Method and apparatus for robotic arm navigation
AssigneesGeneral Electric Company, Oliver Crispin Robotics Limited
InventorsAndrew Crispin Graham, Julian Matthew Foxall, Rafael S. Brada, Guy Ben-Yosef
Life of this patent
Estimating the term…
Abstract
A robotic arm is inserted into a passage of a part to be examined. Operator instructions defining a tip motion for a tip of the robotic arm, sensor readings, and an environmental map are received. The operator instructions, the environmental map and sensor readings are applied to a previously trained machine learning model to produce control signals. The control signals to an actuator on the arm to control a movement of the robotic arm allowing the robotic arm to automatically gain traction in the passage and automatically move according to the movement.
Claims20
A system, the system comprising:
- a robotic arm, the robotic arm being flexible, the robotic arm being inserted into a passage within a part, the robotic arm having multiple degrees of freedom as it moves through the passage;
- at least one sensor;
- an actuator coupled to the robotic arm;
- a controller coupled to the robotic arm, the at least one sensor, and the actuator, the controller is configured to:
- receive operator instructions defining a tip motion for a tip of the robotic arm;
- receive sensor readings from the at least one sensor;
- access an environmental map, the environmental map defining a geometry of portions of the passage;
- apply the operator instructions, the environmental map and sensor readings to a previously trained machine learning model to produce control signals;
- and
- apply the control signals to the actuator for the robotic arm to control a movement of the robotic arm allowing the robotic arm to automatically gain traction in the passage and automatically move within the passage according to the movement.
A method, the method comprising:
- inserting a robotic arm into a passage within a part, the robotic arm being flexible and having multiple degrees of freedom as it moves through the passage;
- at a controller:
- receiving operator instructions defining a tip motion for a tip of the robotic arm;
- receiving sensor readings from at least one sensor;
- accessing an environmental map, the environmental map defining a geometry of portions of the passage;
- applying the operator instructions, the environmental map and sensor readings to a previously trained machine learning model to produce control signals;
- applying the control signals to an actuator on the robotic arm to control a movement of the robotic arm allowing the robotic arm to automatically gain traction in the passage and automatically move within the passage according to the movement.
Dependencies are inferred from the claim text.