Team MIT Urban Challenge Technical Report

This technical report describes Team MIT's approach to the DARPA Urban Challenge. We have developed a novel strategy for using many inexpensive sensors, mounted on the vehicle periphery, and calibrated with a new cross­modal calibration technique. Lidar, camera, and radar data streams are processed using an innovative, locally smooth state representation that provides robust perception for real­ time autonomous control. A resilient planning and control architecture has been developed for driving in traffic, comprised of an innovative combination of well­proven algorithms for mission planning, situational planning, situational interpretation, and trajectory control. These innovations are being incorporated in two new robotic vehicles equipped for autonomous driving in urban environments, with extensive testing on a DARPA site visit course. Experimental results demonstrate all basic navigation and some basic traffic behaviors, including unoccupied autonomous driving, lane following using pure­pursuit control and our local frame perception strategy, obstacle avoidance using kino­dynamic RRT path planning, U­turns, and precedence evaluation amongst other cars at intersections using our situational interpreter. We are working to extend these approaches to advanced navigation and traffic scenarios. † Executive Summary This technical report describes Team MIT's approach to the DARPA Urban Challenge. We have developed a novel strategy for using many inexpensive sensors, mounted on the vehicle periphery, and calibrated with a new cross-modal calibration technique. Lidar, camera, and radar data streams are processed using an innovative, locally smooth state representation that provides robust perception for real-time autonomous control. A resilient planning and control architecture has been developed for driving in traffic, comprised of an innovative combination of well-proven algorithms for mission planning, situational planning, situational interpretation, and trajectory control. These innovations are being incorporated in two new robotic vehicles equipped for autonomous driving in urban environments, with extensive testing on a DARPA site visit course. Experimental results demonstrate all basic navigation and some basic traffic behaviors, including unoccupied autonomous driving, lane following using pure-pursuit control and our local frame perception strategy, obstacle avoidance using kino-dynamic RRT path planning, U-turns, and precedence evaluation amongst other cars at intersections using our situational interpreter. We are working to extend these approaches to advanced navigation and traffic scenarios. DISCLAIMER: The information contained in this paper does not represent the official policies, either expressed or implied, of the Defense Advanced Research Projects Agency (DARPA) or the Department of Defense. DARPA does not guarantee the accuracy or reliability of the information in this paper. Additional support …

[1]  E. Feron,et al.  Robust hybrid control for autonomous vehicle motion planning , 2000, Proceedings of the 39th IEEE Conference on Decision and Control (Cat. No.00CH37187).

[2]  William Whittaker,et al.  A robust approach to high‐speed navigation for unrehearsed desert terrain , 2006, J. Field Robotics.

[3]  M. Buehler,et al.  Editorial for Journal of Field Robotics—Special Issue on the DARPA Grand Challenge: Editorial , 2006 .

[4]  Ümit Özgüner,et al.  Intelligent off‐road navigation algorithms and strategies of Team Desert Buckeyes in the DARPA Grand Challenge 2005 , 2006, J. Field Robotics.

[5]  Jo Yung Wong,et al.  Theory of ground vehicles , 1978 .

[6]  Charles F. Reinholtz,et al.  Virginia Tech's twin contenders: A comparative study of reactive and deliberative navigation , 2006, J. Field Robotics.

[7]  Alain L. Kornhauser,et al.  Prospect Eleven: Princeton University's entry in the 2005 DARPA Grand Challenge , 2006, J. Field Robotics.

[8]  Sebastian Thrun,et al.  Stanley: The robot that won the DARPA Grand Challenge , 2006, J. Field Robotics.

[9]  Jürgen Guldner,et al.  Lane following during backward driving for front wheel steered vehicles , 1997, Proceedings of the 1997 American Control Conference (Cat. No.97CH36041).

[10]  Joel W. Burdick,et al.  Alice: An information‐rich autonomous vehicle for high‐speed desert navigation , 2006, J. Field Robotics.

[11]  Arthur G. Richards,et al.  Robust constrained model predictive control , 2005 .

[12]  Chung Tin,et al.  Robust multi-UAV planning in dynamic and uncertain environments , 2004 .

[13]  Ann Jones,et al.  MITRE Meteor: An off-road autonomous vehicle for DARPA's Grand Challenge , 2006, J. Field Robotics.

[14]  Emilio Frazzoli,et al.  The Golem Group / UCLA Autonomous Ground Vehicle in the DARPA Grand Challenge , 2007 .

[15]  Cris Koutsougeras,et al.  KAT-5: Robust systems for autonomous vehicle navigation in challenging and unknown terrain , 2006, J. Field Robotics.

[16]  Sanghyuk Park.  Avionics and control system development for mid-air rendezvous of two unmanned aerial vehicles , 2004 .

[17]  Yoshiaki Kuwata,et al.  Trajectory planning for unmanned vehicles using robust receding horizon control , 2007 .

[18]  Alonzo Kelly,et al.  An Approach to Rough Terrain Autonomous Mobility , 1997 .

[19]  Alberto Broggi,et al.  The TerraMax autonomous vehicle , 2006, J. Field Robotics.