30 results about "Nao robot" patented technology

A robot control apparatus allows a plurality of mobile robots to carry out tasks at a reduced or minimized cost as a whole with consideration given to costs derived from an encounter with an obstacle is provided. An action optimization controller provided in the robot control apparatus generates an instruction for optimizing actions of the plurality of mobile robots so that the plurality of mobile robots carry out the tasks at a minimized cost, based upon locomotion plan information indicative of locomotion plans of the plurality of mobile robots. A possibility that any robots have an encounter with an obstacle is determined by comparing distances from the robots to the obstacles. A locomotion plan implementation cost is calculated with consideration given to the possibility of encounter, and thus an optimum route is selected based upon the locomotion plan implementation cost with the encounter-derived cost. In accordance with the optimum route, the locomotion plan for the robot is modified.

A robot data transfer method includes the step of collecting data from each of a plurality of robots in a multi-robot production facility in real-time. The data collected from the robots is then transferred in real-time from a controller of each of the robots to a first data collection device. Within the first data collection device, the data is buffered using a multi-segment queueing mechanism. The queueing mechanism is configured with a retention policy. The data is then transferred to a second data collection device based on the retention policy of the queueing mechanism of the first data collection device. The second data collection device analyzes the data and determines whether maintenance or optimization is necessary for any of the robots.

The invention discloses an HOG (Histogram of Oriented Gradient) and Mean Shift algorithm-based indoor pedestrian detection and tracking method and belongs to the technical field of pedestrian detection and tracking in indoor complex environments. The method includes the following steps of: positioning of a Nao robot and a human body; HOG algorithm feature extraction; pedestrian detection HOG as well as SVM training and verification; Mean Shift algorithm target tracking; and Nao robot platform-based verification. According to the indoor pedestrian detection and tracking method of the invention, the HOG algorithm and the Mean Shift algorithm are adopted, and therefore, pedestrians can be detected in real time, and detected pedestrians can be tracked. Compared with methods in an early stage which perform pedestrian detection through Haar features, the indoor pedestrian detection and tracking method of the invention has a higher detection success rate and can reach a detection success rate of 90% in an INRIA pedestrian image database where backgrounds are complex. The indoor pedestrian detection and tracking method of the invention has the advantages of real-time performance, accurate detection and good practicability.

A method for driving multiple-module mechanisms by a single motor and redundant modular robots produced therefrom comprises a flexible shaft, which transports the rotation from only one irreversible motor to the mechanisms inside all multiple modules of the robot by means of a plurality of pairs of electromagnetic clutches and respective kits of transmission and driving wheels to distribute selectively the torque / rotation of the motor independently to anyone of the robot modules, electromagnetic breaks keep the desired pose of the robot. A simple control system regulates the speed of the motor and employs simple on-off logic control of the electromagnetic clutches and breaks based on feedback of a set of sensors measuring the angle between each two consecutive robot modules. The versatile kinematics provides the possibility the same construction to be used for implementing a manipulator arm, “elephant trunk”, “snake” or “earthworm”.

An apparatus manages robot components in a robot. The apparatus includes a component monitoring unit to monitor a state of the robot components and a breakdown decision unit to judge whether or not any robot components are broken down based on the monitoring results and generate breakdown information corresponding to the breakdown decision results. The apparatus further includes a recovery policy management unit to choose a recovery policy model necessary to recover the breakdown using the breakdown information and a breakdown recovery unit configured to recover the broken robot component based on the chosen recovery policy model.

The invention provides a humanoid robot ball grabbing method. The method comprises the steps that a camera arranged on an NAO robot sends captured target object image information to a processor; the processor conducts color space conversion and outer outline feature extraction on the received target object image information through an OpenCV vision library function connected with an NAO robot platform, comparison with a built object feature database is conducted, and it is recognized that a target object is in a ball shape; the processor calculates the horizontal distance between the NAO robotand the ball; and the processor calculates the NAO robot walking path according to the horizontal distance, and the NAO robot is controlled to grab the ball target on the basis of the walking path.

