Note: This content is accessible to all versions of every browser. However, this browser does not seem to support current Web standards, preventing the display of our site's design details.

  

Mixed Integer Programming for Autonomous Vehicle Path Planning

Back
Abstract:
In this talk we will give an overview of recent work in the field of optimal path planning for autonomous vehicles using Mixed Integer Linear Programming (MILP) on the one hand, and using the concept of a Maneuver Automaton on the other hand. MILP can be used to capture non-convex constraints such as obstacle avoidance and collision avoidance between multiple vehicles. We will focus on a receding horizon planning strategy, and discuss the safety issues introduced by this approach. Several applications will be given, including trajectory generation for a small X-Cell helicopter, capable of performing acrobatic maneuvers autonomously.

Type of Seminar:
Public Seminar
Speaker:
Dr. Bernard Mettler and Tom Schouwenaars
Date/Time:
Feb 19, 2003   17:15
Location:

ETZ E6
Contact Person:

F. Borrelli
File Download:

Request a copy of this publication.
Biographical Sketch:
Tom Schouwenaars is originally from Geel, Belgium, and obtained a Masters degree in Electrical Engineering from the Katholieke Universiteit Leuven, Belgium, in 2001. Since September 2001 he is affiliated with the Laboratory for Information and Decision Systems (LIDS) at the Massachusetts Institute of Technology, where he is working towards a PhD degree under the supervision of Prof. Eric Feron and Prof. Jonathan How. His research is on the use of Mixed Integer Linear Programming for path planning of autonomous vehicles. Bernard Mettler is currently a postdoctoral associate at the Laboratory for Information and Decision System (LIDS) at MIT.† He obtained a Diploma in Mechanical Engineering from the Swiss Federal Institute of Technology (ETHZ) in 1996, and a Ph.D. from Carnegie Mellon University (CMU) in 2001.† His doctoral research focused on modeling, identification, flight characteristics, and control of miniature rotorcraft. He published his results in a book (^”Identification Modeling and Characteristics of Miniature Rotorcraft^‘, Kluwer Academic Publishers, Boston, 2002). He also spent two summers as a visiting researcher at the US Army/NASA rotorcraft division. His current research is on guidance systems for unmanned air vehicles operating in confined and challenging environments; he is interested in methods that are computationally efficient and can make full use of the vehicle^“s range of behaviors.