119 results about "Time trajectory" patented technology

Apparatus and methods are disclosed for use within an image-guided surgical navigation system for the storage and measurement of trajectories for surgical instruments. An icon representing the real-time trajectory of a tracked instrument is overlaid on one or more pre-acquired images of the patient. At the surgeon's command, the navigation system can store multiple trajectories of the instrument and create a static icon representing each saved trajectory for display. The surgeon may also measure a planar angle between any two trajectories. The angle is computed in the plane of the image, and therefore will be computed separately for each image displayed. Furthermore, the surgeon has the option of computing and displaying the three-dimensional distance between two points defined by any two trajectories.

The invention discloses an air traffic control system for four-dimensional (4D)-trajectory-based operation. The air traffic control system comprises a data communication module, a monitoring data fusion module, an airborne terminal module and a control terminal module, wherein the monitoring data fusion module is used for fusing the monitoring data of an air traffic control radar and automatic dependent monitoring data, and providing real-time trajectory information for the control terminal module; and the control terminal module comprises a preflight conflict-free 4D trajectory generation sub-module, an in-flight short-term 4D trajectory generation sub-module, a real-time flight conflict monitoring and alarming sub-module and a flight conflict resolution 4D trajectory optimization sub-module. The invention also discloses an air traffic control method for the system. The control terminal module processes flight plan data, generates 4D trajectories, analyzes potential traffic conflicts of air traffic conditions and provides an optimal resolution scheme. By the system and the method, flight conflicts can be effectively prevented, and the safety of air traffic can be improved.

The invention provides a control method of a human-machine interaction mechanical arm, which relates to a safe control method of a mechanical arm working under an unknown environment and solves the problem that an operator accidentally injured due to failure of the existing mechanical arm to accurately model the working environment when the mechanical arm works in close contact with the operator. A mechanical arm controller of the invention collects a joint position in a real time manner by a joint sensor and transforms the joint position q to a Descartes position x by the positive kinematics, and calculates the real-time trajectory planning xpg which is provided with a feedback of the Descartes force; the mechanical arm controller also collects the torque Tau by the joint sensor in a real time manner, calculates the expected torque Taur by Descartes impedance control, and calculates the input torque Taum of the mechanical arm joint by the dynamic compensation of a motor. The control method can effectively detect the force from each joint of the mechanical arm; when contacting an object, the mechanical arm can carry out a soft contact; when a collision happens, the mechanical arm can ensure that the contact force from each direction is within the range of the expected force, thus ensuring the safety of the mechanical arm and the operator.

The present invention provides computer implemented methodology that permits the safe landing and recovery of rotorcraft following engine failure. With this invention successful autorotations may be performed from well within the unsafe operating area of the height-velocity profile of a helicopter by employing the fast and robust real-time trajectory optimization algorithm that commands control motion through an intuitive pilot display, or directly in the case of autonomous rotorcraft. The algorithm generates optimal trajectories and control commands via the direct-collocation optimization method, solved using a nonlinear programming problem solver. The control inputs computed are collective pitch and aircraft pitch, which are easily tracked and manipulated by the pilot or converted to control actuator commands for automated operation during autorotation in the case of an autonomous rotorcraft. The formulation of the optimal control problem has been carefully tailored so the solutions resemble those of an expert pilot, accounting for the performance limitations of the rotorcraft and safety concerns.

A coupled real time emulation method for positioning and location system includes the steps of receiving real time trajectory data from a 6DOF trajectory generator and generating global positioning system simulated measurements and inertial measurement unit simulated electronic signals which are injected into an on-board integrated global positioning system / inertial measurement unit system. When the on-board integrated global positioning system / inertial measurement unit system is excited in dynamic operation, a performance thereof is able to be tested and evaluated as if carrying a real transportation test.

