173 results about "Human–machine system" patented technology

The invention provides an unmanned-gyroplane system used for automatic inspection of bridges and tunnels and a navigation method, belonging to the field of automatic detection of bridge and tunnel diseases. According to the invention, aimed at the characteristics of bridge and tunnel areas, the unmanned gyroplane inspection system which realizes autonomous navigation in virtue of GPS, laser radar and IMU is designed; and the system realizes autonomous inspection of an open bridge area by using a GPS navigation system and autonomous inspection of a closed tunnel area by using a laser radar navigation system, dodging of bridges, tunnels and motor vehicles via an automatic evadible system, and shooting of images of key areas, wherein the images are sent back to a ground station, and thematic pictures of diseases of bridge and tunnels are generated by the ground station and provided to related personnel for use. The unmanned-gyroplane system provided by the invention has the characteristics of mobility and flexibility in the process of inspection and has the advantages of a wide inspection coverage area, unblocking of traffic, real-time returning of live shots, etc.

Extended-range monitoring and surveillance of facilities and infrastructure—such as oil, water, and gas pipelines and power lines—employs autonomous vertical take-off and landing (VTOL) capable, small unmanned aerial system (sUAS) aircraft and docking platforms for accommodating the sUAS aircraft. Monitoring and surveillance of facilities using one or more embodiments may be performed continually by the sUAS flying autonomously along a pre-programmed flight path. The sUAS aircraft may have an integrated gas collector and analyzer unit, and capability for downloading collected data and analyzer information from the sUAS aircraft to the docking platforms. The gas collector and analyzer unit may provide remote sensing and in-situ investigation of leaks and other environmental concerns as part of a “standoff” (e.g., remote from operators of the system or the facilities) survey that can keep field operators out of harm's way and monitor health of the environment.

The invention relates to a quadrotor unmanned plane control method based on a fuzzy expansion state observer and an adaptive sliding formwork. The method comprises steps that a quadrotor unmanned plane system model is established, and a system state and controller parameters are initiated; a tracking differentiator is designed; a non-linear expansion state observer is designed; fuzzy rules are established; a parameter adaptive law is designed; an adaptive sliding formwork controller is designed. According to the method, the expansion state observer is designed to estimate indetermination of a system model and external disturbance; a pole assignment method is utilized to determine an initial value of an expansion state observer parameter; the fuzzy rules are introduced to realize online setting for the expansion state observer parameter; the parameter adaptive law is designed to acquire ideal controller gain; the adaptive sliding formwork controller is designed, rapid stabilization of a system tracking error and convergence to a zero point are guaranteed, and rapid and stable position tracking and pose adjustment of the quadrotor unmanned plane are realized. The method is advantaged in that system performance is improved, and rapid and stable system position tracking and pose adjustment are realized.

The invention relates to an unmanned aerial vehicle system with in-site virtual-actual coupling. The system comprises an environment detection module, a virtual flight simulation module, an unmanned aerial vehicle remote control module, an unmanned aerial vehicle ground station module and an unmanned aerial vehicle flight module, wherein the environment detection module is used for detecting varied environmental parameters of the actual flight environment of the site; the virtual flight simulation module is used for generating virtual training environment and a virtual unmanned aircraft; the unmanned aerial vehicle remote control module is used for generating and transmitting remote control commands for an unmanned flight unit, and the remote control commands can be received by the unmanned aerial vehicle flight module and the virtual flight simulation module; the unmanned aerial vehicle flight module is an actually-mounted unmanned aircraft; an unmanned aerial vehicle ground station is equipment which is placed on the ground, and use staff perform initialization and real-time information treatment on the actually-mounted unmanned aircraft or the virtual unmanned aerial vehicle aircraft through the unmanned aerial vehicle ground station, so that the initial route of the actually-mounted unmanned aircraft or the virtual unmanned aerial vehicle aircraft is programmed, and the position, the attitude parameter and the obtained video signal of the actually-mounted unmanned aircraft or the virtual unmanned aerial vehicle aircraft are received.

