Sanjiv Singh, Research Professor, The Robotics Institute, Carnegie Mellon University

"Slipping the Surly Bonds of Earth:  Intelligent Navigation and Collaboration for Air Vehicles"

Tuesday, April 15, 4:00 PM

Packard Lab 466

Reception prior to talk in Packard Lab lobby at 3:30

In the last two decades autonomous robots with legs and wheels have moved cautiously from simple indoor environments to the more complicated outdoors. Some robots now drive at highway speeds while others negotiate rough terrain even on distant planets with minimal supervision. In contrast, autonomous air vehicles have been constrained to fly high where they are very unlikely to encounter obstacles,  or to fly under careful manual supervision when close to the ground.

In this talk I will discuss an agenda for intelligent air vehicles that navigate, explore and collaborate in and around significant three dimensional structures. Fundamental to intelligent navigation is the ability to get from A to B, without prior knowledge of the environment,  sensing and avoiding obstacles in the way.  I will describe intelligent control or an autonomous helicopter that has evolved from autonomous ground vehicles in development at Carnegie Mellon since the early 1980s.  Continuing the philosophy of "plan globally, react locally", we have developed a tiered architecture that simplifies the need to consider geometry and dynamics simultaneously.  The highest level plans paths considering geometry of the environment, a middle layer controls steering incorporating vehicle dynamics, using the planned path as a suggestion, and the lowest level modulates speed using a forward closed-loop model of the control.

 While the logistics and safety issues of autonomous flight are complicated, I will show why in many cases, "slipping the surly bonds of earth" simplifies the problem of intelligent navigation.   I will show results from series of experiments that have recently demonstrated  autonomous flight  close to the ground, between wires, trees and buildings.  I will conclude with an overview of related projects that are extending autonomous navigation to mapping, avoidance of other aircraft, and collaboration with ground vehicles.

Bio:Sanjiv Singh is an Associate Research Professor at the Robotics Institute, Carnegie Mellon University. His recent work has two main themes:  perception in natural environments and multi-agent coordination. He has led projects in both ground and air vehicles operating in unknown or partially known environments, in applications such as mining, agriculture, emergency response, surveillance and exploration.  He is also actively involved in the automation of complex tasks, such as the assembly of large space structures, that cannot be addressed by single agents and must necessarily be performed by teams.  Prof Singh received his B.S in Computer Science from the University of Denver (1983)  M.S  in Electrical Engineering from Lehigh University (1985) and a PhD in Robotics from Carnegie Mellon (1995). He  is the founder and Editor-in-Chief of the  Journal of Field Robotics.