44 results about "Cloud robotics" patented technology

The present disclosure discloses a cloud robot system, including: a cloud computing platform and at least one robot; wherein the cloud computing platform is used for receiving perform information sent by the at least one robot in the system; the perform information includes data, status and requests of the at least one robot; the cloud computing platform is used for processing the data and status, sending process results back to the at least one robot, and sending control instructions to corresponding robot according to the requests; the at least one robot is used for sending the perform information to the cloud computing platform, receiving process results from the cloud computing platform, and performing according to the control instructions sent from the cloud computing platform. By using the present disclosure, computing ability and storage capacity of the robots can be expanded unlimited, while the thinking ability and memory of the robots are improved. Besides, the ability of the brains of the robots can be allocated according to demand, thus lowering the cost of the robots.

The invention discloses a system and a method for navigating an indoor cloud robot. The system comprises a cloud terminal, wherein the cloud terminal is connected with a UWB base station group and a robot group respectively; the UWB base station group is configured to detect the positions of corresponding robots in the robot group in a global environment and feeding back the detected positions tothe cloud terminal; the cloud terminal is configured to send a navigation command to an appointed robot and receive the local minimum subgraph of the current position constructed by the appointed robot; the cloud terminal is configured to determine the orientation of the robot by using the local minimum subgraph of the current position constructed by the appointed robot and the position in the global environment; the cloud terminal is configured to download the pre-planning global path of the appointed robot from the current position to a navigation end point and a middle navigation point; thecloud terminal is configured to receive the local minimum subgraph of the appointed robot at the middle navigation point, optimize the posture of the current robot in combination with the position inthe global environment and then optimize the global path and adjust the middle navigation point; and the cloud terminal is configured to download the optimized global path, the posture and the middlenavigation point to the appointed robot for continuous navigation until a navigation end point is reached.

The invention provides a cloud robot distributed control system and a method based on a dynamic Agent. The system comprises a knowledge base Agent and a core Agent. The method comprises the steps of building a cloud robot ROS (Read-Only-Storage) node; deploying the knowledge base Agent; receiving a task instruction through a cloud robot, connecting the core Agent to an Internet so as to build reliable communication connection between the core Agent and the knowledge base Agent, and applying to the knowledge base Agent for downloading; receiving a download request through the knowledge base Agent, searching for a corresponding function application, downloading the corresponding function application into an operating system ROS of a local cloud robot, and regarding the corresponding function application as the dynamic Agent; activating the dynamic Agent through the core Agent, executing the task through the core Agent, and returning a task execution result to a user through the core Agent; and after the completion of the task, controlling the dynamic Agent to unload a cloud computing Agent through the core Agent, then unloading the dynamic Agent through the core Agent, and realizing dynamic unloading. According to the cloud robot distributed control system and the method based on the dynamic Agent provided by the invention, the problem that the computing capacity and the functions are limited when the cloud robot executes the complex task is solved, the on-demand loading and the dynamic unloading of the cloud robot functions are realized, and the computing resources and the storage resources of the cloud robot can be saved.

The invention discloses a cloud robot interactive method and cloud robot based on a cloud platform and the cloud platform. The method comprises the following steps that according to an obtained imageof surrounding environments, image processing is carried out, whether obstacles exist in the surrounding environments or not is judged, planned obstacle avoidance path information is received, obstacle avoidance is completed according to the planned obstacle avoidance path information, and an interaction including sending information to the cloud platform and receiving the information sent by thecloud platform can be carried out through a transmission control protocol / an internet interconnection protocol and the cloud platform. In this way, effective obstacle identification of the cloud robotand the obstacle avoidance can be realized, data transmission is stable, and the probability of packet loss is less in the process of the data transmission.

The invention provides an AR-glasses-based cloud robot holographic evaluation system and method. The system comprises local equipment and a robot cloud platform system, wherein one set of local equipment is provided for each remote user, and data interaction among all the remote local equipment is achieved through the robot cloud platform system. The method allows two users to use the system to perform robot holographic evaluation. The AR-glasses-based cloud robot holographic evaluation system and method has the advantages that the actions, three-dimensional model modification and voices of aremote engineer can be transmitted to another engineer who communicates with the remote engineer so as to achieve holographic communication, the own-side engineers can learn about the sight, actions,holographic model operation and voices of the opposite-side engineers, the on-site robot evaluation process of robot equipment is restored to an extremely large extent, efficiency is increased, and the cycle of remote evaluation is shortened.

The invention relates to a multi-robot controller based on an edge cloud service. The multi-robot controller based on the edge cloud service is applied to a multi-robot cooperative control operation scene in a distributed network environment under an edge cloud architecture. The multi-robot controller conforms to the edge cloud technology category and is equipped with a high-performance CPU+FPGA heterogeneous acceleration framework and multiple sets of physical network interfaces, so that edge cloud robot application remote deployment is supported, and multi-robot control model calculation anddistributed collaborative control are realized. In addition, in order to realize multi-robot cooperative control, virtualization technology is adopted to uniformly control hardware resources, networkresources and storage resources of the controller, a high-speed data buffer is created for multi-robot data sharing, and thus integrated high-performance multi-robot control is realized.

