Praxis Der Forschung: Localization of a Robotic Platform Using Arcore

Praxis Der Forschung: Localization of a Robotic Platform Using Arcore

Fakultät für Informatik Institut für Anthropomatik und Robotik Lehrstuhl für Intelligente Sensor-Aktor-Systeme (ISAS) Intelligente Prof. Dr.-Ing. Uwe D. Hanebeck Sensor-Aktor-Systeme Praxis der Forschung: Localization of a Robotic Platform using ARCore Contact: Dipl.-Inf. Antonio Zea Email: [email protected] Keywords: Tracking, Localization, Indoor Navigation, Computer Vision In the last few years, visual odometry has made large strides both in robustness and resource efficiency. The idea in this field is to allow for the real-time localization of a camera by finding certain markers or features in a video image, and then estimating their three-dimensional position in the world. Then, by following their motion in successive frames, it is possible to obtain the position and orientation of the camera accurately, without requiring additional hardware or changes in the infrastructure. The entrance of giants such as Google and Apple in the last few months has further revolutionized the field, allowing for visual odometry to be usable even in small devices such as smartphones. While their main target is the field of augmented reality, the tracking algorithms can also be used in many other applications. In this project, we want to explore the applicability of Google's ARCore for use in robotic indoor localization and navigation. The idea is to attach a smartphone on a small moving robotic platform, called Omnimover, to allow it to locate itself as it carries a load to a given location. This task is not straightforward, as the robot needs to know its absolute starting position, avoid sensor drift, detect and move around obstacles, and solve many other issues. Robustness must also be taken into account, given that the robot needs to work in a large variety of scenarios and environments. Work Packages: • Learn about programming in Android and game engines (such as Unreal or Unity) • Research algorithms for detection of fiducial markers using OpenCV • Implement a procedure for the platform to find its starting pose based on found markers • Find a mechanism to detect obstacles using the sparse point cloud provided by ARCore Requirements: • Solid programming skills. The languages used in the project are C#, Java, and some C++ • Knowledge of basic linear algebra (transformations, coordinate systems, etc.) • Background in computer vision preferred • You enjoy working independently, researching on your own, and improvising solutions 1.

View Full Text

Details

  • File Type
    pdf
  • Upload Time
    -
  • Content Languages
    English
  • Upload User
    Anonymous/Not logged-in
  • File Pages
    1 Page
  • File Size
    -

Download

Channel Download Status
Express Download Enable

Copyright

We respect the copyrights and intellectual property rights of all users. All uploaded documents are either original works of the uploader or authorized works of the rightful owners.

  • Not to be reproduced or distributed without explicit permission.
  • Not used for commercial purposes outside of approved use cases.
  • Not used to infringe on the rights of the original creators.
  • If you believe any content infringes your copyright, please contact us immediately.

Support

For help with questions, suggestions, or problems, please contact us