Biologically inspired intrinsically motivated learning for service robots based on novelty detection and habituation

Author(s):  
Yiannis Gatsoulis ◽  
Chris Burbridge ◽  
T. Martin McGinnity
Author(s):  
Michael Grunwald ◽  
Matthias Hermann ◽  
Fabian Freiberg ◽  
Matthias O. Franz

2018 ◽  
Vol 2018 ◽  
pp. 1-16
Author(s):  
Ester Martinez-Martin ◽  
Angel P. del Pobil

Aimed at building autonomous service robots, reasoning, perception, and action should be properly integrated. In this paper, the depth cue has been analysed as an early stage given its importance for robotic tasks. So, from neuroscience findings, a hierarchical four-level dorsal architecture has been designed and implemented. Mainly, from a stereo image pair, a set of complex Gabor filters is applied for estimating an egocentric quantitative disparity map. This map leads to a quantitative depth scene representation that provides the raw input for a qualitative approach. So, the reasoning method infers the data required to make the right decision at any time. As it will be shown, the experimental results highlight the robust performance of the biologically inspired approach presented in this paper.


2013 ◽  
Vol 133 (1) ◽  
pp. 18-27 ◽  
Author(s):  
Hisato Fukuda ◽  
Satoshi Mori ◽  
Katsutoshi Sakata ◽  
Yoshinori Kobayashi ◽  
Yoshinori Kuno

2020 ◽  
Vol 19 (10) ◽  
pp. 1965-1986
Author(s):  
T.A. Komkina ◽  
M.A. Nikonova ◽  
M.G. Dubinina

Subject. The article analyzes development trends in certain types of service robots, namely, hybrid UAVs, bionic prosthetic hands, robotic vacuum cleaners. Objectives. We focus on identifying the main trends in the development of certain types of service robots, building dynamic models of their technical indicators and models of dependence of their price and weight on absolute characteristics and technical parameters. Methods. The study employs methods of correlation and multiple regression analysis. The data of the IFR, the Remotely Piloted Aircraft System, and websites of robot manufacturers serve as the informational basis of the paper. Results. The modeling unveils positive correlation between the integrated indicator of the technical level of hybrid UAVs of convertiplane type and the wingspan. The analysis of modern bionic prosthetic hands shows that the developers focus on optimizing the structure of the prosthetic, however, as the functions of the hand improve, the weight of bionic hand increases. The main factors influencing the price of robot vacuum cleaners are their power, weight, and operating hours. Conclusions. The unit price of a complex indicator of the technical level of hybrid UAVs is lower than the corresponding indicator of fixed-wing UAVs, reflecting a greater efficiency of hybrid UAVs. The analysis of technical indicators of robotic prosthetics (using the case of bionic hands) shows that any improvement of functional characteristics leads to deterioration of weight. The analysis of technical and economic indicators of robotic vacuum cleaners reveals a positive correlation between the price and weight, operating hours and power.


Sign in / Sign up

Export Citation Format

Share Document