New SLAM System Enhances Robot Navigation by Integrating Self-Dynamics
A research team has developed a new Simultaneous Localization and Mapping (SLAM) system designed to improve robot navigation, particularly in challenging environments where rapid movement can compromise camera-based visual information. This innovative framework combines visual data from cameras with input from an inertial measurement unit (IMU). The system leverages the robot's own self-dynamics to predict feature motion, represent coupled motion states, and correct accumulated navigation drift. This approach has demonstrated stronger tracking capabilities during rapid movement, vibrations, dim lighting conditions, and significant illumination changes, all while maintaining real-time operation. The research, published online on May 12, 2026, in CAAI Transactions on Intelligence Technology, was conducted by researchers at the National Key Laboratory of Machine Perception, Shenzhen Graduate School, Peking University; the Shenzhen Institute of Artificial Intelligence and Robotics for Society; and The Chinese ...
