Optimal Motion Planning using Sampling-based Motion Planners

Section 347 personnel. Oktay Arslan; Robotics Technologist. Requesters Richard Volpe, Stephanie Cowans Photographer: T. Wynne Date: 19-OCT-2015 Photolab order:070915-143765

Speaker: Oktay Arslan
Affiliation: NASA/Caltech Jet Propulsion Laboratory

Abstract: The robot motion planning problem is a canonical problem in robotics and its applications have become incredibly broad and theoretically deep at the same time. In this talk, I will provide an up-to-date foundation in motion planning field, make the fundamentals of motion planning algorithms accessible to the interested researchers and relate low-level implementation to high-level algorithmic concepts. I will give a survey of state-of-the-art sampling-based planners such as Probabilistic Roadmaps (PRM) and Rapidly-exploring Random Trees (RRT) and their variants with asymptotic optimality guarantees, notably, PRM*, RRT*, RRT#, RRT-X etc. More specifically, I will explain how these algorithms work and guarantee asymptotic optimality, and will reveal some connection to fundamental principles in dynamic programming. The talk will be concluded with some applications of sampling-based planners to real-world problems such as high-level route planning of a full-scale unmanned helicopter, autonomous navigation of Rovers.

Biography:  Oktay Arslan is currently the Robotics Technologist of the Mobility and Robotic Systems Section at the NASA/Caltech Jet Propulsion Laboratory. He was previously a research intern at Mitsubishi Electric Research Laboratories, a robotics software engineer at Aurora Flight Sciences, Inc., and a visiting researcher at Laboratory for Information and Decision Systems at MIT. He received his dual BS degrees in Electrical Engineering (with focus in Control Engineering) and Computer Engineering, an MS degree in Defense Technologies all from the Istanbul Technical University in Turkey. He also obtained his dual MS degrees in Aerospace Engineering and Computer Science, a PhD degree in Robotics all from the Georgia Institute of Technology, USA. His research interests are autonomy, planning, and control for autonomous systems, preferably in the fields of automotive, aerospace and robotics.

For more information, contact Prof. Paulo Tabuada (tabuada@ucla.edu)

Date/Time:
Date(s) - Nov 07, 2016
11:00 am - 12:00 pm

Location:
E-IV Tesla Room #53-125
420 Westwood Plaza - 5th Flr., Los Angeles CA 90095