Autonomous and semi-autonomous control of aerial robotic systems
AssigneeAltec Industries, Inc.
InventorsJonathan Westin Sykes, Timothy J. Mourlam, David Lindquist, William Naber, Robert Nichols
Life of this patent
Estimating the term…
Abstract
Systems and methods for performing a task in an operation environment of an aerial device with an autonomous or semi-autonomous robot are described. In some embodiments, a robot is disposed at an end of a boom of an aerial device. The robot may comprise cameras, actuators, sensors, processors, and manipulators that work together to perform tasks fully autonomously or semi-autonomously. Furthermore, the robot may comprise tools for performing the tasks and computer-executable instructions for performing the tasks may be based on the various sensory inputs, the tools, and the tasks to be performed.
Claims20
A robot system for performing automated tasks in an operational environment of an aerial device, the robot system comprising:
- at least one processor;
- a robot unit disposed at a boom tip comprising at least one manipulator configured to perform a task in the operational environment;
- a tool configured to attach to the at least one manipulator and perform the task;
- a camera for obtaining images of the operational environment;
- a sensor associated with the robot unit;
- and
- one or more non-transitory computer-readable media storing computer-readable instructions that, when executed by the at least one processor, perform a method of completing the task, the method comprising:
- obtaining, by the camera, information indicative of a location of an object in the operational environment;
- obtaining sensor data from the sensor,
- wherein the sensor data is indicative of a state of the at least one manipulator;
- classifying the object by a machine learning algorithm;
- identifying the tool based on the classifying and the task;
- autonomously attaching the tool to the at least one manipulator;
- automatically transforming a tool reference point based on a geometry of the tool;
- and
- performing the task based on the location of the object and the sensor data.
A method of performing automated tasks by a robot unit in an operational environment of an aerial device, the method comprising:
- obtaining, by a camera, object information indicative of an object and location information indicative of a location of the object in the operational environment;
- classifying the object based on the information indicative of the object;
- identifying a tool based on the classifying of the object;
- autonomously obtaining the tool;
- automatically transforming a reference location for a boom-tip coordinate system based on a geometry of the tool;
- obtaining sensor data by a sensor associated with the robot unit,
- wherein the sensor data is indicative of a state of at least one manipulator of the robot unit;
- and
- manipulating the object by the at least one manipulator to complete a task,
- wherein the manipulating is based at least in part on the location of the object and the sensor data from the sensor.
A robot system for performing automated tasks in an operational environment of an aerial device, the robot system comprising:
- at least one processor;
- a robot unit comprising at least one manipulator configured to perform a task in the operational environment;
- a tool configured to attach to the at least one manipulator and perform the task;
- a camera for obtaining images of the operational environment;
- a sensor associated with the robot unit;
- and
- one or more non-transitory computer-readable media storing computer-readable instructions that, when executed by the at least one processor, perform a method of completing the task, the method comprising:
- obtaining, by the camera, information indicative of a location of an object in the operational environment;
- obtaining sensor data from the sensor,
- wherein the sensor data is indicative of a state of the at least one manipulator;
- classifying the object by a machine learning algorithm;
- identifying the tool based on the classifying and the task;
- autonomously attaching the tool to the at least one manipulator;
- automatically transforming a tool reference point based on a geometry of the tool;
- and
- manipulating the object by the at least one manipulator and the tool to complete the task,
- wherein the manipulating is based at least in part on the location of the object and the sensor data from the sensor.
Dependencies are inferred from the claim text.