Feature based navigation and localization of Autonomous Underwater Vehicles (AUVs)

• Main Authors: Balasuriya, Arjuna Prabhath, Wijesoma, Wijerupage Sardha
• Other Authors: School of Electrical and Electronic Engineering
• Format: Research Report
• Language: English
• Published: 2008
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Control and instrumentation::Robotics
• Online Access: http://hdl.handle.net/10356/14509
• Institution: Nanyang Technological University

Under this project research and development work is carried out to introduce on-board intelligence for Autonomous Underwater Vehicles (AUVs). Techniques and algorithms are proposed for underwater localization and map-building using sonar and optical imaging. Underwater positioning is one of the biggest challenges faced by AUV community due to the unavailability of a global positioning system (GPS). The complex nature in the highly hostile underwater environment makes most of the commercially available sensor data corrupt with noise. In this project, new technologies are proposed to fuse different sensor modalities to obtain a reliable update of the state of the vehicle as well as its operating environment. Initially, a test-bed AUV platform is designed and built at NTU, called the ‘NTU_UAV’ to test the performance of the new research ideas in the hostile under sea environment. The in-house built NTU_UAV has a re-configurable structure enabling researchers to change the software/hardware architecture on-site for different applications. Tetherless NTU_UAV has successfully demonstrated its autonomous maneuvers in applications such as sea-bed following. Under this project, sonar/optics based AUV navigation algorithms are developed and their performances are tested in real-world conditions.