The invention discloses a multi-target tracking method based on depth track prediction. The method comprises the following steps: constructing a track prediction model based on a long-short time memory network for a multi-target tracking system; using the trajectory data of the real tracking scene to train a trajectory prediction model; constructing conservative short-time trajectory fragments byusing the appearance characteristics of target detection, and calculating the appearance similarity among the trajectory fragments; carrying out depth track prediction on the target on line by using the trained track prediction model, obtaining the motion similarity between track segments, comprehensively considering the appearance similarity and the motion similarity, and setting a network modelof target tracking to complete multi-target tracking. According to the method, a long-short time memory network-based trajectory prediction model is constructed for a multi-target tracking system, andcompared with a traditional method, the method can fully consider the historical trajectory information and scene information of the target, calculate the inter-target motion similarity with better robustness, and further improve the multi-target tracking effect.

The invention relates to a genetic-algorithm-based trajectory planning optimization method for a mobile mechanical arm. According to the technical scheme, the method comprises the following steps of first establishing a forward kinematic model and an inverse kinematic model of a multi-degree-of-freedom mobile mechanical arm; then fitting a joint trajectory by adopting a composite curve of a quartic polynomial mathematical model and a quintic polynomial mathematical model, and calculating solutions of the corresponding mathematical models according to a linear constraint equation; next selecting a trajectory optimization target according to the principles of shortest motion time, minimum spatial motion distance and less than or equal to maximum set joint torque of the mobile mechanical arm; and finally globally optimizing the optimization target by utilizing a genetic algorithm to obtain an optimal trajectory curve of an end actuator of the mechanical arm. According to the method, the trajectory planning efficiency and the tracking accuracy of the mechanical arm are improved, and the problems of real-time trajectory planning of the mobile mechanical arm and trajectory planning optimization and control of the mechanical arm in an uncertain environment are also solved; and the trajectory planning optimization method for the mobile mechanical arm is effective.

The invention discloses a real-time trajectory planning method for an autonomous vehicle. The real-time trajectory planning method comprises the steps of: S1, acquiring relevant information of the autonomous vehicle in real time; S2, generating a reference trajectory, a feasible trajectory cluster determined by means of the reference trajectory and a speed corresponding to each feasible trajectoryin the feasible trajectory cluster based on the relevant information of the autonomous vehicle; S3, calculating an action of each feasible trajectory according to the feasible trajectories and the corresponding speeds thereof by utilizing a target optimization function taking safety and efficiency as targets, and selecting the feasible trajectory with the least action as the expected optimal trajectory, and carrying out optimization to obtain an expected optimal velocity corresponding to the expected optimal trajectory, wherein the target optimization function is obtained according to the principle of least action and an equivalent force method. The real-time trajectory planning method can enable the autonomous vehicle to imitate driving features of a driver in an unknown environmental condition, and can plan a trajectory that best meets the driver's driving expectation by taking the safety and efficiency as the driving targets according to the surrounding vehicles and environmental information in real time.

A method and apparatus for speech processing in a distributed speech recognition system having a front-end and a back-end. The speech processing steps in the front-end are as follows: extracting speech features from a speech signal and normalizing the speech features in order to alter the power of the noise component in the modulation spectrum in relation to the power of the signal component, especially with frequencies above 10 Hz. A low-pass filter is then used to filter the normalized modulation spectrum in order to improve the signal-to-noise ratio (SNR) in the speech signal. The combination of feature vector normalization and low-pass filtering is effective in noise removal, especially in a low SNR environment.

A method and apparatus for determining, calculating, and / or viewing a trajectory. The trajectory can be displayed on a display relative to image data of a patient. A user can use the system to determine relationships between two or more trajectories that have been determined. The relationships can be within two dimensional, three-dimensional, or four dimensional space. The relationships can include distance, angle, etc. The relationships can also be determined between real time trajectories and stored trajectories, or combinations thereof.