The invention discloses an intelligent man-machine conversation system in a closed domain. The system comprises a first modeling module, a second modeling module and a third modeling module, wherein the first modeling module is used for constructing a multi-feature fusion deep intention recognition model on the basis of a bidirectional long/short-term memory network and a convolutional neural network; the second modeling module is used for constructing an MC-BLST-MSCNN-based conversation state tracking model by adoption of a man-machine conversation system current state input and context statement combined modeling manner; and the third modeling module is used for constructing a Bi-LSTM matching model on the basis of an extraterritorial recover mechanism of a displacement attention mechanism, and inputting recognized user intentions and user slot values into a displacement network to carry out weight distribution the attention mechanism, so as to realize conversation state encoding andconversation control matching. The system has higher intention recognition accuracy, conversation state tracking correctness and conversation control stability, so as to enhance the cognition intelligence capability of man-machine systems.

A system and method are provided to support accommodating safe integration of small unmanned aircraft systems (sUASs) into the National Airspace Structure in the United States. A specifically-tailored service is provided to address a change of paradigm from aircraft-based avionics/capabilities to a ground-based solution centered on the sUAS control station that is typically employed to manage an sUAS mission and/or flight. Appropriate software, server and system components are integrated into an interactive, easy-to-use, web-based tool that provides interested parties with real-time, graphical flight-following information to acquire position information regarding an sUAS platform from the control console for the sUAS platform. The acquired position information is forwarded to a separate server that can augment and provide graphical display of the sUAS intended route of flight (flight planned route). The acquired position information for the sUAS is converted to a format commonly used by aviation and air traffic control systems.

The invention discloses a nonlinear robust controller design method based on back-stepping and sliding mode control technologies and aimed at a nonlinear model of a quad-rotor unmanned plane. A sliding mode controller of a speed-constant reaching law is designed to an attitude angle system of the quad-rotor unmanned plane, and rapid tracking for the attitude angle is ensured. To realize track tracking for the spatial position of the quad-rotor unmanned plane, a sliding mode surface and a virtual control quantity are constructed according to a stepping back control idea to realize nonlinear control law design and system stability design from the kernel to the external layer of a system. After an equation of the related virtual control quantity is obtained, an expected track value of the attitude angle is obtained by solving the equation via arithmetic inverse operation, and a design method of the speed-constant reaching law is used to determine a final input control law of the quad-rotor unmanned plane system. According to the method of the invention, the characteristic that sliding mode control is uncertain for the model and insensitive to external interference is utilized, robust trace tracking for the nonlinear quad-rotor unmanned plane can be controlled under interference.

An Unmanned Aerial Vehicle (UAV) system that couples the speed and responsiveness of a shoulder-launched rocket with the stable, slow-moving aerial platform of a parafoil is disclosed. The unique use of an over-damped rocket automatically positions the parafoil upwind of its target and overcomes the inherent inability of the parafoil to make headway in adverse wind conditions. This marriage of a rocket and a parafoil creates a valuable new synergy that allows the rocket to very quickly position a payload at altitude and defeat any adverse winds, while the parafoil provides an inexpensive and easy-to-fly vehicle for reconnaissance or accurately placing a payload on a target. The system is suitable for aerial videography, thermal imagery, target designation, sensor placement or precision munitions delivery; and can perform these functions at a small fraction of the cost of any other UAV. Unlike other UAV's, no flying skills are required of the operator. The system is so simple to use that no special training is required even for flying at night, and the intrinsic stability of the parafoil eliminates the need for avionic control systems.

