Filters








153,456 Hits in 6.8 sec

Surveying Human Habit Modeling and Mining Techniques in Smart Spaces

Francesco Leotta, Massimo Mecella, Daniele Sora, Tiziana Catarci
2019 Future Internet  
In this paper, we propose a Systematic Literature Review (SLR) that classifies most influential approaches in the area of smart spaces according to a set of dimensions identified by answering a set of  ...  executing actions, giving suggestions and sending alarms.  ...  The rules structure follows the Event-Condition-Action (ECA) paradigm, borrowed by database techniques. The rules specify how the system has to react to a given event in a specific context.  ... 
doi:10.3390/fi11010023 fatcat:hdvhtvf7qbavthdxdwjrwfvjy4

Robot Motion Planning in Learned Latent Spaces [article]

Brian Ichter, Marco Pavone
2018 arXiv   pre-print
Notably, these networks can be trained through only raw data of the system's states and actions along with a supervising collision checker.  ...  This paper presents Latent Sampling-based Motion Planning (L-SBMP), a methodology towards computing motion plans for complex robotic systems by learning a plannable latent representation.  ...  The latent space is trained from a series of trajectories from the robotic system in operation; i.e., a sequence of states x t and actions u t .  ... 
arXiv:1807.10366v2 fatcat:r26v3snl45edpfmy3wr6km3zhm

Challenge balancing for personalised game spaces

Sander Bakkes, Shimon Whiteson, Guangliang Li, George Viorel Visniuc, Efstathios Charitos, Norbert Heijne, Arjen Swellengrebel
2014 2014 IEEE Games Media Entertainment  
Challenge Balancing for Personalised Game Spaces Bakkes, S.C.J.; Whiteson, S.A.; Li, G.; Viniuc, G.V.; Charitos, E.; Heijne, N.; Swellengrebel, A.  ...  for the individual user in online gameplay -employing the learned feedback model and a straightforward model of user abandonment.  ...  for learning a feedback model (i.e., the part of the parameter space that is not covered by domain knowledge of the game designer).  ... 
doi:10.1109/gem.2014.7047971 dblp:conf/gamesem/BakkesWLVCHS14 fatcat:jrz3fwd4jngy7ehbyuhvc2cplq

Enabling Visual Action Planning for Object Manipulation through Latent Space Roadmap [article]

Martina Lippi, Petra Poklukar, Michael C. Welle, Anastasiia Varava, Hang Yin, Alessandro Marino, Danica Kragic
2021 arXiv   pre-print
We propose a Latent Space Roadmap (LSR) for task planning which is a graph-based structure globally capturing the system dynamics in a low-dimensional latent space.  ...  We present a framework for visual action planning of complex manipulation tasks with high-dimensional state spaces, focusing on manipulation of deformable objects.  ...  Challenges of State Representation Learning for Planning. For planning, the system dynamics should also be captured in the latent space.  ... 
arXiv:2103.02554v2 fatcat:cygugk5oiva4vczgwvkotgg4am

Temporal BYY Encoding, Markovian State Spaces, and Space Dimension Determination

L. Xu
2004 IEEE Transactions on Neural Networks  
, especially with a new learning mechanism that makes selection of the state number or the dimension of state space either automatically during adaptive learning or subsequently after learning via model  ...  Index Terms-Gated multitemporal models, harmony learning, hidden Markov model, linear state spaces, space dimension, state selection, temporal Bayesian Ying-Yang (BYY) system, temporal factor analysis.  ...  One key problem is how to decide the scales of the state spaces (i.e., the numbers , , ).  ... 
doi:10.1109/tnn.2004.833302 pmid:18238092 fatcat:g2hol2l5rfgrpj3l2ggejjc4vm

The State Space of Artificial Intelligence

Holger Lyre
2020 Minds and Machines  
The goal of the paper is to develop and propose a general model of the state space of AI.  ...  As the distinguishing feature of such networks is the ability to self-learn, self-learning is identified as one important dimension of the AI state space.  ...  To view a copy of this licence, visit http://creat iveco mmons .org/licen ses/by/4.0/.  ... 
doi:10.1007/s11023-020-09538-3 fatcat:pjeseaxbqza2fizkuylv3hemfm

Robot Motion Planning in Learned Latent Spaces

Brian Ichter, Marco Pavone
2019 IEEE Robotics and Automation Letters  
Notably, these networks can be trained through only raw data of the system's states and actions along with a supervising collision checker.  ...  This letter presents latent sampling-based motion planning (L-SBMP), a methodology toward computing motion plans for complex robotic systems by learning a plannable latent representation.  ...  Schmerling and A. Majumdar for their helpful discussions on this work. The GPUs used for this research were donated by the NVIDIA Corporation.  ... 
doi:10.1109/lra.2019.2901898 fatcat:oxt53m3nhrdgjgnmhsl7iwtdiu

Phase Space Reconstruction Network for Lane Intrusion Action Recognition [article]

