13 results about "Robot software" patented technology

A system and method of undoing capability intent actions of an artificial intelligence (AI) productivity tool chatbot software application comprising processing a received first user-query input and generating a query intent action, correlating a capability intent action with the user-query inputs by invoking an ML model algorithm to correlate the query intent value to a capability intent value for a capability to be executed by an AI productivity tool-enablable software application as a responsive capability intent action, initiating the capability intent action and identifying a negated intent that describes a reversing action that may be executed to reverse the capability intent action that is correlated to the first user query input, and generating a system state defining the state of the information handing system prior to the capability intent action being executed by the AI productivity tool-enablable software application.

The invention provides a task processing method and a robot, the robot comprises a classifier, a task machine and a process state machine, the method comprises the following steps: the classifier determines whether a target task is a process task, if yes, task information corresponding to the target task is sent to the task machine, if not, a task type corresponding to the target task is determined, and the task type corresponding to the target task is sent to the task machine; and sending task information corresponding to the target task to a process state machine according to the task type. The task machine preprocesses the task information to enable the task information to meet task execution requirements corresponding to the process task, and then sends the task information to the process state machine; and after receiving the task information, the process state machine executes a task process corresponding to the target task. The target task is an intelligent agent task sent by a large language model corresponding to the robot, and the process task is a task comprising a plurality of different types of tasks. Therefore, the intelligent agent task can be better processed by the robot, the performance of the robot is improved, and the software development and maintenance cost of the robot is reduced.

The application discloses a robot skill primitive library automatic generation method and system based on a large language model, and relates to the fields of artificial intelligence and robot software engineering. The method comprises the following steps: adopting a double-level function extraction strategy to extract modular functions and process scripts in a robot code library from a robot task-level python file; based on the extracted robot function code, adopting a preset thinking chain prompt word to guide a large language model to generate global semantic description and to distinguish functions with the same name; based on the function metadata of the robot task level after the same name function is distinguished, adopting a preset thinking chain prompt word to guide the configured large language model to perform perception type code reconstruction with embedded field constraints; based on the reconstructed code, adopting a preset thinking chain prompt word to guide the configured large language model to perform adaptive iterative code evaluation and optimization closed loop to obtain a robot skill primitive library. The application can automatically and reliably generate a robot skill primitive library.

The invention relates to the technical field of robot software architecture and distributed systems, in particular to a data flow driven robot low-delay communication system and method. The system comprises a middleware scheduler, a sender computing node and a receiver computing node. And the middleware scheduler is used for loading a predefined data stream topology description file to declare all permitted communication paths, and performing admission verification on a data stream sending request according to the file. And the sender computing node is used for initiating a sending request and writing to-be-sent data into the shared memory area in a unified memory layout format after verification is passed. And the receiver computing node is used for registering a receiving intention and directly reading the written data in the shared memory area according to the indication of the middleware scheduler after the receiving intention passes the verification. According to the method, the defects of the existing open type robot middleware in the aspects of safety, real-time performance and resource utilization rate are systematically solved.

The invention relates to a humanoid robot OTA automatic upgrading method and system, and relates to the field of robot software maintenance, and the method comprises the steps: determining a target robot set based on robot state information; issuing batch upgrading tasks to the target robot set, and performing installation and upgrading by using a silent installation method; collecting the current battery electric quantity of the robot; if the current battery electric quantity is lower than the upgrading maintaining threshold value, determining a nearest target charging area according to the current robot position; an idle robot is determined based on the current robot position, the idle robot is controlled to carry the current robot to the target charging area for charging, and meanwhile the silent installation process is completed in the target charging area; and after the installation upgrade is completed, automatically running a self-checking program to verify the core function, and when an upgrade self-checking result accords with a preset self-checking requirement result, marking the upgraded version information as upgrade success and reporting the upgraded version information to the cloud management platform. The method has the effect of improving the upgrading efficiency of the robot.

The present application relates to a kind of humanoid robot OTA automatic upgrading method and system, it relates to the field of robot software maintenance, it includes: based on robot state information to determine target robot set;Batch upgrade task is issued to target robot set, and is installed and upgraded with silent installation method;Current battery capacity of robot is collected;If current battery capacity is lower than upgrade maintenance threshold, determine the nearest target charging area according to current robot position;Based on current robot position to determine idle robot, and control idle robot to carry current robot to target charging area and charge, while completing silent installation process in target charging area;After installation upgrade is completed, automatically run self-checking program to verify core function, when upgrade self-checking result meets the preset self-checking requirement result, mark the version information after upgrade as upgrade success and report to cloud management platform.The present application has the effect of improving the upgrading efficiency of robot.