The invention relates to a petrol-electric hybrid power fixed wing vertical take-off and landing unmanned plane system, which comprises a fuselage, a wing I and a wing II. The wing I is provided with a vertical propeller I and a wing motor I. The wing II is provided with a vertical propeller II and a wing motor II. The front end of the fuselage is externally connected to a fixed wing horizontal propeller, the tail of the fuselage is provided with a longitudinal balance directional propeller and a longitudinal balance directional control motor, and the fuselage is internally provided with an autopilot for intelligently controlling the operation of the wing motor I, the wing motor II, a petrol power engine and the longitudinal balance directional control motor. The petrol-electric hybrid power fixed wing vertical take-off and landing unmanned plane system provided by the invention realizes the all functions of unmanned plane take-off replying on power battery vertical take-off, hovering to petrol power driven fixed wing fast flight, and return flight hovering to vertical landing petrol-electric hybrid power flight, has the capability of vertical take-off and landing and hovering, and also has the characteristics of fast speed, long voyage and long time.

The invention relates to an active stroke lower limb rehabilitation robot control method based on healthy side and affected side coupling. The method comprises the following steps that: a characteristic pathological gait correction strategy based on a characteristic pathological gait model is formulated; after the limbs of the patient begin to move, multi-sensor signals of the lower limbs of the healthy side of the patient are collected, and multi-sensor signal processing is conducted; constructing of a multi-sensor information fusion vector is carried out; the motion intention of the patientis acquired; the motion intention and the characteristic pathological gait correction strategy are coupled to obtain healthy side-affected side coupling information, and the healthy side-affected sidecoupling information is transmitted to a human body-rehabilitation robot closed-loop controller, so that the system function of the rehabilitation robot is controlled, and man-machine coordinated operation is guaranteed. According to the invention, feedback type motion replanning and control integration are carried out through accurate identification of the healthy side leg motion intention, coupling regulation and control of a man-machine system are achieved, and finally, the goal of healthy side and affected side coupling training is achieved.

The invention discloses an enhanced-type double-power reaching law sliding-mode control method for a four-rotor-wing unmanned plane system. The enhanced-type double-power reaching law sliding-mode control method is designed for the four-rotor-wing unmanned plane system through combining with a double-power reaching law sliding-mode control method. The design of an enhanced-type double-power reaching law aims at guaranteeing that the sliding mode of the system can reach a sliding mode plane more quickly while the vibration of the system is not increased, thereby achieving the quick and stable control of the system.

The invention discloses an enhanced-type constant-speed reaching law sliding-mode control method for a four-rotor-wing unmanned plane system. The enhanced-type constant-speed reaching law sliding-modecontrol method is designed for the four-rotor-wing unmanned plane system through combining with a constant-speed reaching law sliding-mode control method. The design of an enhanced-type index reaching law aims at guaranteeing that the sliding mode of the system can reach a sliding mode plane more quickly while the vibration of the system is not increased, thereby achieving the quick and stable control of the system.

The invention discloses a rotary ejection frame for small-sized unmanned aerial vehicles, belonging to the aeronautical machinery technical field. The rotary ejection frame comprises a launcher base, a rotary rocker arm and a torsion spring, wherein two ends of the torsion spring are respectively fixed with the base and the rotary rocker arm; a tripod with height and angle adjustable is arranged on the base; a flying gripping mechanism, a releasing mechanism and a counterweight mechanism are arranged on the rotary rocker arm; and the formed rotary ejection frame has the advantages of simple structure and convenient operation. Moreover, the rotary ejection frame is small in occupied area, rapid to unfold and withdraw. Compared with common linear-type ejection frames, the size of the rotary ejection frame is greatly reduced, which provides convenience for the use of small-sized unmanned aerial vehicles.

The invention discloses a system and a method for implementing safety monitoring of a virtual machine system. According to the invention, a safety enhancing module is arranged for each virtual machine in the virtual machine system, a safety monitoring strategy aiming at the virtual machines is set and according to the safety monitoring strategy, the virtual machines are subjected to safety monitoring, wherein the safety monitoring strategy comprises safety strategies and security plug-ins; the safety strategies can be formed by autonomous safety strategies configured by user virtual machines and a global safety strategy configured by a management virtual machine; a safety function is uniformly configured to the security plug-ins; and the user virtual machines can carry out optional configuration as required. By the system and the method for implementing safety monitoring of the virtual machine system, which are disclosed by the invention, safety monitoring can be carried out according to individual requirements of the virtual machines and a safety monitoring function of a virtual machine monitor is reduced, so that the structure of the virtual machine system is enabled to be simple and the integral virtual machine system is more safe and reliable.

