Continuous Goal-Directed Actions (CGDA)

cgda

Description

The search for the Grial of generalizing robot actions continues! In Continuous Goal-Directed Actions (CGDA), our robot imitation framework, an action is modelled as the changes it produces on the environment. First, record all the features you can off some user demonstrations. By features, we mean features! The robot joint q2 angle, a human hand Z coordinate, the percentage of a wall painted, the square of the room temperature plus ambient noise… Throw in a demonstration and feature selection algorithm, let it decide which demonstrations were consistent, and which features are relevant. You now have an action encoded as a CGDA model, which is essentially a multi-dimensional time series. As described in its first conference paper, recognition can be performed using costs such as those extracted by DTW, and execution can be achieved by evolutionary algorithms in a simulated environment. While we have performed some work in combining sequences of random movements, we are mostly content with the evolutionary strategies we later developed, such as IET. Additional references include the original S. Morante PhD thesis.

Entries:
Synthesis of bisphosphonate derivatives of ATP by T4 RNA ligase
FEBS Lett. num. 24 , vol. 580 , pages: 5723 – 5727 , 2006
E. Silles
Synthesis of (di)nucleoside polyphosphates by the ubiquitin activating enzyme E1
FEBS Lett. num. 27 , vol. 579 , pages: 6223 – 6229 , 2005
E. Silles

Entries:
Elbow Functional Compensation using a Lightweight MagnetorheologicalClutch.
Annual International Conference of the IEEE EMBS Boston, MassachusettsUSA, 5215-5218., -,
A. Flores D. Copaci D. Blanco L. Moreno
Design of a controllable wheelchair for simulation of real life conditions
In Proceedings of the 6th International Conference of the International Society for Gerontechnology, Pisa, Italy
J.G. Quijano
A design methodology to allow scalability of EAP materials as actuators
3rd World Congress on Biomimetics, Artificial Muscles & Nano-Bio, 2006, Laussane, Switzerland
D. Fernandez L. Moreno
Characterization of IPMC using standard testing methods
Smart Structures and Materials., 2006, San Diego, USA
D. Fernandez L. Moreno
Actuator design using Electroactive materials
Smart Sensors Actuators and MEMS II. Microtechnologies for the New Millenium. , 2005, Sevilla, Spain
D. Fernandez L. Moreno
A bio-inspired EAP actuator design methodology
Smart Structures and Materials, 2005, San Diego, USA
D. Fernandez L. Moreno
Towards standarization of EAP actuator test procedures
Smart Structures and Materials, San Diego, USA
D. Fernandez L. Moreno
Electroactive Polymer Actuator design for space applications
8th ESA Workshop on Advanced Space Technologies for Robotics and AutomationASTRA 2004, 2004, ESTEC, Noordwik, Netherlands
D. Fernandez L. Moreno

Entries:
Image Analysis in Life Sciences
chapter: Imaging blood vessels with confocal microscopy for quantitative analysis Signpost , ISBN: 978-81-308-0312, 2009
S.M. Arribas M. Abderrahim

Projects

Robots

Robot types & applications