Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation

Çelikkanat, Hande
Orhan, Guner
Pugeault, Nicolas
Guerin, Frank
Şahin, Erol
Kalkan, Sinan
In this paper, we formalize and model context in terms of a set of concepts grounded in the sensorimotor interactions of a robot. The concepts are modeled as a web using Markov Random Field (MRF), inspired from the concept web hypothesis for representing concepts in humans. On this concept web, we treat context as a latent variable of Latent Dirichlet Allocation (LDA), which is a widely-used method in computational linguistics for modeling topics in texts. We extend the standard LDA method in order to make it incremental so that: 1) it does not relearn everything from scratch given new interactions (i.e., it is online); and 2) it can discover and add a new context into its model when necessary. We demonstrate on the iCub platform that, partly owing to modeling context on top of the concept web, our approach is adaptive, online, and robust: it is adaptive and online since it can learn and discover a new context from new interactions. It is robust since it is not affected by irrelevant stimuli and it can discover contexts after a few interactions only. Moreover, we show how to use the context learned in such a model for two important tasks: object recognition and planning.


Steering self-organized robot flocks through externally guided individuals
Celikkanat, Hande; Şahin, Erol (Springer Science and Business Media LLC, 2010-09-01)
In this paper, we study how a self-organized mobile robot flock can be steered toward a desired direction through externally guiding some of its members. Specifically, we propose a behavior by extending a previously developed flocking behavior to steer self-organized flocks in both physical and simulated mobile robots. We quantitatively measure the performance of the proposed behavior under different parameter settings using three metrics, namely, (1) the mutual information metric, adopted from Information ...
Modeling human thinking about similarities by neuromatrices in the perspective of fuzzy logic
Grobelny, Jerzy; Michalski, Rafal; Weber, Gerhard Wilhelm (Springer Science and Business Media LLC, 2020-09-01)
In this work, we propose a new method for modeling human reasoning about objects' similarities. We assume that similarity depends on perceived intensities of objects' attributes expressed by natural language expressions such as low, medium, and high. We show how to find the underlying structure of the matrix with intensities of objects' similarities in the factor-analysis-like manner. The demonstrated approach is based on fuzzy logic and set theory principles, and it uses only maximum and minimum operators....
Learning and Using Context on a Humanoid Robot Using Latent Dirichlet Allocation
Celikkanat, Hande; Orhan, Guner; Pugeault, Nicolas; Guerin, Frank; Şahin, Erol; Kalkan, Sinan (2014-10-16)
In this work, we model context in terms of a set of concepts grounded in a robot's sensorimotor interactions with the environment. For this end, we treat context as a latent variable in Latent Dirichlet Allocation, which is widely used in computational linguistics for modeling topics in texts. The flexibility of our approach allows many-to-many relationships between objects and contexts, as well as between scenes and contexts. We use a concept web representation of the perceptions of the robot as a basis fo...
Improving reinforcement learning by using sequence trees
Girgin, Sertan; Polat, Faruk; Alhajj, Reda (Springer Science and Business Media LLC, 2010-12-01)
This paper proposes a novel approach to discover options in the form of stochastic conditionally terminating sequences; it shows how such sequences can be integrated into the reinforcement learning framework to improve the learning performance. The method utilizes stored histories of possible optimal policies and constructs a specialized tree structure during the learning process. The constructed tree facilitates the process of identifying frequently used action sequences together with states that are visit...
A Hopfield neural network with multi-compartmental activation
Akhmet, Marat (Springer Science and Business Media LLC, 2018-05-01)
The Hopfield network is a form of recurrent artificial neural network. To satisfy demands of artificial neural networks and brain activity, the networks are needed to be modified in different ways. Accordingly, it is the first time that, in our paper, a Hopfield neural network with piecewise constant argument of generalized type and constant delay is considered. To insert both types of the arguments, a multi-compartmental activation function is utilized. For the analysis of the problem, we have applied the ...
Citation Formats
H. Çelikkanat, G. Orhan, N. Pugeault, F. Guerin, E. Şahin, and S. Kalkan, “Learning Context on a Humanoid Robot using Incremental Latent Dirichlet Allocation,” IEEE TRANSACTIONS ON COGNITIVE AND DEVELOPMENTAL SYSTEMS, pp. 42–59, 2016, Accessed: 00, 2020. [Online]. Available: https://hdl.handle.net/11511/43339.