The present invention discloses a wearable display-based asynchronous type brain-controlled unmanned aerial vehicle system. A wearable display is utilized to display a group of visual stimulation units which flick with different frequencies; the visual stimulation units are corresponding to one group of different operation instructions of an unmanned aerial vehicle; a user gazes at different visual stimulation units, so that brain electrical signals can be generated, and the brain electrical signals are processed, so that the visual stimulation units which are gazed by the user and operation instructions corresponding to the visual stimulation units are identified; identification results are sent to the unmanned aerial vehicle end so as to be executed; the real-time scene pictures of the unmanned aerial vehicle are transmitted to the ground and are superimposed with the visual stimulation units, and superimposition results are displayed on the wearable display; and therefore, first-person perspective feedback can be provided for the user, and the portability of a steady-state vision-induced electric potential brain-computer interface system can be improved. According to the wearable display-based asynchronous type brain-controlled unmanned aerial vehicle system of the invention, an idle state can be fully utilized to perform decoding, and therefore, operational burden and fatigue feeling caused by using a brain-computer interface to control flight can be greatly decreased, and more free flight experience can be brought to the user.

The invention discloses a wireless sensor network unmanned aerial vehicle system communication method based on an optimization particle swarm algorithm. The method is used for a wireless sensor unmanned aerial vehicle system network composed of a mobile node unmanned aerial vehicle, a ground communication station (2) and multiple ground wireless sensor nodes (3), and comprises the following steps:(10) network region partition: the whole network region is partitioned into multiple sub-regions by using the optimization particle swarm algorithm; (20), sub-region cluster head selection: a sensornode in each sub-region computes weight sum, and selects a cluster head node; (30) next-hop access node selection: the mobile node accesses the cluster head node with the maximum residual overflow cache time, and then selects the cluster head node needing to be accessed by the next hop of the mobile node; and (40) data transmission: the unmanned aerial vehicle (1) transmits the data to the groundcommunication station (2). Through the wireless sensor network unmanned aerial vehicle communication method disclosed by the invention, the energy consumption is less, the network load equilibrium isgood, and the network life is long.

The invention discloses a walking aid lower limb of an exoskeleton robot. The walking aid lower limb comprises a first actuator fixing part (1.1), a thigh rod (1.2), a bionic knee-joint (1.3), a shank guard board (1.4), a shank guard board fixing part (1.5), a shank rod (1.6), a shank guard board connecting piece (1.7), a second actuator fixing part (1.8), and an actuator (1.9). The invention provides a walking aid lower limb of an exoskeleton robot, combined with a crossed four-bar linkage structure, a bionic mechanism which accords with physiological movement characteristics of human knee joints is designed. The walking aid lower limb can eliminate harmful applied forces generated by man-machine offset, and solves problems of radial deviation and tangential rotation offsets generated by man-machine system microscopic offset along a shank, so as to improve use security and wearing comfortableness of a rehabilitation exoskeleton.

The invention discloses a non-contact virtual human-computer interaction method based on a smart television set; the method comprises the steps: step 1, connecting to the smart television set to image sensing equipment, establishing a gesture identification system and a gesture information database in the smart television set, and storing a plurality of appointed gestures as well as smart television set executing programs in one-to-one correspondence association with the appointed gestures in the gesture information database; step 2, setting two operational models; step 3, directly operating a two-dimensional menu interface and a three-dimensional control interface switched by the gestures in the smart television set when the operational model A is carried out; and step 4, when the operational model B is carried out, keeping the present interface of the smart television set unchanged and calling the smart television set executing programs correspondingly associated with the gestures. The non-contact virtual human-computer interaction method based on the smart television set has the beneficial effects of exploring users' interaction purposes in the combination of virtual interface location awareness and users' behavior models and providing a new way for solving the 'Midas Touch Problem' which is difficult to be solved on the basis of a gesture interaction human-computer system.

