3 results about "Robot software" patented technology

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.

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.