IEEE Computer Society: http://computer.org Computer: http://computer.org/computer computer@computer.org IEEE Computer Society Publications Office: +1 714 821 8380 December 2006, Volume 39, Number 12 Cover design and artwork by Dirk Hagner A B O U T T H I S I S S U E Iunmanned n this issue, we feature the latest developments in ground-based autonomous vehicles as seen in the highly publicized DARPA Grand Challenge. While the Grand Challenge focuses attention on current UAVs, this issue also devotes special attention to the future of unmanned vehicles and computational paradigms that might be used as part of a system of intelligent vehicles. C O V E R F E A T U R E S G U E S T E D I T O R S ��� I N T R O D U C T I O N 26 Unmanned Vehicles Come of Age: The DARPA Grand Challenge Guna Seetharaman, Arun Lakhotia, and Erik Philip Blasch A host of novel issues related to autonomous vehicles afford design and computer-engineering challenges for the future. 31 VisLab and the Evolution of Vision-Based UGVs Massimo Bertozzi, Alberto Broggi, and Alessandra Fascioli Unmanned ground vehicle researchers are still building prototypes, but now they���re moving toward demonstrations. 40 Perception and Planning Architecture for Autonomous Ground Vehicles Bob Touchton, Tom Galluzzo, Danny Kent, and Carl Crane Team CIMAR developed a robust autonomous ground vehicle platform with advanced sensing and planning capabilities. 48 Testing Driver Skill for High-Speed Autonomous Vehicles Chris Urmson, William ���Red��� Whittaker, Sam Harbaugh, Michael Clark, and Phillip Koon Carnegie Mellon University���s Red Team developed effective tools for measuring autonomous ground vehicle driving skill. 52 To Drive Is Human Isaac Miller, Ephrahim Garcia, and Mark Campbell Cornell University researchers offer an insider���s perspective on the issues the DARPA Grand Challenge competitors faced in creating a humanlike driver���without the human. 57 On the Importance of Being Contextual Paolo Lombardi, Bertrand Zavidovique, and Michael Talbert Multimodal awareness is the key to improved unmanned vehicle control performance. 62 Memory-Based In Situ Learning for Unmanned Vehicles Patrick McDowell, Brian S. Bourgeois, Donald A. Sofge, and S.S. Iyengar Researchers are using a sensor-input-based metric to develop a team of robots that could meet their overall goals in dynamic unstructured environments. 68 A Vision for Supporting Autonomous Navigation in Urban Environments Vason P. Srini The mobile sensor network for autonomous navigation systems can support modern vehicles equipped with actuators for steering, throttle, and brakes. Innovative Technology for Computer Professionals