Engineering Colloquium Home
Schedule including this lecture.

Goddard Space Flight Center Engineering Colloquium

Date: Monday, March 25, 2002

Title: AI Techniques in Planetary Robotics

Speaker: Ayanna Howard

Abstract

Artificial Intelligence (AI) is the capability of a device to perform functions that are normally associated with human intelligence, such as reasoning and learning through experience. For robotics, this concept means that the system must possess autonomous on-board perception, reasoning, and decision-making capability in order to function in natural environments. The difficulty for planetary robotics is that robust operation must occur at sites that are Unknown, Unsafe, and Unexpected. Additional constraints include the necessity to deal with minimum on-board computational resources and imprecise sensors with low resolution and limited processing power. To address these limitations, we employ approaches that utilize human-inspired techniques, such as neural networks, fuzzy logic, and visual sensing, to develop autonomous planetary robotic systems. This talk will give an overview of the AI techniques used in planetary robotics for NASA and give concrete examples of research that is currently conducted in this area. We will cover recent research focused on the use of fuzzy logic methods for rover navigation, neural networks to assess natural environmental characteristics, adaptive techniques for mimicking human visual perception, and intelligent sensing for reconfigurable robotic systems.

Speaker

Ayanna Howard received her B.S. in Electrical Engineering from Brown University, her M.S.E.E. from the University of Southern California, and her Ph.D. in Electrical Engineering/Computer Science from the University of Southern California, Los Angeles, in 1999. During her career, Dr. Howard has been a key leader in the development of two artificial intelligence packages that utilize genetic algorithms and neural networks to solve real-world problems. She has published over 30 journal articles, conference papers, and technical reports on the successful use of AI techniques in a number of projects — from intelligent terrain assessment algorithms to cognitive sensor technology. Since 1990, she has been at the NASA Jet Propulsion Laboratory, California Institute of Technology, where she has led research efforts on various projects utilizing vision, fuzzy logic, and neural network methodologies. In 2001, Dr. Howard received the Lew Allen Award for Excellence in Research — the highest honor possible at JPL in recognition of significant leadership and technological innovation performed during the early years of an employee's professional career. Her current responsibilities include managing a team of engineers to develop a reconfigurable software/hardware robotic system for use in exploration and leading a technology development effort to create a real-time software package for autonomous rover navigation. In addition to her research contributions, Dr. Howard is actively involved in community service activities having a technical focus. As part of these activities, she serves as Chair and Founder of the Pasadena Delta Academy, a non-profit program focused on mentoring young "at-risk" girls and encouraging them to pursue careers in math and science. She also acts as an Engineering Advisor for a local high school team involved with the FIRST (For Inspiration and Recognition of Science and Technology) robotics competition. And in her spare time, Dr. Howard speaks to students around the world about the wonders of robotics, computers, and technology. 


Colloquium Committee Sponsor: Brent Warner


Engineering Colloquium home page: https://ecolloq.gsfc.nasa.gov

Home