A passive electro-optical tracker uses a two-band IR intensity ratio to discriminate high-speed projectiles and obtain a speed estimate from their temperature, as well as determining the trajectory back to the source of fire. In an omnidirectional system a hemispheric imager with an MWIR spectrum splitter forms two CCD images of the environment. Three methods are given to determine the azimuth and range of a projectile, one for clear atmospheric conditions and two for nonhomogeneous atmospheric conditions. The first approach uses the relative intensity of the image of the projectile on the pixels of a CCD camera to determine the azimuthal angle of trajectory with respect to the ground, and its range. The second calculates this angle using a different algorithm. The third uses a least squares optimization over multiple frames based on a triangle representation of the smeared image to yield a real-time trajectory estimate.

A passive electro-optical tracker uses a two-band IR intensity ratio to discriminate high-speed projectiles and obtain a time-varying speed estimate from their time-varying temperature, as well as determining the trajectory back to the source of fire. In an omnidirectional system a hemispheric imager with an MWIR spectrum splitter forms two CCD images of the environment. Various methods are given to determine the azimuth and range of a projectile, both for clear atmospheric conditions and for nonhomogeneous atmospheric conditions. One approach uses the relative intensity of the image of the projectile on the pixels of a CCD camera to determine the azimuthal angle of trajectory with respect to the ground, and its range. A second uses a least squares optimization over multiple frames based on a triangle representation of the smeared image to yield a real-time trajectory estimate.

A goal programming based hypersonic flight vehicle re-entry trajectory online optimization method comprises the steps of giving a kinetic model of hypersonic flight vehicle re-entry process, including height, latitude, longitude, course angle and trajectory angle kinetic equations; calculating a re-entry corridor within a speed-height plane, setting an attack angle alpha as a segmented linear function and using two speed values V1and V2 as a segmentation points to obtain the attack angle alpha; respectively designing a longitudinal trajectory and a transverse trajectory. The goal programming based hypersonic flight vehicle re-entry trajectory online optimization method is applicable to online trajectory generation of the hypersonic flight vehicle re-entry process, is feasible and effective for solving the problem of the re-entry trajectory optimization under the condition that a terminal point position is known, can generate a feasible trajectory within short time, meets quick and real-time trajectory optimization, can further make the obtained trajectory to meet all constraint conditions within a certain error accuracy range and ensures trajectory feasibility.

Provided are an apparatus and a method that chooses an object to be preferentially controlled based on an accident risk degree and hazard and controls the chosen object. In the present invention, it is possible to choose and control a ship having high hazard calculated with trajectory prediction, current operation state information, and past history information under a traffic situation in which the ships are concentrated, by priority. The ship having high hazard is chosen by calculating and applying various history information including an accident record, an entry history of an operator, an aging degree history of the ship, and a steering feature history by using a collision risk on a real-time trajectory collision risk and past history information and different warnings are given during a control for each level.

The invention relates to a dynamic trajectory planning method for performing obstacle avoidance and overtaking based on lane line parallel shift. Different state spaces are established for different road scenes, so that trajectory planning under different working conditions is achieved; and a more accurate subsequent real-time trajectory is planned through coordinate conversion and decoupling. Themethod has the beneficial effects that the different state spaces are established for the different road scenes, so that the effective and accurate trajectory planning under the different working conditions is achieved; through the coordinate conversion and decoupling, the more accurate real-time trajectory planning is achieved for a subsequent trajectory planning party; a planned trajectory screening objective function and constraint conditions are set, so that the trajectory planning efficiency is improved, and the safety, comfort and stability requirements of trajectory planning are met; and evaluation conditions for ensuring the path consistency are set, so that the situation that unsafe factors are generated for a planned path due to environmental changes during vehicle running is avoided, and a dangerous warning of the planned path can be found in time to carry out trajectory re-planning or a driver can be reminded to carry out intervention operation when an optimal path cannotbe selected.

