Sensing to recognize and locate objects is a critical need for robotic operations in unstructured environments. An accurate 3D model of objects in the scene is necessary for efficient high level control of robots. Drawing upon concepts from supervisory control, we have developed an interactive system for creating object models from range data, based on simulated annealing. Site modeling is a task that is typically performed using purely manual or autonomous techniques, each of which has inherent strengths and weaknesses. However, an interactive modeling system combines the advantages of both manual and autonomous methods, to create a system that has high operator productivity as well as high flexibility and robustness. Our system is unique in that it can work with very sparse range data, tolerate occlusions, and tolerate cluttered scenes. We have performed an informal evaluation with four operators on 16 different scenes, and have shown that the interactive system is superior to either manual or automatic methods in terms of task time and accuracy.

This paper describes component installation and testing of computer assisted control of an underground, diesel-powered, articulated haul truck. The sensing components are four ultrasonic transducers, four wheel encoders and two steering-cylinder linear potentiometers. On-board, 68030-processor based computing hardware controls engine idle, fuel shutoff transmission direction and speed selector, engine starter, parking and driving brakes, and steering. Control algorithms are encoded in C using the National Institute of Standards and Technology (NIST) Real-time Control System (RCS) architecture. A 480 kHz transmitter and receiver enables remote manual control. The truck successfully negotiated a simulated mine corridor located on the Colorado School of Mines campus 17 times in first and second gear without collisions.>