Carnegie Mellon University

Xiaoyu Abrasive Inc.

Xiaoyu Arasive Inc.

Patrick S Rowe

Anthony Joseph Stentz

Parag Batavia

Penglai Guo

Michael Lawrence

Sanjiv Singh

John E Bares

Patrick C Leger

Jorgen Pedersen

Norman Keith Lay

According to embodiments of the present disclosure is an automatic floor preparation or maintenance system. The system uses a laser rangefinder to map a workspace, while a path planning module uses the map to determine a path for the concrete polishing vehicle to travel. A propulsion system moves the vehicle along the determined path. A user interface allows an operator to remotely monitor the autonomous operations.

Autonomous navigational system for floor preparation and maintenance equipment

In accordance with the present invention, a system to organize and coordinate components associated with earthmoving machinery capable of performing excavating and loading tasks autonomously is disclosed. The system comprises an earthmoving machine equipped with a scanning sensor system operable to provide data regarding regions within an earthmoving environment including an excavation region and a loading region and a planning and control module operable to receive data from the scanning sensor system to plan a task associated with the control of the earthmoving machine while concurrently performing another task associated with control of the earthmoving machine. Any number and type of sensor systems, such as a laser rangefinder or a radar rangefinder, may be incorporated in the system depending on requirements and the capabilities of the system. The sensor systems have independently controllable fields of view, with each sensor system being capable of providing data pertaining to a different portion of the earthmoving environment.

System for autonomous excavation and truck loading

In accordance with the present invention, a modular architecture to organize and coordinate components that are needed to automate earthmoving tasks, and to coordinate the flow of data between the components is disclosed. The architecture includes three main subdivisions: a sensor pipeline, sensor data consumers, and motion planners and executors. The sensor pipeline receives raw sensor data from perceptual sensors such as a laser rangefinder or radar system, and converts the data into a form which is usable by the other system components. Sensor data can also be represented in the form of an elevation map of the surrounding terrain for other software components to use. Any number and types of sensor systems may be added to the software architecture depending on requirements and the capabilities of the system. The sensor data consumers use the sensor data as input to specific algorithms to produce information regarding the machine's environment for use by other system components. A motion planner receives information provided by the sensor data consumers, and delivers output commands go to controllers on the machine. The motion planner also computes and delivers commands to the sensor systems on the machine. Additional planners may be added at this level to coordinate other system behaviors and actions.

Software architecture for autonomous earthmoving machinery

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. The performance criteria are weighted using local regression techniques so that the prediction of the outcome of alternate motions places emphasis on the performance criteria that is considered most important. As data from repeated motions accumulates, the algorithm uses the history of the results of various motions to recompute and refine the parameters to improve performance.

Learning system and method for optimizing control of autonomous

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.

Growing community of inventors

Pittsburgh, PA, United States of America

Patrick S Rowe