The invention discloses smart site safety management platform system architecture. The smart site safety management platform system architecture is characterized in that the cloud and Internet of Things technology architecture uses a construction safety management platform composed of an intelligent helmet, a locator, a multi-function construction safety monitor, a transmission network, a secondary development BIM modeling software system, a cloud map and application server and a client terminal PC / display screen. Compared with the prior art, the smart site safety management platform system architecture provided by the invention has the functions of real-time position location, real-time trajectory analysis, monitoring of real-time environment safety and other information, personnel intelligent management and the like. Intelligent management of mobile personnel in an area is realized. Dangerous dangers of the personnel are timely alarmed and uploaded to the cloud to ensure the safety of the personnel. Safety management of real-time safety monitoring and safety warning of constructors at a construction site is realized.

The present invention provides computer implemented methodology that permits the safe landing and recovery of rotorcraft following engine failure. With this invention successful autorotations may be performed from well within the unsafe operating area of the height-velocity profile of a helicopter by employing the fast and robust real-time trajectory optimization algorithm that commands control motion through an intuitive pilot display, or directly in the case of autonomous rotorcraft. The algorithm generates optimal trajectories and control commands via the direct-collocation optimization method, solved using a nonlinear programming problem solver. The control inputs computed are collective pitch and aircraft pitch, which are easily tracked and manipulated by the pilot or converted to control actuator commands for automated operation during autorotation in the case of an autonomous rotorcraft. The formulation of the optimal control problem has been carefully tailored so the solutions resemble those of an expert pilot, accounting for the performance limitations of the rotorcraft and safety concerns.

A method, apparatus and computer program product for Functional Space-Time Trajectory Clustering. The method comprises receiving collections of data structures comprising location and time descriptors. The method further comprises estimating functional curves from the collections of data structures. The method further comprises reducing dimensions of the functional curves; and clustering the functional curves into clusters.

The invention provides a trajectory-data-based method and system for recommending a taxi cruising path. The method comprises: (1) network data are initialized and regional grid division is carried out; (2) according to historical trajectory data, a historical traffic charge is calculated; (3) with combination of real-time trajectory data, a traffic charge is calculated and updated; (4) when a taxi arrives at an intersection, a sub regional traffic electric field force applied on the taxi is calculated by using the traffic charge obtained at the step (3) based on an urban traffic Coulomb law, a road network data base is inquired to obtain all road sections of the current intersection, and one road section with the smallest included angle with the traffic electric field force direction is used as a recommended road section; and (5) during the driving process at the recommended road section, if the taxis does not pick up any passenger or the passenger gets off the taxi, the step (4) is carried out; and if the taxi picks up a passenger, recommendation is stopped temporarily. According to the invention, the method has a clear idea and the effect is obvious. The empty driving cruising of the taxi can be reduced and thus the earnings of the taxi driver can be increased; and the urban traffic efficiency can be improved.

The invention is applicable to the field of electrons and provides a mid-air gesture recognition method and device applied to an intelligent terminal. The mid-air gesture recognition method includes: setting sample frequency to acquire real-time location information of mid-air gestures; determining gesture strokes corresponding to a real-time trajectory segment and stroke number of the gesture strokes according to the real-time location information; acquiring coding corresponding to the gesture strokes according to the number of the gesture strokes and calculated displacement of the real-time trajectory segment; sequentially combining the coding of the gesture strokes corresponding to all the real-time trajectory segments contained in the mid-air gestures to acquire the coding of the mid-air gesture. The mid-air gesture recognition method and device has the advantages of being high in recognition speed and high in accuracy.

The invention relates to real-time numerical simulation, network communication, computer programming and visual display. In order to provide a virtual simulation platform integrating real-time simulation, data monitoring, data storage, visual display and performance evaluation, the virtual simulation platform is used for verifying feasibility, applicability and effectiveness of an RLV reentry three-dimensional real-time trajectory optimization and tracking method and a robust adaptive strategy. The invention, RLV virtual simulation platform design and implementation method, designs the Simulink model and the control algorithm of the reusable carrier RLV on the computer, forms the Simulink model library and the control method library, and the control method library includes the super spiralsliding mode, the terminal and the adaptive dynamic programming control algorithm to compile the Simulink model into C code that can be run in the dSPACE simulator and download it to the dSPACE simulator through a computer. The invention is mainly applied to RLV simulation occasions.