The invention provides a cloud robot resource scheduling method and system based on task classification and time sequence prediction, and relates to the technical field of cloud computing resource scheduling, and the method comprises the steps: S1, obtaining a job task sequence of a cloud robot; S2, classifying the tasks according to the dependency relationship between the cloud robot operation tasks and the cloud virtual machine; S3, obtaining an estimated value of the job duration of each job task; S4, converting cloud robot operation task scheduling into a workflow scheduling problem expressed by a directed acyclic graph (DAG); S5, simplifying the DAG generated in the step S4 according to the characteristics of the job task; and S6, solving the final DAG by using various static scheduling methods. According to the method, static analysis can be finally carried out on the operation task of the cloud robot through some preprocessing means, and a better solution for the scheduling problem can be found from the global perspective.

The invention discloses a semantic map construction method based on cloud robot hybrid cloud architecture, aiming to achieve a proper balance between improving the accuracy of object recognition and shortening the recognition time. The technical solution is to build a hybrid cloud composed of robots, private cloud nodes, and public cloud nodes. The private cloud nodes obtain environmental pictures, odometer and location data taken by the robot based on the ROS message mechanism, and use SLAM to draw the environment in real time based on the odometer and location data. Geometric map. The private cloud node performs object recognition based on the environment picture, and uploads the object that may be misrecognized to the public cloud node for recognition. The private cloud node maps the object category identification label returned by the public cloud node with the SLAM map, and marks the object category identification label on the corresponding position of the map to complete the construction of the semantic map. By adopting the invention, the local calculation load of the robot can be reduced, the request response time can be minimized, and the accuracy of object recognition can be improved.

The invention discloses a task scheduling method for a cloud robot, and the method comprises the steps: firstly calling a preset random coding function to carry out the random coding of a target feature attribute of the cloud robot corresponding to a target scheduling task, and obtaining a plurality of different initial feature codes; calling a preset genetic algorithm, and determining a target feature code with the highest fitness with the target scheduling task according to the initial feature code; and determining corresponding target feature attribute information according to the target feature code, and scheduling a corresponding target robot according to the target feature attribute information. According to the method, the consumption of human resources is reduced, the task scheduling efficiency is improved, the influence of personal subjective factors of workers can be effectively avoided, and the optimization of the formulated task scheduling scheme of the cloud robot is improved. The invention further discloses a task scheduling device and equipment of the cloud robot and a computer readable storage medium, which all have the above beneficial effects.

The invention discloses a cloud robot system. The system comprises a cloud server platform and an entity robot; the cloud server platform comprises a cloud robot engine module and a cloud programming engine module; the cloud programming engine module carries out signal transmission between the cloud server platform and the cloud robot engine module, and the entity robot carries out signal transmission with the cloud robot engine module in a cloud service manner; the entity robot comprises a plurality of hardware function modules; the hardware function modules follow the hardware function module standard, and due to the hardware function module standard, the hardware function module can carry out registering and adding in a cloud service manner. According to the cloud robot system, the hardware cost of the robot is reduced, the reusability and maintainability of the system are improved, rapid calling and command treatment of the robot under the familiar site are used for conducting the execution action, and richness of intelligent services of the robot is ensured.

A vehicle remote support system includes a communication system that operates over a plurality of parallel wireless network connections to provide low-latency video from vehicle to a remote support server that provides remote support to the vehicle dependent on real-time video. The vehicle includes a source that encodes multiple versions of the original video segments (e.g., one per wireless network connection) and transmits the multiple versions of the segments to a sink at the remote support server over the respective wireless connections. This redundant multi-path communication system rationally allocates network resources to the managed video streams and balances bandwidth against latency in order to avoid network congestion and safety issues associated with single-path transmissions. In other embodiments, a similar communication system that transmits video or other real-time messages between a source and a sink may be utilized in cloud robotics applications.

The invention discloses a cloud robot task assignment method that jointly considers base station selection and computing migration, including dividing a single robot r task w into five parts, dividing the completion time t of a single robot task w w Use the accumulation of the above five parts to establish a task allocation model; input the task set W of multiple robots r, the robot set R, the base station set B, and upload the corresponding configuration parameters of each task w to the cloud to the task allocation model t w ;Assign task to model t w It is sequentially decomposed into two sub-models to complete the minimization time of all tasks step by step, wherein the first sub-model is a model based on the simulated annealing algorithm; the second sub-model is a model based on the Hungarian algorithm. In the present invention, firstly, the target task is functionalized, and the time to complete all tasks is minimized. Among them, task layout, calculation migration and base station selection are three variables, and then a heuristic algorithm is proposed, which can obtain the allocation strategy of multiple tasks in a short time.

The invention discloses a method for optimizing the time delay of a cloud robot system with joint optimization. The steps of the method are as follows: input parameter data; define variables; preset the threshold ε of the execution time difference between randomly generated branches, and set the gene algebra threshold n; encode the location point information of the robot to generate a gene; each generation generates multiple sets of genes with different values, and calculates the communication bandwidth of each robot at position k through each gene; solves the linear programming about x and z, and obtains about The solution of the variable, and the communication bandwidth is substituted into the objective function, and the linear transformation is performed to find the optimal solution corresponding to each gene; the 30% genes with the lowest objective function value are screened through the objective function, and new genes are generated through the genetic algorithm; Calculate the optimal solution of the next-generation gene; adjust the gene and the threshold ε according to the above steps to find the optimal solution, output the matrix corresponding to x, y, and z of the optimal solution, and determine the layout plan; send the layout plan to a robot to perform the task .