The invention belongs to the field of structure design of racing cars, in particular to a design method for formula car structures. A conventional computer aided design system is adopted to realize man-machine design of racing car structures. The design method includes five steps including working condition setting, parameter setting, man-machine system design, racer model input and design optimization. The working condition setting includes setting of driving conditions, safety conditions, view conditions and racing track conditions. The parameter setting includes basic racing-car parameter setting, racer model parameter setting and racer parameter input. The man-machine system design includes design of racing car seats, racing car operating devices and racing car displaying devices. The design method is simple, scientific in principle, convenient to operate, good in design quality, and high in efficiency.

The invention, which belongs to the field of brain-computer interfaces, relates to a motion-imagination-based portable brain-controlled unmanned aerial vehicle system and a control method thereof. Thesystem is composed of an EEG signal acquisition device, an embedded EEG signal processing device, and a flight portion. The EEG signal acquisition device uses a high-precision and high-integration analog front end and a high-precision and high-integration AD conversion chip, so that power consumption of the EEG signal acquisition module is reduced, the system design is simplified, and the signal-to-noise ratio is improved; and signal processing is carried out well and thus the size of the EEG signal acquisition device is reduced substantially. According to the system, the EEG signal acquisition device is installed at an occipital lobe part of an electrode cap in an integration manner and the bluetooth is used as a data transmission mode, so that the collection part of the EEG signal is combined with the electrode cap and an independent part is formed. Therefore, the comfort and flexibility of the user are improved substantially.

Methods and systems are described for an aerial drone system including a drone system controller, at least one working drone (101), and a plurality of support drones (103). The working drone (101) is operated by the drone system controller (125) to adjust a position of the working drone (101). A tether line (105) coupled to the working drone (101) provides electrical power to the working drone (101). The support drones (103) are each coupled to the tether line (105) at a different location along the tether line (105) forming a tethered aerial drone system. Each support (drone 103) supports a portion of the weight of the tether line (105) and is operated by the drone system controller (125) to adjust the position of the tether line (105) by adjusting the position of one or more of the support drones (103).

The invention provides a human error mode influence analysis method, which comprises the following steps: 1. Human-computer interaction task flow analysis and function model establishment, and human-computer system function model establishment for each sub-task; 2, human error pattern recognition, and finally obtain various human error patterns and their correspond standard probabilities in that task process; 3, construction of environmental impact factor system and determination of parameters; 4, human error probability calculation and human error mode influence analysis, human error probability calculation and human error mode influence on the functional unit and the final task; through the above steps and methods, the relationship between each function is clarified, and the EPC factor in the analysis task is quantified by means of HEART method, which achieves the goal of quantifying the effect of human error mode, and solves the practical problems of comprehensive evaluation of human error mode.

A system interface design method is characterized in that a system interface of the system interface design method gives definitions to a user and a use interface of the user, so that the user and theuse interface become enlightenment of interaction information of a man-machine system, and application authority is given after verification or entry authority is verified for a user operating system; or the permission is controlled for any program of the user; or verifying the entry authority and the use authority of any article in the interval for the user; the authority of entering verification for a virtual space of the user and the authority of using any virtual article in the virtual interval are provided; and, for a user, a permission of entering verification for a virtual space, the permission of selecting any one corresponding virtual article to use the corresponding real article in the real space by the user in a virtual interval is included; the identification technology associated with the emotion expression of the user comprises the following steps of: comparing the original reference objects of any one of the face, gesture and voice of the user; technical stress reference object expressions meeting conditions are formed, and the application permission of information interaction of a man-machine system is achieved.