The invention provides a multi-lane space-time trajectory optimization method for an intelligent network connection vehicle. The space-time trajectory optimization algorithm based on a reinforcement learning algorithm is designed, so the optimal trajectory can be quickly matched. The algorithm comprises the following steps of (1) optimizing a space-time track, taking the current position and speedof a vehicle and a target driving-out lane, taking a time period as an input, and taking a set of vehicle accelerations as an output; and (2) optimizing multi-lane cooperative lane changing, taking the current position and speed of the vehicle and the position and speed threatening the vehicle of the target lane as input, and taking a vehicle acceleration set as output. That is to say, after a vehicle initiates a lane changing request, the track of the vehicle cooperative lane changing process can be matched through reinforcement learning, and after lane changing is completed, the space-timetrack at the moment is matched through reinforcement learning to achieve the multi-lane track optimization process. The method can optimize and generate the space-time track of the passing vehicles inthe road section in real time according to different road environments and traffic states, improves the mutual cooperation capability of the vehicles, improves safety of the passing road section andvehicle passing efficiency of the intersection, reduces the energy consumption level of the vehicles, and improves traffic safety of the road section in order to guarantee the traffic safety of the road; and a new solution and a theoretical basis are provided for improving the travel efficiency.

Described is a system for position estimation. A set of raw sensor outputs are acquired from a sensor of a platform. The set of raw sensor outputs are stored in non-transitory memory. A set of optimized sensor measurements is generated by deducing errors in the raw sensor outputs using an unconstrained optimization algorithm. The system determines a position of the platform based on the set of optimized sensor measurements.

The invention relates to an underwater section monitoring robot controller which includes a controller A arranged in a ship-loaded control box and a controller B arranged in an underwater robot instrument cabinet. The two controllers communicate through an armored umbilical cable. The controller A acquires a remote-control control instruction of a control panel of the ship-loaded controller in a real-time manner and carries out coding and assembled framing on the control instruction according to a customer-defined communication protocol and then sends the control instruction to the underwater controller B via a communication module. The underwater controller B receives a protocol frame, which is sent by the ship-loaded controller A, in a real-time manner and carries out protocol decoding and analyzing out the control instruction according to a protocol format so as to control a switch of a corresponding relay on a relay driving plate to move and thus control of motion postures of the underwater robot is realized. The underwater section monitoring robot controller and the automatic trajectory tracking controlling method adopt a limited-time trajectory tracking control technology to realize tracking of a preset trajectory point by an underwater robot so that wide-range and high-precision motion and posture control of the underwater section monitoring robot can be realized.

The invention discloses an omnidirectional chassis control method based on the fuzzy immune neural network algorithm and is used for solving the technical problem of poor control precision of the existing omnidirectional chassis control method. The technical solution is to introduce the fuzzy algorithm into the parameter setting of the chassis PID, and introduce the neural network algorithm into the fuzzy algorithm to establish a five-layer neural network. The first layer is the input layer, the input quantity is the error (t) and the error variation ([delta]e(t)) of the system output; the second layer is the fuzzification layer, and the input is fuzzed by the membership function; the third and fourth layers are the fuzzy calculation layers and used for completing the fuzzy calculation; and the fifth layer is the output layer, and is used to inversely blur the result and output it. In this process, for the parameters that need to be learned, a back-propagation (BP) algorithm is used for learning, and the immune algorithm is introduced into the learning process. The inertial navigation system, the motion control system, and the IMU are combined to improve the tracking capability fora given trajectory and the real-time trajectory of the system, and the control accuracy is high.

