13,421 Hits in 4.1 sec

Extracting common sense knowledge from text for robot planning

Peter Kaiser, Mike Lewis, Ronald P. A. Petrick, Tamim Asfour, Mark Steedman
2014 2014 IEEE International Conference on Robotics and Automation (ICRA)  
As a result, we aim to automate the process of acquiring general common sense knowledge of objects, relations, and actions, by extracting such information from large amounts of natural language text, written  ...  We present two methods for knowledge acquisition, requiring only limited human input, which focus on the inference of spatial relations from text.  ...  By contrast, the techniques proposed in this paper allow the robot to consider likely locations for an object, informed by common sense knowledge.  ... 
doi:10.1109/icra.2014.6907402 dblp:conf/icra/KaiserLPAS14 fatcat:f54ibsngczaitpuqyk7rx7yoqu

Grounded spatial symbols for task planning based on experience

Kai Welke, Peter Kaiser, Alexey Kozlov, Nils Adermann, Tamim Asfour, Mike Lewis, Mark Steedman
2013 2013 13th IEEE-RAS International Conference on Humanoid Robots (Humanoids)  
We demonstrate how spatial knowledge can be extracted from these two sources of experience.  ...  This representation is grounded on the sensorimotor level by means of exploration and on the language level by making use of common sense knowledge.  ...  ACKNOWLEDGMENT The research leading to these results has received funding from the European Union Seventh Framework Programme FP7/2007-2013 under grant agreement N o 270273 (Xperience).  ... 
doi:10.1109/humanoids.2013.7030018 dblp:conf/humanoids/WelkeKKAALS13 fatcat:a6avmppfbfhy7nt4say2ltgdsq

Building a General Knowledge Base of Physical Objects for Robots [chapter]

Valerio Basile, Elena Cabrio, Fabien Gandon
2016 Lecture Notes in Computer Science  
We extract an RDF knowledge base by automatically reading text on the Web and applying simple inference rules.  ...  The obtained common sense object relations are ready to be used in a domestic robotic setting, e.g. "a frying pan is usually located in the kitchen".  ...  for a domestic robot; ii) then, to learn common knowledge about objects in general, we also experimented with open domain text.  ... 
doi:10.1007/978-3-319-47602-5_2 fatcat:b7fjw3u2yje5leylolxi3t4wve

Semantic Mapping for Mobile Robots in Indoor Scenes: A Survey

Xiaoning Han, Shuailong Li, Xiaohui Wang, Weijia Zhou
2021 Information  
Sensing and mapping its surroundings is an essential requirement for a mobile robot. Geometric maps endow robots with the capacity of basic tasks, e.g., navigation.  ...  A semantic map can help robots to behave in human rules, plan and perform advanced tasks, and communicate with humans on the conceptual level.  ...  The conceptual layer contains the relations linking lower-level sensory information to common-sense knowledge, as well as a static ontology of common-sense knowledge.  ... 
doi:10.3390/info12020092 fatcat:n37meye6dzga3padaaal43gjbu

Domain Authoring Assistant for Intelligent Virtual Agents [article]

Sepehr Janghorbani and Ashutosh Modi and Jakob Buhmann and Mubbasir Kapadia
2019 arXiv   pre-print
Also a team of engineers has to manually translate the natural language description of a character's personality into the planning domain knowledge.  ...  into a planning domain.  ...  For these suggestions a common sense knowledge-base is queried, i.e., ConceptNet [41] .  ... 
arXiv:1904.03266v1 fatcat:d6vawkmqknaanhxfd2p6gflgem

MaestROB: A Robotics Framework for Integrated Orchestration of Low-Level Control and High-Level Reasoning [article]

Asim Munawar, Giovanni De Magistris, Tu-Hoa Pham, Daiki Kimura, Michiaki Tatsubori, Takao Moriyama, Ryuki Tachibana, Grady Booch
2018 arXiv   pre-print
Our framework helps Pepper perceive the human demonstration and generate a sequence of actions for UR5 (collaborative robot arm from Universal Robots), which ultimately performs the assembly (e.g. insertion  ...  To realize this, it handles a hierarchical structure by using the knowledge stored in the forms of ontology and rules for bridging among different levels of instructions.  ...  Raw stream from microphone is extracted by text extractor that calls IBM Watson Speech-To-Text (STT) API.  ... 
arXiv:1806.00802v1 fatcat:7sywrrpiebfudckfmmu7kdg6sa

Putting People's Common Sense into Knowledge Bases of Household Robots [chapter]

Lars Kunze, Moritz Tenorth, Michael Beetz
2010 Lecture Notes in Computer Science  
We present a system that converts commonsense knowledge from the large Open Mind Indoor Common Sense database from natural language into a Description Logic representation that allows for automated reasoning  ...  and for relating it to other sources of knowledge.  ...  Acknowledgments We would like to thank the Honda Research Institute USA Inc. for providing the OMICS data.  ... 
doi:10.1007/978-3-642-16111-7_17 fatcat:dgqjzjpncvdfjhglhckxh5uxdy

Extracting common sense knowledge via triple ranking using supervised and unsupervised distributional models

Soufian Jebbara, Valerio Basile, Elena Cabrio, Philipp Cimiano, Claudia d'Amato, Agnieszka Lawrynowicz, Jens Lehmann
2018 Semantic Web Journal  
Our motivation is to extract manipulation-relevant knowledge that can support robots' action planning.  ...  In this paper we are concerned with developing information extraction models that support the extraction of common sense knowledge from a combination of unstructured and semi-structured datasets.  ...  Rather, our goal is to extract prototypical common sense background knowledge from large corpora.  ... 
doi:10.3233/sw-180302 fatcat:lugtnzrphzhpvgguqkixcchowe

