A Novel ViDAR Device With Visual Inertial Encoder Odometry and Reinforcement Learning-Based Active SLAM Method

Abstract--In the field of multi-sensor fusion for simultaneous localization and mapping (SLAM), monocular cameras and IMU s are widely used to build simple and effective visual-inerti al systems. However, limited research has explored the integr ation of motor-encoder devices to enhance SLAM performance. By incorporating such devices, it is possible to significantly improve active capability and field of view (FOV) with minimal additi onal cost and structural complexity. This paper proposes a novel visual-inertial-encoder tightly coupled odometry (VIEO) based on a ViDAR (Video Detection and Ranging) device. A ViDAR calibration method is introduced to ensure accurate initia lization for VIEO. In addition, a platform motion decoupled active SLAM method based on deep reinforcement learning (DRL) is proposed. Experimental data demonstrate that the proposed Vi-DAR and the VIEO algorithm significantly increase cross-fra me co-visibility relationships compared to its correspondin g visual-inertial odometry (VIO) algorithm, improving state estima tion accuracy. The proposed methodolog y sheds fresh insights into both the updated platform design and decoupled approach of active SLAM systems in complex environments. N recent years, visual odometry (VO) and visual-inertial odometry (VIO) have made significant advancements. This work was supported in part by the Beijing Natural Scienc e Foundation under Grant 2022MQ05, in part by the CIE-Tencent Robotics X R hino-Bird Focused Research Program under Grant 2022-07, and in part by the National Natural Science Foundation of China under Grant 62203015, G rant 62303020, Grant 62303021, and Grant 62273351. Zhanhua Xin, Zhihao Wang, Shihan Kong, Y an Xiong, and Junzhi Y u are with the State Key Laboratory for Turbulence and Complex Systems, Department of Advanced Manufacturing and Robotics, C ollege of Engineering, Peking University, Beijing 100871, China (email: xinzhan-hua@stu.pku.edu.cn;