The invention discloses a Capsule-Net-based face expression recognition method. The method comprises: step one, selecting a data set and selecting a Cohn-Kanade Plus Database expression data set, thatis, a CK+ expression data set; step two, selecting a deep learning model and using a deconvolution-version Capsule Net as an experimental model; step three, carrying out training and testing based onthe model, segmenting the CK+ expression data set into a training data set and a test data set, reading the training data set into the Capsule Net for periodic training to obtain a stable and accurate Capsule Net deep learning model; and step four, combining the trained Capsule Net deep learning model with an NAO robot, tracking the training process in real time by the NAO robot, reporting information related with the model testing regularly, and expressing an image recognition result in a voice and gesture manner. Therefore, convergence is realized quickly within short time; and the facial expression recognition accuracy and the reliability are improved.

The present invention is directed to a device for allowing universal surgical tool exchange. The device of the present invention includes a tool-side adapter and a robot-side adapter that combine the benefits of a robot in the operating room (OR) with a system that has minimal impact on the current surgical workflow. The device of the present invention allows surgeons to preserve their natural grip on the surgical tool, creates a reliable and repeatable connection between the tool and the robot, and allows the user to rapidly swap the tools in and out from the surgical robot using a single-handed motion. A unique RFID tag and receiver is embedded in the tool-side adapter and the robot-side adapter, respectively to allow the robot to identify the tool that has been engaged. The present invention is universally applicable to any robotic system that is intended to hold a set of hand instruments.

Robotic surgical methods and apparatuses, including systems, for determining positioning information using a combination of AI landmark-identification and visual imaging. Also described herein are methods and apparatuses for determining how to train the AI. Also described herein are end effector devices that may be used with any of the robotic surgical methods and apparatuses. Also described herein designs and techniques incorporating AR into robotic surgical procedures.

Systems and methods for automated software engineering are disclosed. A particular embodiment is configured to: establish a data connection with a software code repository; provide a collection of autonomous computer programs or bots configured to automatically perform a specific software development life cycle (SDLC) task; use a first bot of the collection of bots to perform an automatic code review of a software module from the software code repository; use a second bot of the collection of bots to perform automatic unit testing of the software module from the software code repository; and use a third bot of the collection of bots to perform an automatic deployment of the software module from the software code repository. A health engine module can monitor the execution of the other software modules and capture execution metrics. Any of the bots in the bot collection can be machine learning models trained using training data.

The invention relates to an asynchronous communication method based on a socket, a storage medium and a processor; the asynchronous communication method comprises the following steps: a first client in one machine equipment sends a message of a connection request to a second server in any other machine equipment; after the connection is successful, the second server sends a feedback signal of connection success to the first client; the first client communicates with the second server; the second server informs the second client in the machine equipment of the message of connection success; thesecond client sends the connection request to a first server in the machine equipment where the first client is located; after the connection is successful, the first server sends a feedback signal of connection success to the second client, and the second client communicates with the first server; asynchronous communication connection can be achieved; simple and expandable point-to-point communication can be met, and a vascular intervention system influencing navigation is met; and the method, the storage medium and the processor are more suitable for any robot-assisted interventional operation system and have universality.

The invention provides a two anthropomorphic robots employing interaction method for voice communication. The method includes that a first NAO robot plays voice for communication; a second NAO robot acquires voice played by the first NAO robot through a channel of an equipped audio device and converting the voice to an audio file in a wav format; a terminal device connected with the second NAO robot calls Baidu voice recognition REST API to perform voice recognition on the audio file collected by the second NAO robot, performs treatment on the voice recognition result and sends the treatment result to the second NAO robot; the second NAO robot performs voice feedback on the treatment result so as to realize interaction. According to the invention, a control platform Choregraphe software ofthe NAO robot calls the Baidu voice recognition REST API to perform voice recognition on a remote server, so that voice recognition becomes more effective, quick and accurate; and conversation treatment is performed on a computer connected with the anthropomorphic robots aiming at the recognized voice, so that voice communication employing the two anthropomorphic robots is realized.

The invention relates to a Nao robot path planning method based on a deep Double-Q network, which aims at an uncertain environment, utilizes local information acquired by a robot to realize active obstacle avoidance in an indoor environment, plans a path to reach a set target point, and improves the generalization ability of a common path planning algorithm. Through preprocessing training environment data to approach local environment information which can be acquired by a robot in a real scene and setting a proper state space, a proper action space and a proper reward function, the method can directly utilize the acquired local environment information to perform effective obstacle avoidance and path planning in an unknown environment; the method overcomes the defect that a traditional algorithm needs to obtain sufficient environmental information and perform modeling again to explore the environment to a certain extent, improves the generalization ability of the algorithm, and is beneficial to solving the problem of path planning in an unknown environment.

