Field Robotics

This paper presents a summary of SciAutonics-Auburn Engineering’s efforts in the 2005 DARPA Grand Challenge. The areas discussed in detail include the team makeup and strategy, vehicle choice, software architecture, vehicle control, navigation, path planning, and obstacle detection. In particular, the advantages and complications involved in fielding a low budget all-terrain vehicle are presented. Emphasis is placed on detailing the methods used for high-speed control, customized navigation, and a novel stereo vision system. The platform chosen required a highly accurate model and a well-tuned navigation system in order to meet the demands of the Grand Challenge. Overall, the vehicle completed three out of four runs at the National Qualification Event and traveled 16 miles in the Grand Challenge before a hardware failure disabled operation. The performance in the events is described, along with a success and failure analysis.

Mobile robots operating in natural terrain need some sort of long-range perception in order to navigate efficiently. Whereas LADAR is a commonly used sensor on such systems, providing range data out to 25 m and beyond, we have instead focused on what information can be extracted from vision. Our robot has only two stereo camera pairs for terrain sensing; they provide reliable stereo data up to 5 m away, but this is not enough to prevent myopic behavior. To overcome this problem, we have developed a novel approach to navigation using monocular imagery by planning a path in the image space. We take a monocular image and apply a learned color-to-cost mapping to transform the raw image into a cost image. Then, after a pseudo-configuration-space transform, we search for a pixel-to-pixel path from a point in front of the robot to the projected goal point in the cost image. Our implementation has been shown to react to obstacles at a range of 93 m, far beyond the range of our stereo perception. We describe the details of our method and results from testing under the DARPA Learning Applied to Ground Robots (LAGR) program and discuss the characteristics and trade-offs of our approach. © 2009 Wiley Periodicals, Inc.

... In approximate cellular decomposition, the re-gion is approximated with a grid that covers the re ... From this study, it was concluded that 16% of the driving distance could be saved ... Ryerson and Zhang (2006) have proposed using genetic algorithms to solve the coverage path plan ...

This field study examines vertical takeoff and landing (VTOL) small unmanned aerial system (SUAS) operations conducted as part of an 8-day structural inspection task following Hurricane Katrina in 2005. From the observations of the 32 flights spread over 12 missions, four key findings are identified for concept of operations (CONOPS) and the next level of artificial intelligence for rotary-wing SUASs operating in cluttered urban environments. These findings are (1) the minimum useful standoff distance from inspected structures is 2–5 m, (2) omnidirectional sensor capabilities are needed for obstacle avoidance, (3) global positioning system waypoint navigation is unnecessary, and (4) these operations require three operators for one SUAS. Based on the findings and other observations, a crewing organization and flight operations protocol for SUASs are proposed. Needed directions in research and development are also discussed. These recommendations are expected to contribute to the design of platforms, sensors, and artificial intelligence as well as facilitate the acceptance of SUASs in the workplace. © 2009 Wiley Periodicals, Inc.