Abstract: In one embodiment of the present invention, a motion planning algorithm is used to control an autonomous machine. The motion planning algorithm consists of a template or script which captures the general trends of the motion, while parameters in the script are filled in with the kinematic details for a specific machine and set of movements. A learning algorithm computes the script parameters by using feedback of how the machine performed during the preceding cycle with the current parameter set, and adjusting the parameters to improve the machine's performance during succeeding work cycles. The new parameters are evaluated by the learning algorithm using a predictive function approximator to test various performance criteria such as the time required to perform a task and the accuracy with which the task was performed.

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.