Key points are not available for this paper at this time.
Recent work on autonomous navigation at Carnegie Mellon spans the range from hardware improvements to computational speed to new perception algorithms to systems issues. We have a new vehicle, the Navlab, that has room for onboard researchers and computers, and that carries a full suite of sensors. We have ported several of our algorithms to the Warp, an experimental supercomputer capable of performing 100 million floating point operations per second. Our perception now uses adaptive color classification for road tracking, and scanning laser rangefinder data for obstacle detection. We have completed the first system that uses the CMU Blackboard for scheduling, geometric transformations, inter and intra machine communications.
Thorpe et al. (Wed,) studied this question.