The invention discloses a four-rotor-wing unmanned aerial vehicle formation controlling method based on a self-adaption RBF neural network. A three-dimensional formation controlling scheme is studiedunder the condition that there exists dynamic uncertainty in a non-linear multi-four-rotor-wing unmanned aerial vehicle system with time-lag based on a radial basis function (RBF). a linear reduced order observer is designed for obtaining absolute and local state errors of each unmanned aerial vehicle, a Lyapunov function which can simply the designing of the controller is constructed to offset the time-lag existing in an unmanned aerial vehicle dynamic model, and the self-adaption RBF neural network is adopted for treating the non-linear dynamic uncertainty and unavoidable interference.

The invention discloses a self-adapting automation method based on brain function state. The self-adapting automation method comprises the steps of: determining the arrangement of an encephalogram electrode, a near infrared optical spectrum light source and a near infrared optical spectrum probe; establishing an artificial neural network model according to a linear characteristic parameter, a non-linear characteristic parameter, an oxyhemoglobin saturation index and a simulative task performance index, and optimizing the artificial neural network model through a genetic algorithm to obtain a cognitive function state detecting model; determining whether adjusting the task distribution mode of a person and an automatic system and early warning an operator according to a real-time cognitive function state index, a task demand index, a cognitive function state index warning threshold value and a state duration threshold value; and if so, adjusting the task distribution mode of the person and the automatic system, early warning the operator, and ending the process. Compared with the traditional automatic man-machine system, the self-adapting automation method disclosed by the invention distributes the tasks in a self-adapting manner to reduce the occurrence rate of human errors and effectively improve the working efficiency and safety of the man-machine system.

The invention relates to a lower limb rehabilitation training robot mechanism with human-machine motion compatibility. The mechanism is formed by an external skeleton mechanism, as well as a connecting joint and a connecting piece for connecting a lower limb of a human body, wherein the external skeleton mechanism comprises a left branch mechanism and a right branch mechanism which are arranged symmetrically and respectively consist of a waist component, an upper leg component, a lower leg component, a coxa joint and a knee joint; the two branch mechanisms are connected into a whole by virtueof the waist connecting component; the upper leg component and the lower leg component of each branch mechanism are connected with thigh and crus of a single lower limb of the human body by virtue ofthe connecting joint and the connecting piece; and the external skeleton mechanism and all connecting joints and connecting pieces form the lower limb rehabilitation training robot mechanism. According to the lower limb rehabilitation training robot mechanism, wider left-right side swing motion and front-back buckling motion of the lower limb of the human body can be guided. Furthermore, the motion compatibility of a human-machine system formed by wearing the lower limb rehabilitation training robot mechanism is remarkably improved, and the safety and effectivity of lower limb rehabilitation training can be improved.

The invention relates to an auxiliary output-based six-rotor unmanned aerial vehicle fault estimation method. The method comprises the steps that firstly, a dynamic space model is built according to the structure of a six-rotor unmanned aerial vehicle; secondly, by taking residual lift force provided by a six-rotor unmanned aerial vehicle actuator (such as a motor and a rotor) after the six-rotorunmanned aerial vehicle actuator generates a fault as unknown input of the unmanned aerial vehicle system, a state space model of the six-rotor unmanned aerial vehicle system with the actuator fault is built; thirdly, according to the fact that the six-rotor unmanned aerial vehicle system does not meet the matching condition of an unknown input observer, auxiliary output is constructed to break through limitation of the condition; fourthly, a Luenberger observer is designed for the auxiliary output system; and finally, by means of the method of combining Lyapunov functional with robust H-infinity optimization indexes, the observer gain is solved, and precise estimation on the residual lift force signal of the fault motor is achieved. The method can break through limitation of the matchingcondition of the observer, is applied to the six-rotor unmanned aerial vehicle system, has the advantages of being simple in design and easy for engineering realization and can precisely estimate theresidual lift force signal provided by the fault motor under external interference.