Active View Planning for Visual SLAM in Outdoor Environments Based on Continuous Information Modeling

Visual simultaneous localization and mapping (vSLAM) is widely used in satellite-denied and open-field environments for ground and surface robots. However, due to frequent perception failures derived from featureless areas or the swing of robot view direction on rough terrains, the accuracy and robustness of vSLAM are still to be enhanced. This article develops a novel view planning approach of actively perceiving areas with maximal information to address the mentioned problem; a gimbal camera is used as the main sensor. First, a map representation based on feature distribution-weighted Fisher information is proposed to completely and effectively represent environmental information richness. With the map representation, a continuous environmental information model is further established to convert the discrete information space into a continuous one for numerical optimization in real time. Subsequently, receding horizon optimization is utilized to obtain the optimal informative viewpoints with simultaneously considering the robotic perception, exploration, and motion cost based on the continuous environmental model. Finally, several simulations and outdoor experiments are performed to verify the improvement of localization robustness and accuracy by the proposed approach. We release our implementation as an open-source
¹
package for the community.