From Public Wiki
This project studies algorithms for finding and following trails with autonomous mobile robots. Trails are navigationally-useful features of outdoor environments, "showing the way" for UGVs and UAVs which can recognize them and "smoothing the way" to ease passage. Trails may be deliberately engineered, formed by natural features, or inadvertently left by humans or animals. Types of trails that we are studying include paved and dirt roads, true hiking trails, power lines, pipelines, and rivers. A characteristic exhibited by some trails is discontinuity, in which visual markers such as cairns, blazes, footprints, and other "tells" indicate a sequence of waypoints.
This research focuses on approaches to three core trail following tasks: (1) keeping, or discriminating and staying on continuous and discontinuous trails; (2) negotiation, or avoiding within-trail obstacles and setting control policies appropriate to changing terrain conditions; and (3) finding trails and mapping unknown trail networks, including detecting branches, dead-ends, and discontinuities. As a research testbed, we are using a Segway RMP 400 robot, "Warthog", to collect data and test algorithms.
Longer-term goals include exploration of applications such as wildlife monitoring and the development of portable trail-following devices with visual display or haptic outputs. These devices may be vehicle-mounted or carried by people in an assistive or expert capacity.
Ongoing work on this project has been described in IROS 2008, RobVis 2008, and ISVC 2007.
A more formal description of the project plans, taken from the proposal, may be found here.
This work is sponsored by the National Science Foundation.