Understanding and executing instructions for everyday manipulation tasks from the World Wide Web

Moritz Tenorth, Daniel Nyga, Michael Beetz
2010 2010 IEEE International Conference on Robotics and Automation  
Instead composing them from atomic actions -the common approach in robot planning -we propose to transform task descriptions on web sites like into executable robot plans.  ...  We present methods for automatically converting the instructions from natural language into a formal, logic-based representation, for resolving the word senses using the WordNet database and the Cyc ontology  ...  sense knowledge.  ... 
doi:10.1109/robot.2010.5509955 dblp:conf/icra/TenorthNB10 fatcat:pltzmiz2yfg4talcrmvmc6yvk4

The RACE Project

Joachim Hertzberg, Jianwei Zhang, Liwei Zhang, Sebastian Rockel, Bernd Neumann, Jos Lehmann, Krishna S. R. Dubba, Anthony G. Cohn, Alessandro Saffiotti, Federico Pecora, Masoumeh Mansouri, Štefan Konečný (+9 others)
2014 Künstliche Intelligenz  
This paper introduces the general system architecture; it then sketches some results in detail regarding hybrid reasoning and planning used in RACE, and instances of learning from the experiences of real  ...  Enhancement of robot competence is operationalized in terms of performance quality and description length of the robot instructions, and such enhancement is shown to result from the RACE system.  ...  See text for more explanations. Fig. 3 3 The basic RACE architecture; modified from [20] .  ... 
doi:10.1007/s13218-014-0327-y fatcat:3l6fgfutxbchromaxnjfx3ycmi

Learning Task Knowledge from Dialog and Web Access

Vittorio Perera, Robin Soetens, Thomas Kollar, Mehdi Samadi, Yichao Sun, Daniele Nardi, René van de Molengraft, Manuela Veloso
2015 Robotics  
the autonomous service mobile robots, and Mike Licitra for the design and construction of the always-functional and reliable CoBot robot platform.  ...  Finally, the work would not have been possible without the remarkable performance of the CoBot robots, for which we thank Joydeep Biswas, Brian Coltin, and Stephanie Rosenthal, for their development of  ...  about objects deterministically, based on a single highly-probable speech-to-text candidate [26] ; some using large amounts of written text to extract common-sense knowledge about object locations and  ... 
doi:10.3390/robotics4020223 fatcat:4yzwwl2sfndazkurawikmly2v4

Textual Signs Reading for Indoor Semantic Map Construction

Basem Ibraheem, Abeer Hamdy, Nevien Darwish
2012 International Journal of Computer Applications  
In addition, they consider landmarks for the service robots. This paper is a continuous work of developing a framework for creating a semantic map for indoor environment using mobile robot [17] .  ...  Semantic maps have come up to facilitate high-level human robot interaction like "deliver a laptop for maintenance".  ...  In addition, the human robot interface will be much user friendly if it can control the robot with environment entities that will be common between human and robots, for example, if the robot is required  ... 
doi:10.5120/8459-2268 fatcat:7teqnksekzevndk7l32mkpfdn4

Integrating Answer Set Programming with Semantic Dictionaries for Robot Task Planning

Dongcai Lu, Yi Zhou, Feng Wu, Zhao Zhang, Xiaoping Chen
2017 Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence  
In this paper, we propose a novel integrated task planning system for service robot in domestic domains.  ...  Notably, we deployed the proposed planning system on our service robot for the annual RoboCup@Home competitions and achieved very encouraging results.  ...  For future work, one potential direction is to automatically extract knowledge about actions from not only semantic dictionaries but also other resources including plain texts and web pages.  ... 
doi:10.24963/ijcai.2017/609 dblp:conf/ijcai/LuZWZC17 fatcat:mwtjukffevgzndlpe6drqkfgtq

Understanding User Instructions by Utilizing Open Knowledge for Service Robots [article]

Dongcai Lu, Feng Wu, Xiaoping Chen
2016 arXiv   pre-print
To address this, we propose novel algorithms by utilizing semantic roles of common verbs defined in semantic dictionaries and integrating multiple open knowledge to generate task plans.  ...  To verify and evaluate our approach, we implemented a prototype system using knowledge from several open resources.  ...  When a robot tries to plan with put-Placing as its action verb (verb sense) for an instruction, our NLP components will try to extract appropriate entities for every semantic roles specified in the definition  ... 
arXiv:1606.02877v1 fatcat:dlaibdtiyncdtamzldj5jb5jym

Enabling Robots to Understand Incomplete Natural Language Instructions Using Commonsense Reasoning [article]

Haonan Chen, Hao Tan, Alan Kuntz, Mohit Bansal, Ron Alterovitz
2020 arXiv   pre-print
Our results show the feasibility of a robot learning commonsense knowledge automatically from web-based textual corpora, and the power of learned commonsense reasoning models in enabling a robot to autonomously  ...  However, natural language instructions are often missing information that would be obvious to a human based on environmental context and common sense, and hence does not need to be explicitly stated.  ...  common sense.  ... 
arXiv:1904.12907v2 fatcat:gs4g2ijdnrds7afl6dggvbtwlu
« Previous Showing results 1 — 15 out of 13,421 results