Design and Evaluation of a Cost-Effective Autonomous Outdoor Cleaning Robot for Public Park Environments MinSoo Kim Advisor : Prof. Sung Woo Suk, Ph.D. Department of Smart Vehicle System Engineering Graduate School of Chosun University This study pres...
Design and Evaluation of a Cost-Effective Autonomous Outdoor Cleaning Robot for Public Park Environments MinSoo Kim Advisor : Prof. Sung Woo Suk, Ph.D. Department of Smart Vehicle System Engineering Graduate School of Chosun University This study presents a practical approach to developing a low-cost outdoor cleaning robot for real-world deployment. While indoor cleaning robots are widely adopted, their outdoor counterparts remain costly and less accessible due to unstructured environments and increased system complexity. To address this, we retrofitted an off-the-shelf manual sweeper with minimal hardware: a single 3D LiDAR and a compact onboard computer running an open-source autonomy software stack. This LiDAR-centric design eliminates the need for multi-sensor configurations, significantly reducing both hardware and software complexity without sacrificing performance. We focus on adapting three key autonomy modules, mapping, localization, and planning, for semi-structured park environments characterized by dense vegetation and GNSS-denied conditions. A consistent and loop-closed pointcloud map was generated using a LiDAR SLAM framework. Fast and robust localization was achieved using a map-based pose initializer leveraging vector map priors. Reliable bidirectional edge-following behavior was realized through lanelet-based planning adapted for shared narrow paths. Field tests demonstrated fully autonomous cleaning operation with strong empirical results: loop closure error under 0.1 m, consistently low localization uncertainty, and an average lateral tracking error of approximately 0.14 m. These results validate the feasibility of affordable LiDAR-centric autonomy for outdoor service robots.