LG-VIWO: Visual-Inertial-Wheel Odometry Leveraging the Depth-Aided Local Ground Constraints for Mobile Robots

Abstract

Visual-inertial odometry (VIO) has been widely applied in mobile robots due to its low cost and versatility. However, the planar motion of mobile robots leads to the degradation of observability in VIO, while slope variations in outdoor environments invalidate the global planar assumption of existing VIO methods, resulting in a reduction in localization accuracy. To address these issues, this paper proposes a novel depth-assisted tightly coupled optimization framework for visual-inertial-wheel odometry. By extracting the local ground as a key reference plane and incorporating the geometric relationship between the mobile robot and the local ground, novel height and attitude constraints are proposed, enabling the framework to effectively suppress drift in the vertical direction as well as in the roll and pitch degrees of freedom. First, voxel filtering is applied to downsample the dense 3D point cloud generated by the depth camera, which reduces computational complexity while removing noise points from the raw point cloud. Subsequently, the RANSAC plane fitting method is employed to robustly identify local ground planes in environments with noise and dynamic objects. Finally, height and attitude constraints are designed based on the local ground plane parameters, and these are integrated with visual reprojection constraints and inertial-wheel preintegration constraints into the tightly coupled optimization framework to further improve pose estimation accuracy. We evaluate the performance of the proposed method using the KAIST Complex Urban Dataset and real-world experiments, and compare it with state-of-the-art visual-inertial methods such as VINS-Fusion and VIW-Fusion. The results demonstrate that the proposed method achieves high accuracy in mobile robot localization and exhibits greater robustness in uneven terrains and dynamic urban environments.