In order for an unmanned vehicle (UV) to safely navigate through its course, it must be capable of detecting and avoiding obstacles in its path.  From a single camera on the , the 3D structure of its surrounding environment, including any obstacles, can be estimated from motion parallax using a technique called structure from motion.  We present a novel method for calculating structure from motion that does not require a precise calculation of optical flow at each feature point. 

     Another approach we developed for autonomous vehicle to avoid obstacle is using focus of expansion to calculate time-to-impact.  This approach does not require accurate feature tracking and is suitable for the ground vehicle traveling on a planar surface.

     Another research project for obstacle avoidance is using 1-D signal to solve the correspondence for stereo vision.  This approach simplify the correspondence problem into a simple curve matching problem.

 Collaborators:

 Graduate Students:

 Paul Merrell and Pengcheng Zhan

1. P.C. Merrell, D.J. Lee, and R.W. Beard, “Obstacle Avoidance for Unmanned Air Vehicles Using Optical Flow Probability Distributions”, SPIE Optics East, Robotics Technologies and Architectures, Mobile Robot XVII, vol. 5609-04, p. 13-22, Philadelphia, PA, USA, October 25-28, 2004.

2. D.J. Lee, R.W. Beard, P.C. Merrell, and P. Zhan, “See and Avoidance Behaviors for Autonomous Navigation”, SPIE Optics East, Robotics Technologies and Architectures, Mobile Robot XVII, vol. 5609-05, p. 23-34, Philadelphia, PA, USA, October 25-28, 2004.

3. P. Zhan, D.J. Lee, and R.W. Beard, “Solving Correspondence Problem Using 1-D Signal Matching”, SPIE Optics East, Robotics Technologies and Architectures, Intelligent Robots and Computer Vision XXII, vol. 5608, p. 207-215, Philadelphia, PA, USA, October 25-28, 2004.

4. P. Merrell, D.J. Lee, and R.W. Beard, “Statistical Analysis of Multiple Optical Flow Values for Estimation of Unmanned Air Vehicles Height Above Ground”, SPIE Optics East, Robotics Technologies and Architectures, Intelligent Robots and Computer Vision XXII, vol. 5608, p. 298-305, Philadelphia, PA, USA, October 25-28, 2004.