13,233 Hits in 2.9 sec

Mining a New Movement Pattern in RFID Database on Internet of Things

Kongfa Hu, Long Li
2014 International Journal of Database Theory and Application  
For solving the difficult problem, we proposed an algorithm called MTP to discovery the traveling partners from RFID database, it uses a intersecting method to mine moving objects with moving together  ...  In RFID database, there is a vast number of RFID trajectory data with the spatial-temporal characteristic. How to extract the traveling partners from these data is a difficult problem.  ...  Acknowledgments The research in the paper is supported by the National Natural Science  ... 
doi:10.14257/ijdta.2014.7.2.04 fatcat:azsme5vbanc7zav64zzbmkbujm

Study of Traveling Partners' Discovery Algorithm Based Closed Clustering and Intersecting

Kongfa Hu, Jiadong Xie, Chengjun Hu, Tao Yang, Yuqing Mao, Yun Hu, Long Li
2016 International Journal of Hybrid Information Technology  
Through experiments on the RFID synthetic dataset, we demonstrate the effectiveness and efficiency of our algorithm, thus show that our algorithm is suitable for discovering traveling partners in RFID  ...  Because RFID has many characteristics, it leads to become very difficult that extracting moving objects groups that together moving (ie. traveling partners) in a period of time from RFID trajectory stream  ...  Acknowledgements The research in the paper is supported by the National Natural Science  ... 
doi:10.14257/ijhit.2016.9.6.28 fatcat:67nmli7orjanniizqsrvis6cdq

Exploring Zero-Shot Emergent Communication in Embodied Multi-Agent Populations [article]

Kalesha Bullard, Franziska Meier, Douwe Kiela, Joelle Pineau, Jakob Foerster
2020 arXiv   pre-print
Effective communication is an important skill for enabling information exchange and cooperation in multi-agent settings.  ...  In this work, we extend this line of work to a new modality, by studying agents that learn to communicate via actuating their joints in a 3D environment.  ...  This means if agents fail to autonomously discover the induced structure, they will be relegated to overfitting to trajectory input with their current partners and though they might perhaps find some structure  ... 
arXiv:2010.15896v2 fatcat:bjsvutrfqbgf7gsw6pnchqvira

Quasi-Equivalence Discovery for Zero-Shot Emergent Communication [article]

Kalesha Bullard, Douwe Kiela, Franziska Meier, Joelle Pineau, Jakob Foerster
2021 arXiv   pre-print
In contrast, in this work, we present a novel problem setting and the Quasi-Equivalence Discovery (QED) algorithm that allows for zero-shot coordination (ZSC), i.e., discovering protocols that can generalize  ...  Instead, QED can iteratively discovers the symmetries in this setting and converges to the optimal ZSC policy.  ...  In general, discovering symmetries in a Dec-POMDP is an NP-hard problem since they correspond to graph-automorphisms [Lubiw, 1981] .  ... 
arXiv:2103.08067v2 fatcat:7dmoa76arnhbtmr26eu52w52w4

GroupSeeker: An Applicable Framework for Travel Companion Discovery from Vast Trajectory Data

Ruihong Yao, Fei Wang, Shuhui Chen, Shuang Zhao
2020 ISPRS International Journal of Geo-Information  
Due to the close relationship between behavior patterns and movement trajectory, trajectory data mining has been applied in numerous fields to find the behavior pattern.  ...  This paper proposes a flexible framework named GroupSeeker for discovering traveling companions in vast real-world trajectory data.  ...  Discovering accompanying or group behavior pattern is an important branch in mining mobile trajectory data.  ... 
doi:10.3390/ijgi9060404 fatcat:2km4cn6atzf4vgnll4oxj2cvey

RoboBrain: Large-Scale Knowledge Engine for Robots [article]

Ashutosh Saxena, Ashesh Jain, Ozan Sener, Aditya Jami, Dipendra K. Misra, Hema S. Koppula
2015 arXiv   pre-print
Building such an engine brings with it the challenge of dealing with multiple data modalities including symbols, natural language, haptic senses, robot trajectories, visual features and many others.  ...  In this paper we introduce a knowledge engine, which learns and shares knowledge representations, for robots to carry out a variety of tasks.  ...  This was also supported in part by Google PhD Fellowship to Koppula, and by Microsoft Faculty Fellowship, NSF CAREER Award and Sloan Fellowship to Saxena.  ... 
arXiv:1412.0691v2 fatcat:nbqybxn3zne67l6ksq4phbz4ia

Grounding Language to Autonomously-Acquired Skills via Goal Generation [article]

Ahmed Akakzia, Cédric Colas, Pierre-Yves Oudeyer, Mohamed Chetouani, Olivier Sigaud
2021 arXiv   pre-print
In a second stage (L -> G), it trains a language-conditioned goal generator to generate semantic goals that match the constraints expressed in language-based inputs.  ...  We showcase the additional properties of LGB w.r.t. both an end-to-end LC-RL approach and a similar approach leveraging non-semantic, continuous intermediate representations.  ...  For each goal-directed trajectory the agent performs, the social partner provides the description of one of the resulting transformations in the object relations.  ... 
arXiv:2006.07185v3 fatcat:3p653fah5zbxpghexuumq2nwua

Learning interaction protocols by mimicking understanding and reproducing human interactive behavior

Yasser Mohammad, Toyoaki Nishida
2015 Pattern Recognition Letters  
To achieve this goal, the robot should be able to recognize key patterns in human-human interactions.Moreover, the robot should be able to generate similar behaviors during its interaction with human partners  ...  In this paper, an unsupervised system is proposed that allows the robot to build a generative model of the interaction protocol using interaction records.  ...  MK++ is an extension of the MK algorithm proposed by Mueen et al. (2009) to discover the most similar pair of subsequences in a timeseries (Mohammad and Nishida, 2014) .  ... 
doi:10.1016/j.patrec.2014.11.010 fatcat:3hc3xtlbgbe5zfrwlbzmk74yaa

