Filters








6,364 Hits in 3.0 sec

Generalized Grounding Graphs: A Probabilistic Framework for Understanding Grounded Commands [article]

Thomas Kollar, Stefanie Tellex, Matthew Walter, Albert Huang, Abraham Bachrach, Sachi Hemachandra, Emma Brunskill, Ashis Banerjee, Deb Roy, Seth Teller, Nicholas Roy
2017 arXiv   pre-print
Our framework, called Generalized Grounding Graphs (G^3), addresses these issues by defining a probabilistic graphical model dynamically according to the linguistic parse structure of a natural language  ...  We demonstrate our approach for both mobility commands and mobile manipulation commands involving a variety of semi-autonomous robotic platforms, including a wheelchair, a micro-air vehicle, a forklift  ...  We thank Chad Jenkins and the Brown Robotics lab for their help with the PR2 demonstration.  ... 
arXiv:1712.01097v1 fatcat:i76nxbbqerbkrfvwfb6zs5xll4

A General Framework for the Representation of Function and Affordance: A Cognitive, Causal, and Grounded Approach, and a Step Toward AGI [article]

Seng-Beng Ho
2022 arXiv   pre-print
A general framework dealing with functionality would represent a major step toward achieving Artificial General Intelligence.  ...  elaboration, together with the definition of a set of ground level concepts.  ...  The various works cited above satisfy some, but not all, of the criteria listed: a general framework for cognitive, causal, and grounded representation and understanding.  ... 
arXiv:2206.05273v2 fatcat:wlasebf3mnf5zls3kfwgfezvsi

Temporal Grounding Graphs for Language Understanding with Accrued Visual-Linguistic Context [article]

Rohan Paul, Andrei Barbu, Sue Felshin, Boris Katz, Nicholas Roy
2018 arXiv   pre-print
A probabilistic model estimates, from a natural language utterance, the objects,relations, and actions that the utterance refers to, the objectives for future robotic actions it implies, and generates  ...  Instead, our model, Temporal Grounding Graphs, maintains a learned state representation for a belief over factual groundings, those derived from natural-language interactions, and lazily infers new groundings  ...  We thank Naomi Schurr and Yen-Ling Kuo for assistance during system evaluation.  ... 
arXiv:1811.06966v1 fatcat:uurb4jhg6zgblhiumtacnucb64

Temporal Grounding Graphs for Language Understanding with Accrued Visual-Linguistic Context

Rohan Paul, Andrei Barbu, Sue Felshin, Boris Katz, Nicholas Roy
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
A probabilistic model estimates, from a natural language utterance, the objects, relations, and actions that the utterance refers to, the objectives for future robotic actions it implies, and generates  ...  Instead, our model, Temporal Grounding Graphs, maintains a learned state representation for a belief over factual groundings, those derived from natural-language interactions, and lazily infers new groundings  ...  We thank Naomi Schurr and Yen-Ling Kuo for assistance during system evaluation. Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  ... 
doi:10.24963/ijcai.2017/629 dblp:conf/ijcai/PaulBFKR17 fatcat:svwhky2zl5dzfa36na2msqbkde

Robot learning with a spatial, temporal, and causal and-or graph

Caiming Xiong, Nishant Shukla, Wenlong Xiong, Song-Chun Zhu
2016 2016 IEEE International Conference on Robotics and Automation (ICRA)  
We propose a stochastic graph-based framework for a robot to understand tasks from human demonstrations and perform them with feedback control.  ...  The robot can accurately reproduce the learned skill, as well as generalize the task to other articles of clothing.  ...  In addition, we would like to thank SRI International and OSRF for their support.  ... 
doi:10.1109/icra.2016.7487364 dblp:conf/icra/XiongSXZ16 fatcat:agdxx2bwbvcf5l43dkldvmt42m

Following route graphs in urban environments

Roderick de Nijs, Miguel Julia, Nikos Mitsou, Barbara Gonsior, Dirk Wollherr, Kolja Kuhnlenz, Martin Buss
2011 2011 RO-MAN  
An architecture for solving problems such as navigation on the sidewalk, street direction inference, and environment labeling that arise in this situation is presented.  ...  Our initial experiments indicate that the proposed methods enable a robot to safely navigate in urban environments by following abstract route descriptions and reach previously unknown points in a city  ...  For receiving commands in natural language, a module is implemented that receives descriptions in natural language, splits them into route segments and translates them into a route graph G nodes, edges  ... 
doi:10.1109/roman.2011.6005196 dblp:conf/ro-man/NijsJMGWKB11 fatcat:ix2auky7evgvtae6jci7zk3gxy

Graph Neural Networks with Heterophily [article]

Jiong Zhu, Ryan A. Rossi, Anup Rao, Tung Mai, Nedim Lipka, Nesreen K. Ahmed, Danai Koutra
2021 arXiv   pre-print
In this work, we propose a novel framework called CPGNN that generalizes GNNs for graphs with either homophily or heterophily.  ...  Graph Neural Networks (GNNs) have proven to be useful for many different practical applications.  ...  W911NF1810397, an Adobe Digital Experience research faculty award, an Amazon faculty award, a Google faculty award, and AWS Cloud Credits for Research.  ... 
arXiv:2009.13566v3 fatcat:cwiivtjlxnck7bslu6fcvtx6oq

Discovery of interactive graphs for understanding and searching time-indexed corpora

