Robotic training apparatus and methods
AssigneeBrain Corporation
InventorOlivier Coenen
Life of this patent
Estimating the term…
Abstract
Adaptive controller apparatus of a robot may be implemented. The controller may be operated in accordance with a reinforcement learning process. A trainer may observe movements of the robot and provide reinforcement signals to the controller via a remote clicker. The reinforcement may comprise one or more degrees of positive and/or negative reinforcement. Based on the reinforcement signal, the controller may adjust instantaneous cost and to modify controller implementation accordingly. Training via reinforcement combined with particular cost evaluations may enable the robot to move more like an animal.
Claims23
A method for training a computerized robotic apparatus, the method comprising:
- establishing a target trajectory for an operation of the robotic apparatus, the target trajectory being characterized by a performance parameter configured based on a cost function;
- adjusting, with one or more processors, instantaneous cost value based on a training signal, the training signal being provided based on an evaluation of a measure between a current value of the performance parameter and a target value of the performance parameter, the robotic apparatus being configured to receive the training signal via a remote link;
- and
- determining, with one or more processors, an updated cost function based on the adjusted instantaneous cost value and the cost function, the updated cost function being configured to transition the performance parameter towards the target value.
A non-transitory computer-readable storage medium having instructions embodied thereon, the instructions being executable by a processor to perform a method for training a computerized robotic apparatus, the method comprising:
- establishing a target trajectory for an operation of the robotic apparatus, the target trajectory being characterized by a performance parameter configured based on a cost function;
- adjusting, with one or more processors, instantaneous cost value based on a training signal, the training signal being provided based on an evaluation of a measure between a current value of the performance parameter and a target value of the performance parameter, the robotic apparatus being configured to receive the training signal via a remote link;
- and
- determining, with one or more processors, an updated cost function based on the adjusted instantaneous cost value and the cost function, the updated cost function being configured to transition the performance parameter towards the target value.
A computerized robotic system, the system comprising:
- a training apparatus and a robotic apparatus, the training apparatus being configured to train the robotic apparatus, the robotic apparatus comprising one or more processors configured to execute computer program modules, the computer program modules comprising:
- a first logic module configured to receive a training signal from the training apparatus, the training signal being provided based on an evaluation of a measure between a current value of a performance parameter and a target value of the performance parameter;
- a second logic module configured to operate the robotic apparatus in accordance with a target trajectory characterized by the performance parameter;
- and
- a third logic module configured to (1) adjust an instantaneous cost value and, (2) determine an updated cost function configured to transition the performance parameter towards the target value, the updated cost function being based on an initial cost function associated with the performance parameter and the adjusted instantaneous cost value.
Dependencies are inferred from the claim text.