Seminar: The Importance of Coordinate Frames in Dynamic SLAM, 28th March, 1:00pm
When: Thursday 28th of March, 1:00pm AEDT
Where: This seminar will be partially presented at the ACFR lab lvl 4 conference room (J18) and partially online via Zoom. RSVP
Speaker: Jesse Morris, Yiduo Wang, Dr Viorela Ila
Title: The Importance of Coordinate Frames in Dynamic SLAM
Abstract:
Most Simultaneous localisation and mapping (SLAM) systems have traditionally assumed a static world, which does not align with real-world scenarios. To enable robots to safely navigate and plan in dynamic environments, it is essential to employ representations capable of handling moving objects; therefore Dynamic SLAM is an emerging field in SLAM research as it improves the overall system accuracy while providing additional estimation of object motions. State-of-the-art literature informs a variety of solutions for Dynamic SLAM and can be categorised into two main formulations, representing dynamic object points in either the world or object coordinate frame. While expressing object points in their local reference frame may seem intuitive, it does not necessarily lead to the most accurate and robust solutions. We conduct and present a thorough analysis of various Dynamic SLAM formulations, identifying the best approach to address the problem. To this end, we introduce a front-end agnostic framework using GTSAM that can be used to evaluate various Dynamic SLAM formulations.
Bio:
Jesse Morris – Jesse is a second year PhD student at the ACFR supervised by Dr. Viorela Ila, focusing on Visual SLAM in Dynamic Environments. He completed his bachelor’s in Mechatronic Engineering and Computer Science at the University of Sydney in 2022.
Yiduo Wang – Yiduo is a postdoctoral researcher who joined ACFR under Dr. Viorela Ila in 2022. He was a DPhil student at the Oxford Robotics Institute (ORI) and a member of the Dynamic Robots Systems Group (DRS) under Assoc. Prof. Maurice Fallon. He holds an MRes Robotics degree awarded by UCL, where he worked with Prof. Simon Julier.
Viorela Ila – I am senior lecturer with The University of Sydney, School of Aerospace, Mechanical and Mechatronic Engineering. My research interests span from robot vision to advanced techniques for SLAM and 3D reconstruction based on cutting-edge computational tools such as graphical models, modern optimization methods and information theory.