| CPC G06F 18/217 (2023.01) [G06N 3/047 (2023.01)] | 20 Claims |
|
1. A computing system for facilitating autonomous target selection through neural networks, the computing system comprising:
one or more hardware processors; and
a memory coupled to the one or more hardware processors, wherein the memory comprises a plurality of modules in the form of programmable instructions executable by the one or more hardware processors, wherein the plurality of modules comprises:
a data receiver module configured to:
receive a request from a user to select a target from one or more targets for an agent to perform one or more activities, wherein the request comprises: type of the agent, one or more targets to be observed, types of the one or more targets, time to perform the one or more activities, priority of the one or more targets and recurring requirement of performing the one or more activities, wherein the agent is one of: a space craft, land craft and water craft, wherein the one or more targets comprise: one or more ground targets, one or more space targets, one or more air targets and one or more water targets and wherein the one or more activities comprise: capturing one or more images of the one or more targets, collecting observation data of the one or more targets and interacting with the one or more targets;
receive one or more input parameters from at least one of: the user and one or more external sources based on the received request;
a data management module configured to:
generate an expected reward value for each of the one or more targets by applying the received request and the one or more input parameters to a trained value network based Artificial Neural Network (ANN) model;
determine a desired target among the one or more targets based on the generated expected reward value of each of the one or more targets by using one of: the trained value network based ANN model and empirical estimation, wherein the expected reward value associated with the desired target corresponds to a higher expected reward value;
generate one or more actions to be executed by the agent corresponding to the desired target based on the received request, the received one or more input parameters, the desired target, one or more dynamic parameters and the expected reward value by using a trained policy network based ANN model, wherein the one or more actions comprise: slew the agent towards the desired target, take no action, slew to a default state, keep custody of the desired target and change the desired target and wherein the one or more dynamic parameters comprise: changing weather, changing environmental conditions, changing states of the agent and surrounding agents, changing states of the target and of other targets and total time left to execute the one or more actions; and
a data output module configured to output the determined one or more actions to at least one of: the agent and one or more user devices associated with the user for performing the one or more activities.
|