The invention discloses a rapid and high-accuracy NAO type soccer robot visual processing method which comprises the following specific implementation steps: firstly, operating a BHuman robot drive, synchronously operating a software system at the same time, and carrying out image information transmission with a robot; then, calculating and processing images by a well packaged modular algorithm in a driving core algorithm processing library; for a test mode, firstly starting a system daemon process, calling a GUI graphical debugging interface to display an image and output information, and driving a well packaged core algorithm processing module to calculate and process the images. Computer vision and instruction set optimization technology is utilized to carry out rapid assembly line processing and operation on image signals, so that a high-performance robot vision processing algorithm process is realized, and a software system realized by the vision processing method can be simply and rapidly applied to an NAO robot and has high practicability. And the accuracy and the efficiency of robot football match visual processing are greatly improved.

The embodiment of the invention provides a task execution method, a robot, a storage medium and a computer program product so as to flexibly and efficiently complete execution of robot tasks. According to the embodiment of the invention, any task can be disassembled layer by layer, the method is suitable for all tasks, and any complex task can be disassembled. According to the embodiment of the invention, any task can be scheduled layer by layer, all levels are mutually independent, and the scheduling process is completed in order according to the levels of the sub-tasks until a hardware execution mechanism configured by the robot is controlled to execute corresponding actions, so that the corresponding task is completed. Therefore, the task execution method provided by the embodiment of the invention can be suitable for scheduling design of any robot task, so that the robot can flexibly and efficiently complete execution of all tasks.

The invention provides an intelligent robot for adjuvant therapy of autistic children. The intelligent robot comprises a vision recognition module and an intelligent question and answer module, wherein on-site finding, moving and rotary finding are adopted in the search path to achieve 360-degree full-view search; target color recognizing is carried out on the basis of YUV color space; for targettracking, a target is always achieved in the view center algorithm, a method of cloud voice recognition is used, an NAO robot obtains voice questions of a user, the voice questions are uploaded to a web cloud to recognize, and return recognition characters are subjected to corresponding question analyzing and answer searching processing; the emotion of the autistic children is recognized, and corresponding motion is executed; and voice of the autistic children is recognized, and corresponding motion is executed. The intelligent robot has the beneficial effects that a music bank with rich content and various types is constructed, the conversation ability of the autistic children is reinforced through intelligent chat, and therefore the therapy effect of the autistic children is improved remarkably.

The invention discloses a system for grabbing an object based on an NAO robot. The system comprises a first acquisition module, a second acquisition module, a third acquisition module, a first obtaining module, a fourth acquisition module, a fifth acquisition module and a second obtaining module. The first acquisition module is used for acquiring first center point pixel coordinates. The second acquisition module is used for acquiring the first function relation between the head height change value of the NAO robot and the pitch angle. The third acquisition module is used for acquiring the second function relation between the distance between the target object and the NAO robot and the pitch angle. The first obtaining module is used for obtaining second center point pixel coordinates of an image. The fourth acquisition module is used for acquiring the horizontal deflection angle and the vertical deflection angle of the target object relative to the NAO robot. The fifth acquisition module is used for acquiring the distance between the target object and the NAO robot. The second obtaining module is used for obtaining the walking path of the NAO robot. The technical problem that a system for grabbing an object in the prior art is not high in locating precision and poor in real-time performance is solved.

The invention discloses a method for controlling an NAO robot to move based on an MATLAB application program interface, and belongs to the technical field of intelligent robots. The control method comprises the following steps: firstly, inputting a digital label instruction at an MATLAB end; connecting a client established on MATLAB based on a TCP / IP protocol with an IP address and a port number of the NAO robot, and then sending an instruction; setting up a server on control software of the NAO robot, and receiving an instruction through the TCP / IP protocol; after the instruction is received,enabling each digital label instruction to correspond to one action of the NAO robot, and controlling the NAO robot to execute the action of the corresponding label by operating NAO robot control software; and enabling the NAO robot to receive the corresponding digital label instruction to complete the corresponding action. The NAO robot is controlled to move on the basis of the MATLAB application program, the method for controlling the NAO robot to move on the basis of the MATLAB application program is provided, and obstacles encountered by MATLAB fans when the MATLAB fans play and rotate the NAO robot are eliminated.

