Hierarchical incremental context modeling on robots

Doğan, Fethiye Irmak
Context is very crucial for robots to be able to adapt themselves to circumstances and to fulfill their tasks accordingly. There have been many studies on modeling context on robots, however, these studies either do not construct an incremental and hierarchical structure (i.e., use a fixed number of contexts and context layers) or determine the necessity of adding a new context by using rule-based approaches. In this thesis, we propose two different methods to model context. In the first method, we extend the Restricted Boltzmann Machines, a generative associative model, by incrementing the number of contexts and context layers when needed. This model constructs the hierarchical and incremental contextual representations by considering the confidence of the objects and contexts after each new scene encountered. Moreover, this deep incremental model obtains better or on-par results when compared to the incremental or non-incremental models in the literature on different tasks. In the second method, in contrast to our first method and the methods in the literature, determining the necessity of adding a new context is formulated as a learning problem. In order to be able to do that, Latent Dirichlet Allocation (LDA) model is used to generate the data with known number of contexts. The intermediate LDA models with/without the correct number of contexts are then fed to a Recurrent Model, which is trained to predict whether to add a new context or not. Our analysis on artificial and real datasets demonstrate that such a learning-based approach generalizes well, and is a promising approach for solving such incremental problems.


Online mining of human deep intention by proactive environment changes using deep neural networks
Er, Nur Baki; Erkmen, Aydan Müşerref; Department of Electrical and Electronics Engineering (2015)
This thesis focuses on surfacing human deep intention, which is known or assumed, in a smart environment that consists of autonomous robotic systems which can interact with the human. Deep intentions are defined as kind of actions that humans would like to behave but pushed deeper in the stack of the intentions in a daily life. The purpose of the designed system is to observe the human in the smart room for a while and to analyze human’s behaviors to offer the optimal set of system behavior to surface a des...
Swarm robotics: From sources of inspiration to domains of application
Şahin, Erol (Springer Verlag; 2005-09-01)
Swarm robotics is a novel approach to the coordination of large numbers of relatively simple robots which takes its inspiration from social insects. This paper proposes a definition to this newly emerging approach by 1) describing the desirable properties of swarm robotic systems, as observed in the system-level functioning of social insects, 2) proposing a definition for the term swarm robotics, and putting forward a set of criteria that can be used to distinguish swarm robotics research from other multi-r...
Alet (automated labeling of equipment and tools): A dataset for tool detection and human worker safety detection
Kurnaz, Fatih Can; Şahin, Erol; Kalkan, Sinan; Department of Computer Engineering (2020-8)
For humans and robots to be able to collaborate in different tasks in the same real-life environments, robots need to be able to work with tools. This requires that they can recognize the tools, and identify their positions and orientations so that they can use them for their goals. However, neither robotics nor the computer vision community had a dataset to facilitate addressing these problems in real-life environments. In this study, we address these challenges and provide a dataset dedicated to detecting...
Continual Learning for Affective Robotics: Why, What and How?
Churamani, Nikhil; Kalkan, Sinan; Gunes, Hatice (2020-01-01)
Creating and sustaining closed-loop dynamic and social interactions with humans require robots to continually adapt towards their users' behaviours, their affective states and moods while keeping them engaged in the task they are performing. Analysing, understanding and appropriately responding to human nonverbal behaviour and affective states are the central objectives of affective robotics research. Conventional machine learning approaches do not scale well to the dynamic nature of such real-world interac...
Lifelong learning and personalization in long-term human-robot interaction (LEAP-HRI)
Irfan, Bahar; Ramachandran, Aditi; Spaulding, Samuel; Kalkan, Sinan; Parisi, German I.; Gunes, Hatice (2021-03-08)
While most of the research in Human-Robot Interaction (HRI) focuses on short-term interactions, long-term interactions require bolder developments and a substantial amount of resources, especially if the robots are deployed in the wild. Robots need to incrementally learn new concepts or abilities in a lifelong fashion to adapt their behaviors within new situations and personalize their interactions with users to maintain their interest and engagement. The "Lifelong Learning and Personalization in Long-Term ...
Citation Formats
F. I. Doğan, “Hierarchical incremental context modeling on robots,” M.S. - Master of Science, Middle East Technical University, 2017.