Research on autonomous navigation and obstacle avoidance algorithms for robotic vacuum cleaners by fusing LiDAR and visual information

Robotic vacuum cleaners have gained popularity in recent years due to advancements in sensor technology, artificial intelligence, and robotics. However, traditional robotic vacuum cleaners often suffer from poor localization accuracy and inefficient cleaning patterns, limiting their adaptability to complex environments. To address these limitations, this study focuses on integrating a LiDAR sensor and a depth camera on a differential-drive robot to achieve precise mapping and localization. The Gmapping simultaneous localization and mapping (SLAM) algorithm is employed to enhance mapping accuracy and efficiency, while the movebase navigation algorithm is used for path planning and improving cleaning performance. Simulation results on the robot operating system (ROS) platform demonstrate that the proposed system can accurately construct a 2D occupancy grid map and effectively cover the cleaning area according to the planned path. The integration of multi-sensor fusion and intelligent algorithms in this study showcases the potential for improving the intelligence and performance of robotic vacuum cleaners, providing valuable insights for the development of advanced service robots.