The present invention relates to a socket-based asynchronous communication method, storage medium and processor. The asynchronous communication method includes: a first client in a machine device sends a connection request message to a second server in any other machine device ; After the connection is successful, the second server sends a feedback signal of successful connection to the first client, and the first client communicates with the second server; the second server informs the second client in the machine device of the successful connection information; The second client sends a connection request to the first server in the machine where the first client is located; after the connection is successful, the first server sends a feedback signal of successful connection to the second client, and the second client communicates with the first server ; It can realize asynchronous communication connection, satisfy simple and expandable point-to-point communication, not only satisfy the vascular interventional system that affects navigation, but also apply to any robot-assisted interventional surgery system, which is more universal.

The invention discloses an audio and video data acquisition system based on an NAO robot. A binocular camera and a microphone of the NAO robot are controlled to collect audio and video data. The system comprises an audio collection module used for controlling the robot to collect the audio data, select a sound channel and transmit the collected data to a PC terminal to store a selectable path; a video collection module used for controlling the robot to collect video data, displaying camera images in real time and transmitting the collected data to the PC end to store optional paths; an audio and video collection module used for controlling the robot to simultaneously collect audio and video data, select a sound channel, display an image of the camera in real time, and transmit the collected data to the PC end to store a selectable path; an audio playing module used for selecting and playing the recorded and stored audio file for a user to check; and a video playing module used for selecting the recorded and stored video file and playing the video file for a user to view.

The invention discloses a brain-controlled robot system based on a multivariate synchronous exponential algorithm. The invention belongs to the field of brain control. The system comprises an electroencephalogram acquisition module, an online algorithm module, an interactive application module and a feedback module, wherein the online algorithm module comprises a signal calculation module, a calculation platform and a signal frequency identification module; wherein the interactive application module comprises a robot, a circulating receiving module and an interface building module for real-time and ordered instruction transmission. Sine coding stimulation is adopted in the design of a stimulation interface, and stable stimulation can be generated, so that a high-quality steady-state visual evoked potential is induced; an online algorithm adopts a multivariate synchronization index algorithm without training, and results can be classified in real time; an interface between the Matlab and the NAO robot is established by adopting a TCP / IP, and has the advantages of high real-time performance, order arrival of instructions and the like; and finally, all the adopted devices are wireless devices, so that the device is convenient to carry.

The invention discloses a gait optimization method of ball searching of an NAO robot. The method comprises the steps of: searching, confirming and identifying a football by an NAO robot head camera for locking, and calculating an azimuth angle difference between the football and the NAO robot; if the angle difference is smaller than 75 DEG C, employing a mode of shaking legs originally given by anNAOqi system up and down for rotation; if the angle difference is larger than 75 DEG C and smaller than 105 DEG C, employing a library file with a steering angle of 90 DEG C, and performing small-amplitude angle regulation in the process of the robot going ahead and approaching the football; if the angle difference is in a range of 105-135 DEG C, employing a library file with a steering angle of120 DEG C for sliding steering; and if the angle difference is in a range of 135-180 DEG C, employing a library file with a steering angle of 150 DEG C for sliding steering. The turn-back process of the robot is changed to direct adoption of flexible rotation between joints of legs to allow the legs and the soles to directly generate sliding on the ground so as to maintain good stability.

The invention discloses an auxiliary teaching system and method based on an NAO robot, and the auxiliary teaching system comprises: a visual recognition module which recognizes the movement of a userthrough an image photographed by an NAO camera or a recorded video, and carries out the corresponding reaction; aan intelligent interaction module; an NAO robot which performs emotion expression in amode of combining body movement with voice, and then calls a voice function in a system server by utilizing a network communication function, so that communication with a user is realized; a basic sensing module, wherein an NAO robot responds to stimulation of basic information and can find a person and interact with the person; and an action execution module is used for recognizing voice, whereinthe NAO robot executes corresponding actions set by the system.