Hierarchical Instantiated Goal Recognition
نویسندگان
چکیده
We present a goal recognizer that statistically recognizes hierarchical goal schemas and their corresponding parameter values. The recognizer is fast (quadratic in the number of possible goal schemas and observations so far), and also supports partial parameter and subgoallevel prediction as well as n-best prediction.
منابع مشابه
Recognizing Instantiated Goals using Statistical Methods
We present our work on using statistical, corpusbased machine learning techniques to perform instantiated goal recognition — recognition of a goal schema and its parameter values. The recognizer is fast (linear in the number of goal schemas and observed actions) and is able to make partial predictions by optionally predicting individual parameter values for a goal schema. This allows it to make...
متن کاملStatistical Goal Parameter Recognition
We present components of a system which uses statistical, corpus-based machine learning techniques to perform instantiated goal recognition — recognition of both a goal schema and its parameter values. We first present new results for our previously reported statistical goal schema recognizer. We then present our goal parameter recognizer. The recognizer is fast (linear in the number of observe...
متن کاملHierarchies of neural networks for connectionist speech recognition
We present a principled framework for context-dependent hierarchical connectionist HMM speech recognition. Based on a divideand-conquer strategy, our approach uses an Agglomerative Clustering algorithm based on Information Divergence (ACID) to automatically design a soft classi er tree for an arbitrary large number of HMM states. Nodes in the classi er tree are instantiated with small estimator...
متن کاملTowards Integrating Hierarchical Goal Networks and Motion Planners to Support Planning for Human-Robot Teams
Low-level motion planning techniques must be combined with high-level task planning formalisms in order to generate realistic plans that can be carried out by humans and robots. Previous attempts to integrate these two planning formalisms mostly used either Classical Planning or HTN Planning. Recently, we developed Hierarchical Goal Networks (HGNs), a new hierarchical planning formalism that co...
متن کاملNotes on Semantic Hierarchical Temporal Memory for Perceptual, Motoric and Intentional Intelligence
The Hierarchical Temporal Memory (HTM) approach to perception processing, pursued by prior authors including Jeff Hawkins and Itamar Arel, is expanded to encompass more abstract semantic forms of HTM, and to include separate, coupled hierarchies for perception, motor control and goal management. No experimental evidence or detailed calculations are presented; this is merely a conceptual paper d...
متن کامل