counter Bit-counter and a mode controller. The voltage-driven includes two NMOSs, and the two NMOSs are respectively connected with a selector MUX. The modified sensor circuit compares the resistance between a first node to a second node and a third node to a fourth node by using a pre-charge sense amplifier. The storage array is composed of the skyrmion racetrack memories. The computing in-memory architecture is designed by utilizing the skyrmion racetrack memory, so that storage is realized in the memory, and computing operation can be carried out in the memory.

Abstract: A method is provided for modeling and analyzing a generalized microscopic stress concentration phenomenon on a machined surface.