Autoplan a self-processing network model for an extended blocks world planning environment
Abstract: "Self-processing network models (neural/connectionist models, marker-passing/message passing networks, etc.) are currently undergoing intense investigation for a variety of information processing applications. These models are potentially very powerful in that they support a large amount of explicit parallel processing, and they cleanly integrate 'high-level' and 'low-level' information processing. However they are currently limited by a lack of understanding of how to apply them effectively in many application areas. This project is studying the formulation of self-processing network methods for dynamic, reactive planning.
"Abstract: "Self-processing network models (neural/connectionist models, marker-passing/message passing networks, etc.) are currently undergoing intense investigation for a variety of information processing applications. These models are potentially very powerful in that they support a large amount of explicit parallel processing, and they cleanly integrate 'high-level' and 'low-level' information processing. However they are currently limited by a lack of understanding of how to apply them effectively in many application areas. This project is studying the formulation of self-processing network methods for dynamic, reactive planning."@en
"The long-term goal is to formulate robust, computationally- effective information processing methods for the distributed control of semiautonomous exploration systems, e.g., the Mars Rover. Our current research effort is focusing on hierarchical plan generation, execution and revision through local operations in an 'extended blocks world' environment. This scenario involves many challenging features that would be encountered in a real planning and control environment: multiple simultaneous goals, parallel as well as sequential action execution, action sequencing determined not only by goals and their interactions but also by limited resources (e.g., three tasks, two acting agents), need to interpret unanticipated events and react appropriately through replanning, etc.""@en
This is a placeholder reference for a Topic entity, related to a WorldCat Entity. Over time, these references will be replaced with persistent URIs to VIAF, FAST, WorldCat, and other Linked Data resources.
This is a placeholder reference for a Topic entity, related to a WorldCat Entity. Over time, these references will be replaced with persistent URIs to VIAF, FAST, WorldCat, and other Linked Data resources.
This is a placeholder reference for a Topic entity, related to a WorldCat Entity. Over time, these references will be replaced with persistent URIs to VIAF, FAST, WorldCat, and other Linked Data resources.
This is a placeholder reference for a Topic entity, related to a WorldCat Entity. Over time, these references will be replaced with persistent URIs to VIAF, FAST, WorldCat, and other Linked Data resources.
This is a placeholder reference for a Topic entity, related to a WorldCat Entity. Over time, these references will be replaced with persistent URIs to VIAF, FAST, WorldCat, and other Linked Data resources.
This is a placeholder reference for a Topic entity, related to a WorldCat Entity. Over time, these references will be replaced with persistent URIs to VIAF, FAST, WorldCat, and other Linked Data resources.