Abstract: The disclosed terrain model is a generative, probabilistic approach to modeling terrain that exploits the 3D spatial structure inherent in outdoor domains and an array of noisy but abundant sensor data to simultaneously estimate ground height, vegetation height and classify obstacles and other areas of interest, even in dense non-penetrable vegetation. Joint inference of ground height, class height and class identity over the whole model results in more accurate estimation of each quantity. Vertical spatial constraints are imposed on voxels within a column via a hidden semi-Markov model. Horizontal spatial constraints are enforced on neighboring columns of voxels via two interacting Markov random fields and a latent variable. Because of the rules governing abstracts, this abstract should not be used to construe the claims.

Abstract: The disclosed terrain model is a generative, probabilistic approach to modeling terrain that exploits the 3D spatial structure inherent in outdoor domains and an array of noisy but abundant sensor data to simultaneously estimate ground height, vegetation height and classify obstacles and other areas of interest, even in dense non-penetrable vegetation. Joint inference of ground height, class height and class identity over the whole model results in more accurate estimation of each quantity. Vertical spatial constraints are imposed on voxels within a column via a hidden semi-Markov model. Horizontal spatial constraints are enforced on neighboring columns of voxels via two interacting Markov random fields and a latent variable. Because of the rules governing abstracts, this abstract should not be used to construe the claims.

Abstract: The disclosed terrain model is a generative, probabilistic approach to modeling terrain that exploits the 3D spatial structure inherent in outdoor domains and an array of noisy but abundant sensor data to simultaneously estimate ground height, vegetation height and classify obstacles and other areas of interest, even in dense non-penetrable vegetation. Joint inference of ground height, class height and class identity over the whole model results in more accurate estimation of each quantity. Vertical spatial constraints are imposed on voxels within a column via a hidden semi-Markov model. Horizontal spatial constraints are enforced on neighboring columns of voxels via two interacting Markov random fields and a latent variable. Because of the rules governing abstracts, this abstract should not be used to construe the claims.

Abstract: A mining machine having a position sensing and control apparatus is claimed. The mining machine has a vehicle body having forward and rearward ends and movable along a mine floor. A cutter head is mounted on the forward end of the mining machine for upward and downward movement relative to the vehicle body. A conveyor mounted on the vehicle body conveys material cut by the cutter head. The position sensing and control apparatus has at least one light source and at least one imaging device mounted on the machine. The position sensing and control apparatus captures images of natural features of an interior surface of a mine, digitizes the images and determines the distance between the imaging device and the natural feature to determine positional change of the machine.

Abstract: A mining machine comprising a vehicle body having forward and rearward ends, the vehicle body being movable along a mine floor, a cutter head mounted on the forward end of the vehicle body, and a position sensing and control apparatus including first and second generally vertical, generally parallel surfaces on the vehicle body, an off-board light source emitting a light beam that strikes the surfaces, an imaging device for imaging both of the plates in a single image, and a computer receiving the single image from the camera, the computer using the single image to determine at least one of the roll, yaw and lateral offset of the machine.

Abstract: Robotic machines, such as mobile manipulators, are controlled by a relatively high-level script while changes in the environment are accommodated by including parameters in the script. Sensors, manual inputs, and other software can be used as sources of data for setting the values of the parameters. The high-level script includes sets of instructions with each set defining movement of one portion of the robotic machine, such as a joint of the manipulator. The several sets of instructions are executed concurrently in a primary script. One or more secondary scripts, each containing concurrently executed sets of instructions may be executed when an abnormal condition is detected. The movements performed by the robotic machine are generally defined by the instructions, but precisely how the movements are performed is determined by the values of the parameters. By using parameterized scripts, it is unnecessary to compute and track trajectories.

Abstract: Robotic machines, such as mobile manipulators, are controlled by a relatively high-level script while changes in the environment are accommodated by including parameters in the script. Sensors, manual inputs, and other software can be used as sources of data for setting the values of the parameters. The high-level script includes sets of instructions with each set defining movement of one portion of the robotic machine, such as a joint of the manipulator. The several sets of instructions are executed concurrently in a primary script. One or more secondary scripts, each containing concurrently executed sets of instructions may be executed when an abnormal condition is detected. The movements performed by the robotic machine are generally defined by the instructions, but precisely how the movements are performed is determined by the values of the parameters. By using parameterized scripts, it is unnecessary to compute and track trajectories.