3D Map Update in Human Environment Using Change Detection from LIDAR Equipped Mobile Robot

For future mobility services in dynamic human living environment, this paper proposes a map update framework based on a 3D change detection method using a mobile robot equipped with a Laser Imaging Detection and Ranging (LI- DAR) sensor. The proposed framework updates a given 3D map and refines its information effectively to correct inconsistencies between it and the real environment. It is effective for various mobile robots and environments, and the 3D map is updated just by the mobile robot traveling around and observing its surroundings. The change detection method is used to specify the changed (appeared/disappeared) parts from an existing 3D map by comparing it with LIDAR observations while the robot is moving. The experimental results with an indoor mobile robot and outdoor car application show that the proposed framework can exclude noise and disappeared objects, add static appeared objects, and supplement blanks into the given 3D map.

[1]  Armando Sousa,et al.  Robust 3/6 DoF self-localization system with selective map update for mobile robot platforms , 2016, Robotics Auton. Syst..

[2]  D. Girardeau-Montaut,et al.  CHANGE DETECTION ON POINTS CLOUD DATA ACQUIRED W ITH A GROUND LASER SCANNER , 2005 .

[3]  Daniel Cremers,et al.  LSD-SLAM: Large-Scale Direct Monocular SLAM , 2014, ECCV.

[4]  Marc Pollefeys,et al.  Geometric Change Detection in Urban Environments Using Images , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  Hiroshi Mizoguchi,et al.  Real-time 6DoF localization for a mobile robot using pre-computed 3D laser likelihood field , 2015, 2015 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[6]  Mario Fernando Montenegro Campos,et al.  Spatial Density Patterns for Efficient Change Detection in 3D Environment for Autonomous Surveillance Robots , 2014, IEEE Transactions on Automation Science and Engineering.

[7]  Yoko Sasaki,et al.  Long-term demonstration experiment of autonomous mobile robot in a science museum , 2017, 2017 IEEE International Symposium on Robotics and Intelligent Sensors (IRIS).

[8]  Naohiro Uyama,et al.  6-DoF Monte-Carlo localization for hand-held applications based on state vector verification , 2017, 2017 IEEE SENSORS.

[9]  Andreas Nüchter,et al.  The Peopleremover—Removing Dynamic Objects From 3-D Point Cloud Data by Traversing a Voxel Occupancy Grid , 2018, IEEE Robotics and Automation Letters.

[10]  Hiroaki Takada,et al.  Implementation and Evaluation of Local Dynamic Map in Safety Driving Systems , 2015 .

[11]  Paulo Drews,et al.  Fast and adaptive 3D change detection algorithm for autonomous robots based on Gaussian Mixture Models , 2013, 2013 IEEE International Conference on Robotics and Automation.

[12]  Wolfram Burgard,et al.  OctoMap: an efficient probabilistic 3D mapping framework based on octrees , 2013, Autonomous Robots.

[13]  Jiaojiao Tian,et al.  3D change detection – Approaches and applications , 2016 .

[14]  Cyrill Stachniss,et al.  Fast Image-Based Geometric Change Detection Given a 3D Model , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).