Example-based control of human motion

Eugene Hsu, Sommer Gentry, Jovan Popovi?
2004 Proceedings of the 2004 ACM SIGGRAPH/Eurographics symposium on Computer animation - SCA '04  
A dynamic programming algorithm can then be used to interpret an input control specification in terms of mapping instances.  ...  In the first, we synthesize a walking human character that follows a sampled trajectory. In the second, we generate a synthetic partner for a dancer whose motion is acquired through motion capture.  ...  Eugene Hsu was partially supported by an MIT Presidential Fellowship. Sommer Gentry was supported by a Department of Energy Computational Science Graduate Fellowship.  ... 
doi:10.1145/1028523.1028534 fatcat:rctnumhqhjcgpcffwh7kskuzmq

Pluralized life courses? An exploration of the life trajectories of individuals with psychiatric disorders

Nicolas S. Müller, Marlène Sapin, Gauthier Jacques-Antoine, Alina Orita, Eric D. Widmer
2011 International Journal of Social Psychiatry  
An additional reason for empirically addressing life trajectories of individuals with psychiatric problems relates to recent changes of family and occupational trajectories in relation to societal trends  ...  Therefore, it is essential to take into account the diversity of occupational and family trajectories when dealing with individuals in therapeutic settings.  ...  An additional reason for empirically addressing life trajectories of individuals with psychiatric problems relates to recent changes of family and occupational trajectories in relation to societal trends  ... 
doi:10.1177/0020764010393630 pmid:21447526 fatcat:mgv572466vbdljrrka4k33tmtm

Help Me Explore: Minimal Social Interventions for Graph-Based Autotelic Agents [article]

Ahmed Akakzia, Olivier Serris, Olivier Sigaud, Cédric Colas
2022 arXiv   pre-print
In social episodes, a social partner suggests goals at the frontier of the learning agent knowledge.  ...  In autotelic episodes, agents can either learn to master their own discovered goals or autonomously rehearse failed social goals; 2) GANGSTR, a graph-based autotelic agent for manipulation domains capable  ...  The authors would like to thank Hugo Caselles-Dupré, Pierre-Yves Oudeyer and Mohamed Chetouani for insightful discussions.  ... 
arXiv:2202.05129v1 fatcat:6f74scyoinfexjdzhhypy6exne

A Framework of Loose Travelling Companion Discovery from Human Trajectories

Elahe Naserian, Xinheng Wang, Xiaolong Xu, yu-ning Dong
2018 IEEE Transactions on Mobile Computing  
Finally, three algorithms have been developed to discover the proposed group patterns: (i) straightforward approach, (ii) smart-and-fast method, (iii) and opportunistic algorithm.  ...  In addition, we propose weakly continuous loose travelling companion pattern (WCLTCP) to relax the continuous time constraint in LTCP.  ...  Therefore, the groups should be reported in an incremental manner such that the discovery algorithm has to output the results while processing the trajectory data stream, simultaneously. • Efficiency:  ... 
doi:10.1109/tmc.2018.2813369 fatcat:be5oykto2nalzd4e75zo5kciwa

Interactive spatio-temporal cluster analysis of VAST challenge 2008 datasets

Gennady Andrienko, Natalia Andrienko
2009 Proceedings of the ACM SIGKDD Workshop on Visual Analytics and Knowledge Discovery Integrating Automated Analysis with Interactive Exploration - KDD '09  
We demonstrate the use of the method by applying it to two datasets from the VAST Challenge 2008: evacuation traces (trajectories of people movement) and landings and interdictions of migrant boats (point  ...  The method combines clustering with interactive visual displays, in particular, map and space-time cube.  ...  The work on interactive cluster analysis of trajectories was done together with our GeoPKDD partners from the University of Pisa, Italy.  ... 
doi:10.1145/1562849.1562850 dblp:conf/kdd/AndrienkoA09 fatcat:7iwrnshrknaibeoe75b5apm2ti

Homotopy switching model for dyad haptic interaction in physical collaborative tasks

Paul Evrard, Abderrahmane Kheddar
2009 World Haptics 2009 - Third Joint EuroHaptics conference and Symposium on Haptic Interfaces for Virtual Environment and Teleoperator Systems  
The main result of this paper is a new model based on homotopy switching between intrinsically distinct controllers, to encompass most behaviors encountered in dyadic haptic collaborative tasks through  ...  an intermediate object.  ...  Note that each partner may have a different planed trajectory to realize the same task.  ... 
doi:10.1109/whc.2009.4810879 dblp:conf/haptics/EvrardK09 fatcat:na5cni4a6vguzaiigtayypner4

Fast wall-following exploration with two cooperating mobile robots

Mohammad Al khawaldah, Salvatore Livatino
2010 2010 IEEE International Symposium on Industrial Electronics  
In this paper two cooperating robots are used to explore an unknown environment. The new technique aims to decrease the exploration time and the energy consumption.  ...  Then they employ frontierbased algorithm to complete exploring the remained unexplored areas.  ...  If a robot scans a cell and discovers that there is an obstacle in that cell, this cell is assigned to be an "O" cell until the end of the exploration. 6.  ... 
doi:10.1109/isie.2010.5637013 fatcat:txrpztzqlzcgzgpcssli63yfrq
« Previous Showing results 1 — 15 out of 13,233 results