Scalable and efficient episodic memory in cognitive processing for automated systems
AssigneeHRL Laboratories, LLC
InventorsYoungkwan Cho, Hyukseong Kwon, Rajan Bhattacharyya
Life of this patent
Estimating the term…
Abstract
Described is a system for an episodic memory used by an automated platform. The system acquires data from an episodic memory that comprises an event database, an event-sequence graph, and an episode list. Using the event-sequence graph, the system identifies a closest node to a current environment for the automated platform. Based on the closest node and using a hash function or key based on the hash function, the system retrieves from the event database an episode that corresponds to the closest node, the episode including a sequence of events. Behavior of the automated platform in the current environment is guided based on the data from the episodic memory.
Claims22
A system for episodic memory for an automated platform, the system comprising:
- one or more processors and a non-transitory computer-readable medium having executable instructions encoded thereon such that when executed, the one or more processors perform operations of:
- acquiring data from an episodic memory that comprises an event database, an event-sequence graph, and an episode list, wherein acquiring data comprises:
- using the event-sequence graph, identifying a closest node to a current environment for the automated platform;
- based on the closest node and using a hash function, retrieving from the event database an episode that corresponds to the closest node, the episode including a sequence of events,
- wherein the hash function maps a hash key directly to a corresponding event to reduce a number of comparisons needed for finding a matching event;
- and
- guiding behavior of the automated platform in the current environment based on the data from the episodic memory.
A computer implemented method for episodic memory for an automated platform, the method comprising an act of:
- causing one or more processors to execute instructions encoded on a non-transitory computer-readable medium, such that upon execution, the one or more processors perform operations of:
- acquiring data from an episodic memory that comprises an event database, an event-sequence graph, and an episode list, wherein acquiring data comprises:
- using the event-sequence graph, identifying a closest node to a current environment for the automated platform;
- based on the closest node and using a hash function, retrieving from the event database an episode that corresponds to the closest node, the episode including a sequence of events,
- wherein the hash function maps a hash key directly to a corresponding event to reduce a number of comparisons needed for finding a matching event;
- and
- guiding behavior of the automated platform in the current environment based on the data from the episodic memory.
A computer program product for episodic memory for an automated platform, the computer program product comprising:
- computer-readable instructions stored on a non-transitory computer-readable medium that are executable by a computer having one or more processors for causing the processor to perform operations of:
- acquiring data from an episodic memory that comprises an event database, an event-sequence graph, and an episode list, wherein acquiring data comprises:
- using the event-sequence graph, identifying a closest node to a current environment for the automated platform;
- based on the closest node and using a hash function, retrieving from the event database an episode that corresponds to the closest node, the episode including a sequence of events,
- wherein the hash function maps a hash key directly to a corresponding event to reduce a number of comparisons needed for finding a matching event;
- and
- guiding behavior of the automated platform in the current environment based on the data from the episodic memory.
Dependencies are inferred from the claim text.