Configuring a simulator for robotic machine learning
AssigneeGeneral Electric Company
InventorBradford Wayne Miller
Life of this patent
Estimating the term…
Abstract
Provided are systems and methods for configuring a robotic simulator that is used to train a robot via machine learning. In one example, a method may include storing a domain description which comprises information about an operating environment of a robot, generating, via an automated planner, a plurality configuration files for a robotic simulator based on the domain description, where each configuration file comprises different configurations of a simulation environment for training a machine learning algorithm of the robot, and storing the plurality of configuration files in a memory device.
Claims20
A computing system comprising:
- a storage configured to store a domain description which comprises information about an operating environment of a robot;
- and
- a processor configured to generate, via an automated planner, a plurality of configuration files for a robotic simulator based on the domain description, where each configuration file comprises different configurations of a simulation environment for training a machine learning algorithm of the robot, and store the plurality of configuration files in a memory device.
A method comprising:
- storing a domain description which comprises information about an operating environment of a robot;
- generating, via an automated planner, a plurality of configuration files for a robotic simulator based on the domain description, where each configuration file comprises different configurations of a simulation environment for training a machine learning algorithm of the robot;
- and
- storing the plurality of configuration files in a memory device.
A non-transitory computer-readable medium comprising instructions which when executed by a processor cause a computer to perform a method comprising:
- storing a domain description which comprises information about an operating environment of a robot;
- generating, via an automated planner, a plurality of configuration files for a robotic simulator based on the domain description, where each configuration file comprises different configurations of a simulation environment for training a machine learning algorithm of the robot;
- and
- storing the plurality of configuration files in a memory device.
Dependencies are inferred from the claim text.