Relocalization based on millimeter wave radar point cloud for visually degraded environments

Abstract

Simultaneously localization and mapping (SLAM) has been widely used in autonomous mobile systems to fulfill autonomous navigation. Relocalization plays an important role in SLAM for closing the loop and eliminating the drift of pose estimation. Traditional methods mostly rely on LiDAR or camera sensors, which may degrade or even fail in rainy or dusty situations or with large illumination changes. In this article, we explore the use of low‐cost commercial millimeter wave (mmWave) radars and propose a noval mmWave radar point cloud‐based relocalization method. Our method first pre‐processes the radar point cloud and, based on that, achieves fast 3‐DOF pose estimation for the robot. We build a prototype and thoroughly evaluate our method using data sets collected by our platform in four complex environments, including street, park, road, and water surface scenarios. The experimental results show that our method consistently outperforms other baseline methods including the vision‐based counterparts, especially in the visual degraded scenes.

Four-Dimensional (4D) Millimeter Wave-Based Sensing and Its Potential Applications in Digital Construction: A Review

“…In robotics, a 4D mmw radar can be integrated as a perception sensor to enable robots to detect and track objects, relocate, and avoid obstacles in their environment [55][56][57][58], which is similar to the applications in autonomous driving. In addition, some researchers have also applied this technology to develop human-following robots [59] and estimate the velocity of robots in visually degraded environments [60].…”

Advancing robust state estimation of wheeled robots in degenerate environments: harnessing ground manifold and motion states

“…These environments may include weak GNSS signals, limited visibility, complex indoor structures, or harsh climatic conditions. These circumstances can introduce pronounced sensor measurement noise or even failure, thereby detrimentally impacting the robot's state estimation [19]. The selection of proprioceptors (IMUs, encoders) is an effective approach to tackling state estimation challenges of robots in degraded environments.…”