The invention relates to a power system transient stability evaluation method based on a short-time disturbed trajectory after fault removal. The method is characterized by comprising the following steps: firstly, selecting the short-time disturbed trajectory of the electric quantity at the end of the generator after the fault is removed, and secondly, searching the characteristic arrangement modeof the short-time trajectory when the evaluation accuracy is optimal, so that the local characteristic extracted by the model is more robust, and optimizing the parameters of the network window by taking the optimal comprehensive evaluation index of the model as the target, so that the generalization ability of the model is enhanced, and finally establishing the mapping relation between the short-time trajectory and the transient stability, so that rapid and accurate transient stability rapid evaluation of the power system can be realized. According to the method, misjudgment missing samplesof model evaluation can be effectively reduced, and compared with a traditional machine learning evaluation method, the method is more accurate and efficient, and the transient stability can be evaluated based on the short-time disturbed trajectory, and a certain time margin is reserved for a dispatcher to take a control measure.

The invention discloses an intelligent vehicle real-time trajectory planning method based on nonlinear model predictive control; the method comprises the following steps of by combining a linear two-degree-of-freedom model of a vehicle and a kinematic equation of the vehicle under geodetic coordinates, establishing a nonlinear dynamics equation of a controlled object; discretizing the establishednonlinear dynamics model by using a time interval Ts to obtain a state prediction equation of the system in the prediction time domain; constructing NMPC problem containing a terminal constraint by introducing a cost function and the constraint of the control problem; solving the nonlinear optimal control problem through a tool box, and obtaining the optimal control sequence, and supplying the first component of the optimal control sequence to the controlled object; and establishing a Simulink and Carsim combined simulation platform for experimental verification.

A behavior tracking system include a video monitoring module, Regional headcount module, motion trajectory perimeter prevention and control module, Automatic Tracking Module of Motion Trajectory, A fast motion trajectory retrieval module, a motion trajectory automatic prediction module and a motion disturbance elimination recognition module track and monitor the real-time trajectory of each objectin the delimited range, and a human body recognition framework based on depth self-learning AI and an action roadmap can be drawn, and a roadmap image video of the trajectory in a specific period ofits history can also be accessed. It provides an accurate basis for recording, inquiring and predicting the motion of objects in video images.

The invention discloses a multi-preset point dynamic intelligent monitoring method applied to a border defence video monitoring system. A detection range is expanded: various detection modes are provided, including a preset point mode, a patrol path mode, a patrol scheme mode, a double-front end detector target measuring mode and a multi-front end detector target measuring mode, and omnibearing three-dimensional monitoring of border lines can be performed by us of the detection modes. Monitoring quality is improved: setting of monitoring rules can be performed on each path of video of each front end detector in a targeted manner, and the detection rate of monitoring targets (detection rate>=90%) is improved. The double-front end detector target measuring mode and the multi-front end detector target measuring mode can sufficiently utilize construction advantages of the front end detectors, continuously track monitoring targets and can obtain spatial position parameters, record and display a real-time trajectory, thereby contributing to cognition of a current monitoring target situation of monitoring personnel and command decision-making of a current situation of command personnel.

The invention provides a multifactor association comparison health monitoring system and method, and relates to the technical field of human health detection. The system comprises a factor detection unit, a user terminal and a cloud server which are wirelessly connected in turn. The factor detection unit is used for detecting vital sign information, detecting environmental information within the range of matching time, identifying and recording the current geographical location information, recording the occurrence time of factors and performing time trajectory series connection of the factorsto acquire a time axis, recording the daily life of individuals to acquire life trajectory information, viewing the factor recording information according to binding information and inputting symptominquiry information. The cloud server is used for associating the factor recording information to acquire factor association information and comparing the factor association information according tothe symptom inquiry information so as to obtain the factor comparison index. The comprehensiveness of the health data and the health result inquiry accuracy can be enhanced by multifactor association.