Ilija Subašić, Bettina Berendt
2009 Knowledge and Information Systems  
We propose a method and a visualisation tool for solving ETP3 by understanding, searching and interacting with such stories and their underlying documents.  ...  In addition, it relies on interactive graphs rather than natural language as the abstracted story representations. Furthermore, we present an evaluation framework.  ...  [59] ), but in general not on the usefulness of the groups for human understanding.  ... 
doi:10.1007/s10115-009-0227-x fatcat:qv42q347yfetxnqvsak2z3wtei

Cutting melted butter? Common Ground inconsistencies management in dialogue systems using graph databases

Maria Di Maro, Antonio Origlia, Francesco Cutugno
2021 Italian Journal of Computational Linguistics  
In this work, a spoken dialogue system architecture capable of dealing with Common Ground inconsistencies is proposed.  ...  Appropriate question forms are, indeed, adopted for the occurring type of common ground conflict, based on previous experiments, which showed that providing automatic dialogue systems with such grounding  ...  In this way, a hypothetical common ground is created to check for consistency based on the rules defined in the graph.  ... 
doi:10.4000/ijcol.892 fatcat:i4g5hxhf4ne7vl4d4ivgctkzyu

Learning to Represent Programs with Graphs [article]

Miltiadis Allamanis, Marc Brockschmidt, Mahmoud Khademi
2018 arXiv   pre-print
For example, long-range dependencies induced by using the same variable or function in distant locations are often not considered.  ...  In this work, we present how to construct graphs from source code and how to scale Gated Graph Neural Networks training to such large graphs.  ...  We consider it as a first proxy for the core challenge of learning the meaning of source code, as it requires to probabilistically refine standard information included in type systems.  ... 
arXiv:1711.00740v3 fatcat:7ncbkhsxhncbhlbjfo6lqetory

Approaching the Symbol Grounding Problem with Probabilistic Graphical Models

Stefanie Tellex, Thomas Kollar, Steven Dickerson, Matthew R. Walter, Ashis Gopal Banerjee, Seth Teller, Nicholas Roy
2011 The AI Magazine  
We first describe an early result, a generative model that factors according to the sequential structure of language, and then discuss our new framework, generalized grounding graphs (G3).  ...  The G3 framework dynamically instantiates a probabilistic graphical model for a natural language input, enabling a mapping between words in language and concrete objects, places, paths and events in the  ...  Next we presented a hierarchical model, called Generalized Grounding Graphs (G 3 ), that is able to learn word meanings from corpora and compose them to understand novel commands.  ... 
doi:10.1609/aimag.v32i4.2384 fatcat:o52l2szpfvaxfkiphy5q7uv7x4

roadscene2vec: A Tool for Extracting and Embedding Road Scene-Graphs [article]

Arnav Vaibhav Malawade, Shih-Yuan Yu, Brandon Hsu, Harsimrat Kaeley, Anurag Karra, Mohammad Abdullah Al Faruque
2021 arXiv   pre-print
The goal of roadscene2vec is to enable research into the applications and capabilities of road scene-graphs by providing tools for generating scene-graphs, graph learning models to generate spatio-temporal  ...  scene-graph embeddings, and tools for visualizing and analyzing scene-graph-based methodologies.  ...  Authors in [25] propose using a probabilistic graph approach for explainable traffic collision inference.  ... 
arXiv:2109.01183v2 fatcat:3xlwjy4hj5cx3j7pd42x4tmurm

Strategic port graph rewriting: an interactive modelling framework

MARIBEL FERNÁNDEZ, HÉLÈNE KIRCHNER, BRUNO PINAUD
2018 Mathematical Structures in Computer Science  
We present strategic port graph rewriting as a basis for the implementation of visual modelling tools.  ...  The traditional operators found in strategy languages for term rewriting have been adapted to deal with the more general setting of graph rewriting, and some new constructs have been included in the strategy  ...  We also thank Jason Vallet for implementing several features of Porgy, writing the documentation and developing the social network propagation influence example.  ... 
doi:10.1017/s0960129518000270 fatcat:t34y2fatgfhglp6c4b4savxq6q

Toward Information Theoretic Human-Robot Dialog

Stefanie Tellex, Pratiksha Thaker, Robin Deits, Thomas Kollar, Nicholas Roy
2012 Robotics: Science and Systems VIII  
After receiving an answer, the robot fuses information from the command, the question, and the answer in a joint probabilistic graphical model in the G 3 framework.  ...  To enable a robot to recover from a failure to understand a natural language utterance, this paper describes an information-theoretic strategy for asking targeted clarifying questions and using information  ...  In order to derive an expression for the robot's uncertainty about groundings in the external world, our approach builds on the Generalized Grounding Graph (G 3 ) framework [18, 17] .  ... 
doi:10.15607/rss.2012.viii.052 dblp:conf/rss/TellexTDKR12 fatcat:5y3ohhn6bjgplflrdtftqtr2ha

A Systematic Survey on Deep Generative Models for Graph Generation [article]

Xiaojie Guo, Liang Zhao
2020 arXiv   pre-print
Owing to its wide range of applications, generative models for graphs have a rich history, which, however, are traditionally hand-crafted and only capable of modeling a few statistical properties of graphs  ...  As one of a critical problem in this area, graph generation considers learning the distributions of given graphs and generating more novel graphs.  ...  For the score-based generative modeling process, the core is to design a plain graph generation framework based on score function [101] .  ... 
arXiv:2007.06686v2 fatcat:xox7apwdvbfhlgnsgrr3w3rv5m
« Previous Showing results 1 — 15 out of 6,364 results