Action recognition through action generation

Download
index.pdf
2010
Akgün, Barış
Show full item record
180
views
96
downloads
This thesis investigates how a robot can use action generation mechanisms to recognize the action of an observed actor in an on-line manner i.e., before the completion of the action. Towards this end, Dynamic Movement Primitives (DMP), an action generation method proposed for imitation, are modified to recognize the actions of an actor. Specifically, a human actor performed three different reaching actions to two different objects. Three DMP's, each corresponding to a different reaching action, were trained using this data. The proposed method used an object-centered coordinate system to define the variables for the action, eliminating the difference between the actor and the robot. During testing, the robot simulated action trajectories by its learned DMPs and compared the resulting trajectories against the observed one. The error between the simulated and the observed trajectories were integrated into a recognition signal, over which recognition was done. The proposed method was applied on the iCub humanoid robot platform using an active motion capture device for sensing. The results showed that the system was able to recognize actions with high accuracy as they unfold in time. Moreover, the feasibility of the approach is demonstrated in an interactive game between the robot and a human.
Computer engineering., Computer hardware.
http://etd.lib.metu.edu.tr/upload/12612306/index.pdf
https://hdl.handle.net/11511/19915
Graduate School of Natural and Applied Sciences, Thesis

Suggestions

Performance analysis of a power aware routing protocol for ad hoc networks
Yazıcı, Mehmet Akif; Bilgen, Semih; Department of Electrical and Electronics Engineering (2006)
In this thesis, performance of the Contribution Reward Routing Protocol with Shapley Value (CAP-SV), a power-aware routing protocol for ad hoc networking is analyzed. Literature study on ad hoc network routing and ower-awareness is given. The overhead induced by the extra packets of the redirection mechanism of CAP-SV is formulized and the factors affecting this overhead are discussed. Then, the power consumption of CAP-SV is analytically analized using a linear power consumption model. It is shown that CAP...
A fluid dynamics framework for control of mobile robot networks
Paç, Muhammed Raşid; Erkmen, Aydan Müşerref; Department of Electrical and Electronics Engineering (2007)
This thesis proposes a framework for controlling mobile robot networks based on a fluid dynamics paradigm. The approach is inspired by natural behaviors of fluids demonstrating desirable characteristics for collective robots. The underlying mathematical formalism is developed through establishing analogies between fluid bodies and multi-robot systems such that robots are modeled as fluid elements that constitute a fluid body. The governing equations of fluid dynamics are adapted to multi-robot systems and a...
Anomaly detection from personal usage patterns in web applications
Vural, Gürkan; Yöndem (Turhan), Meltem; Department of Computer Engineering (2006)
The anomaly detection task is to recognize the presence of an unusual (and potentially hazardous) state within the behaviors or activities of a computer user, system, or network with respect to some model of normal behavior which may be either hard-coded or learned from observation. An anomaly detection agent faces many learning problems including learning from streams of temporal data, learning from instances of a single class, and adaptation to a dynamically changing concept. The domain is complicated by ...
Reinforcement learning using potential field for role assignment in a multi-robot two-team game
Fidan, Özgül; Erkmen, İsmet; Department of Electrical and Electronics Engineering (2004)
In this work, reinforcement learning algorithms are studied with the help of potential field methods, using robosoccer simulators as test beds. Reinforcement Learning (RL) is a framework for general problem solving where an agent can learn through experience. The soccer game is selected as the problem domain a way of experimenting multi-agent team behaviors because of its popularity and complexity.
Direct perception of traversibility affordance on range images through learning on a mobile robot
Uğur, Emre; Şahin, Erol; Department of Computer Engineering (2006)
In this thesis, we studied how physical affordances of the environment, such as traversibility for a mobile robot, can be learned. In particular, we studied how the physical properties of the environment, as acquired from range images obtained from a 3D laser scanner mounted on a mobile robot platform, can specify the traversibility affordance. A physics based simulation environment is used during exploration trials, where the traversibility affordances and the relevant features for each behavior are learne...
Citation Formats
B. Akgün, “Action recognition through action generation,” M.S. - Master of Science, Middle East Technical University, 2010.
METU IIS - Integrated Information Service open@metu.edu.tr