Ruiwen Zhang and Zhidong Deng and Hongsen Lin and Hongchao Lu
2021 arXiv   pre-print
and further characterized by a learnable Lyapunov exponent-like classifier that indicates discrimination in terms of average exponential divergence of state trajectories.  ...  In this paper, we propose a novel object-level phase space reconstruction network (PSRNet) for motion time series classification, aiming to recognize lane intrusion actions that occur 150m ahead through  ...  Each state vector of a dynamic system is expressed as a point in phase space.  ... 
arXiv:2102.11149v1 fatcat:pwrtg7v5nrhcnen5y2tom67gke

Classical Planning in Deep Latent Space: Bridging the Subsymbolic-Symbolic Boundary [article]

Masataro Asai, Alex Fukunaga
2017 arXiv   pre-print
), LatPlan finds a plan to the goal state in a symbolic latent space and returns a visualized plan execution.  ...  Meanwhile, although deep learning has achieved significant success in many fields, the knowledge is encoded in a subsymbolic representation which is incompatible with symbolic systems such as planners.  ...  A.1 State Augmentation As mentioned in the paper, the number of bits should be larger than the minimum encoding length log 2 |S| of the entire state space S. 36 bits in the latent layer sufficiently covers  ... 
arXiv:1705.00154v3 fatcat:b7kpd4rhrrcaflhkhgk5jfrcxe

Mental state space visualization for interactive modeling of personalized BCI control strategies [article]

Ilya Kuzovkin, Konstantin Tretyakov, Andero Uusberg, Raul Vicente
2019 bioRxiv   pre-print
state space.  ...  The system is based on a modification of the self-organizing map (SOM) algorithm and enables interactive communication between the user and the learning system through a visualization of user's mental  ...  Methods At the core of almost any BCI system lies a machine learning algorithm that classifies user brain signal into desired actions [37] .  ... 
doi:10.1101/867119 fatcat:ruyaj4golrhelc5xi6mdqjke3u

Semantic Modelling of Space [chapter]

Andrzej Pronobis, Patric Jensfelt, Kristoffer Sjöö, Hendrik Zender, Geert-Jan M. Kruijff, Oscar Martinez Mozos, Wolfram Burgard
2010 Cognitive Systems Monographs  
The cues are combined using a high-level cue integration scheme that learns how to optimally weight each cue [12] .  ...  As it provides coarse discretization of space it limits the state space of the path planning tasks and is also extremely useful for storing semantic information.  ... 
doi:10.1007/978-3-642-11694-0_5 fatcat:f2bloj56snevhoa2ti6u2c65pm

Machine learning in space: extending our reach

Amy McGovern, Kiri L. Wagstaff
2011 Machine Learning  
In addition to the challenges provided by the nature of space itself, the requirements of a space mission severely limit the use of many current machine learning approaches, and we encourage researchers  ...  We introduce the challenge of using machine learning effectively in space applications and motivate the domain for future researchers.  ...  with the National Aeronautics and Space Administration.  ... 
doi:10.1007/s10994-011-5249-4 fatcat:ztbxck675bdalpdueqnxqcloz4

A global space policy that would revive space exploration

Tanay Sharma, C.R.C Chatwin, R.C.D Young, P. Birch
2011 Proceedings of 5th International Conference on Recent Advances in Space Technologies - RAST2011  
It also focuses on how the establishment of a global space program could prove to be an innovative and cost-effective way of ensuring a robust space industry that serves the social and political objectives  ...  Current national space programs run by these countries cover various commercial, civilian and military aspects.  ...  The following sections of this paper will consider why nations might choose to initiate a national space program, the role of the United States and the impact of ITAR, and how establishing a global space  ... 
doi:10.1109/rast.2011.5966963 fatcat:apezhkycvngmznrf4hp53tnxmq

Exploring Complex Learning Spaces

Philip Wood, Paul Warwick
2018 Journal of Learning and Teaching in Higher Education  
This research intends to consider the complex interplay of these different spaces in the learning of students and also how they relate to the formal spaces of which we have a clearer understanding.  ...  Developing work already carried out by the project leaders on experimental learning spaces within the university, this is a project which aims to gain a better understanding of the 'learning lives' of  ...  also be seen as a wider ecology of learning (systems approach), and that they should be participatory, actively involving all participants.  ... 
doi:10.29311/jlthe.v1i1.2591 fatcat:r6yqecuqfreyxg262zutw7qpgi

Artificial intelligence in space [article]

George Anthony Gal, Cristiana Santos, Lucien Rapp, Réeka Markovich, Leendert van der Torre
2020 arXiv   pre-print
intelligence and machine learning defined as covering a wide range of innovations from autonomous objects with their own decision-making power to increasingly sophisticated services exploiting very large  ...  For this reason, a legal methodology must be developed that makes it possible to link intelligent systems and services to a system of rules applicable thereto.  ...  implement a course of action. 42 To this extent, it seems that launching State fault-based liability should not be premised solely on the decision to launch an intelligent space object, as such a sweeping  ... 
arXiv:2006.12362v1 fatcat:ag6oe3njfvba5d2tacaiqlpz6i
« Previous Showing results 1 — 15 out of 153,456 results