A machine for machining and / or measuring gearing, having two or more numerically controlled machine axes for carrying out machining movements and / or measuring movements, having a machine controller, wherein the machine controller has a control software, wherein the control software is set up for executing machine functions, such as executing program sequences for controlling the numerically controlled machine axes, the output of service reports or the like. The machine controller has a user interface set up for interaction with a machine operator, wherein for at least one of the machine functions it is predetermined by the control software that the execution of this machine function requires at least one manual input by a machine operator at the user interface. A bot software is assigned to the control software in order to replace the at least one manual input and to execute the machine function independently of a machine operator.

The application discloses a method and device for configuring software of a sweeping robot, electronic equipment and a storage medium, and applies to the technical field of computers. The method for configuring the software of the sweeping robot comprises the following steps: obtaining modification data corresponding to client software of the sweeping robot, and obtaining a modified configuration file according to the modification data; selecting environment configuration data matched with environment parameters corresponding to the modification data in the configuration file according to the environment parameters; and analyzing target configuration data corresponding to the environment configuration data by the client software of the sweeping robot, so as to complete the configuration of the modification data. The application solves the technical problem of low development efficiency of the software of the sweeping robot.

This application discloses an automated method and system for generating a robot skill primitive library based on a large language model, relating to the fields of artificial intelligence and robotics software engineering. The method includes: extracting modular functions and procedural scripts from the robot's task-level Python files using a two-level function extraction strategy; based on the extracted robot function code, using preset thought chain prompts to guide the large language model in generating global semantic descriptions and disambiguating functions with the same name; based on the robot task-level function metadata after disambiguation, using preset thought chain prompts to guide the configured large language model in perceptual code reconstruction with embedded domain constraints; and based on the reconstructed code, using preset thought chain prompts to guide the configured large language model in adaptive iterative code evaluation and optimization loops to obtain the robot skill primitive library. This application can generate a robot skill primitive library fully automatically and with high reliability.

The application relates to the technical field of robot control, in particular to a self-adaptive robot driving system based on an RT-Thread, which comprises a power module, an integrated main control module, a motor driving module and a serial port transmission module; wherein the power module is used for providing power supply and monitoring the battery voltage in real time; the integrated main control module is used for carrying a real-time thread operating system and scheduling different function modules; the motor driving module is used for configuring the motor of a driving chassis and executing robot moving operation; and the serial port transmission module is used for reserving a serial port for communication connection and data transmission. The self-adaptive robot driver using the RT-Thread operating system is built by fusing the motor and sensor data accessed by the driving system, the special posture of the vehicle body can be detected in time and real-time control is carried out, and the convenience of robot software and hardware integration is greatly improved.

Machine (2) for machining and / or measuring gears, with two or more numerically controlled machine axes for performing machining and / or measuring movements, with a machine control (10), wherein the machine control (10) comprises control software (12), wherein the control software (12) is configured to execute a plurality of machine functions (F1, F2... FN), such as executing program sequences for controlling the numerically controlled machine axes, outputting service reports, or the like, wherein the machine control (10) comprises a user interface (14), wherein the user interface (14) is configured for interaction with a machine operator, wherein for at least one of the machine functions (F1, F2... FN) the control software (12) specifies that the execution of this machine function (F1, F2...FN) requires at least one manual input by a machine operator at the user interface (14), wherein the control software (12) is associated with a bot software (20) to replace the at least one manual input and to execute the machine function (F1, F2... FN) independently of a machine operator.

The invention relates to a machine tool (2) for machining and / or measuring teeth, comprising two or more numerical control spindles for carrying out machining and / or measuring movements, comprising a machine tool control system (10), which has control software (12), the invention relates to a machine tool control system (10) for a numerical control spindle (12), comprising control software (14) which is designed to carry out a plurality of machine tool functions (F1, F2... FN), such as to carry out program flows for controlling the numerical control spindle, to output service reports or the like, having a user interface (14) which is designed to interact with a machine tool operator, according to the invention, the control software provides that at least one manual input is required by a machine tool operator on the user interface to carry out the machine tool function, and the control software is provided with robot software in order to replace the at least one manual input and carry out the machine tool function independently of the machine tool operator.

The application provides a task processing method and a robot, the robot comprising a classification machine, a task machine and a process state machine, the method comprising: the classification machine first determining whether a target task is a process task, if yes, sending task information corresponding to the target task to the task machine, if not, determining a task type corresponding to the target task, and sending the task information corresponding to the target task to the process state machine according to the task type. The task machine pre-processes the task information to make it meet the task execution requirements corresponding to the process task, and then sends it to the process state machine. After receiving the task information, the process state machine executes a task process corresponding to the target task. The target task is an agent task sent by a large language model corresponding to the robot, and the process task is a task comprising multiple different types of tasks. In this way, the robot can better process the agent task, improve the performance of the robot, and reduce the software development and maintenance cost of the robot.