Policy layers for machine control
AssigneeNVIDIA Corporation
InventorsNathan Donald Ratliff, Karl Van Wyk, Man Xie, Anqi Li, Muhammad Asif Rana
Life of this patent
Estimating the term…
Abstract
Apparatuses, systems, and techniques provide a policy that can be executed to cause a machine to move. In at least one embodiment, a first policy layer is provided to cause the machine to execute a first motion that causes the machine to accelerate to reach an unbiased state. A second policy layer is provided to cause the machine to execute a second motion without influencing the unbiased state to be reached by machine. The policy can comprise the first and second policy layers.
Claims24
A computer system comprising one or more processors and computer-readable memory storing instructions executable by the one or more processors to cause the computer system to at least:
- identify a policy to cause a machine to execute at least one movement, the policy including at least a plurality of policy layers comprising:
- a first policy layer to cause the machine to execute a first motion that reaches an unbiased state, the first motion to be limited by at least a first parameter associated with the machine and a second parameter associated with an area in which the machine is to operate, and
- a second policy layer to cause the machine to execute a second motion without influencing the unbiased state associated with the first policy layer;
- and
- execute the policy to cause the machine to execute the at least one movement, the at least one movement comprising at least the first motion and the second motion.
A device comprising:
- one or more processors and memory storing executable instructions that, as a result of being executed by the one or more processors, cause the device to:
- generate a first policy layer to cause a machine to execute a first motion that causes the machine to accelerate to reach an unbiased state, and
- generate a second policy layer to cause the machine to execute a second motion without influencing the unbiased state to be reached by machine;
- and
- execute the first policy layer and the second policy layer to cause the machine to execute the first motion and the second motion.
A computer-implemented method, comprising:
- generating a first policy layer to cause a machine to execute a first motion that causes the machine to accelerate to reach an unbiased state, and
- generating a second policy layer to cause the machine to execute a second motion without influencing the unbiased state to be reached by machine;
- and
- executing the first policy layer and the second policy layer to cause the machine to execute the first motion and the second motion.
Dependencies are inferred from the claim text.