Towards a cognitive architecture for self-supervised transfer learning for objects detection with a Humanoid Robot

2020 ◽  
Author(s):  
Jonas Gonzalez-Billandon ◽  
Alessandra Sciutti ◽  
Giulio Sandini ◽  
Francesco Rea
Keyword(s):  
Transfer Learning ◽  
Humanoid Robot ◽  
Cognitive Architecture ◽  
Objects Detection

A cognitive architecture for a humanoid robot: a first approach

2006 ◽  
Author(s):  
C. Burghart ◽  
R. Mikut ◽  
R. Stiefelhagen ◽  
T. Asfour ◽  
H. Holzapfel ◽  
...  
Keyword(s):  
Humanoid Robot ◽  
Cognitive Architecture

scholarly journals Social signs processing in a cognitive architecture for an humanoid robot

2018 ◽  
Vol 123 ◽  
pp. 63-68 ◽  
Author(s):  
Agnese Augello ◽  
Emanuele Cipolla ◽  
Ignazio Infantino ◽  
Adriano Manfré ◽  
Giovanni Pilato ◽  
...  
Keyword(s):  
Humanoid Robot ◽  
Cognitive Architecture

IMPLEMENTATION OF COGNITIVE CONTROL FOR A HUMANOID ROBOT

2008 ◽  
Vol 05 (04) ◽  
pp. 547-586 ◽  
Author(s):  
KAZUHIKO KAWAMURA ◽  
STEPHEN M. GORDON ◽  
PALIS RATANASWASD ◽  
ERDEM ERDEMIR ◽  
JOSEPH F. HALL
Keyword(s):  
Cognitive Control ◽  
Control Systems ◽  
Intelligent Control ◽  
Humanoid Robot ◽  
Cognitive Architecture ◽  
World Systems ◽  
Control Techniques ◽  
Robot Architecture ◽  
Cognitive Activities ◽  
Different Levels

Engineers have long employed control systems utilizing models and feedback loops to control real-world systems. Limitations of model-based control led to a generation of intelligent control techniques such as adaptive and fuzzy control. The human brain, on the other hand, is known to process a variety of inputs in parallel, and shift between different levels of cognitive activities while ignoring distractions to focus on the task in hand. This process, known as cognitive control in psychology, is unique to humans and a handful of animals. We are interested in implementing such cognitive control functionalities for our humanoid robot ISAC. This paper outlines the features of multiagent-based cognitive architecture for a humanoid robot and the progress made toward the realization of cognitive control functionalities using attention, working memory and internal rehearsal. Several experiments have been conducted to show that the implementation of an integrated cognitive robot architecture is feasible.

scholarly journals Enaction as a Conceptual Framework for Developmental Cognitive Robotics

2010 ◽  
Vol 1 (2) ◽  
Author(s):  
David Vernon
Keyword(s):  
Cognitive Abilities ◽  
Humanoid Robot ◽  
Cognitive Architecture ◽  
Cognitive System ◽  
Cognitive Robotics ◽  
Robotic Systems ◽  
Sense Making ◽  
Cognitive Systems ◽  
Core Set ◽  
The World

AbstractThis paper provides an accessible introduction to the cognitive systems paradigm of enaction and shows how it forms a practical framework for robotic systems that can develop cognitive abilities. The principal idea of enaction is that a cognitive system develops it own understanding of the world around it through its interactions with the environment. Thus, enaction entails that the cognitive system operates autonomously and that it generates its own models of how the world works. A discussion of the five key elements of enaction — autonomy, embodiment, emergence, experience, and sense-making — leads to a core set of functional, organizational, and developmental requirements which are then used in the design of a cognitive architecture for the iCub humanoid robot.

Task Oriented Control of a Humanoid Robot Through the Implementation of a Cognitive Architecture

2016 ◽  
Vol 85 (1) ◽  
pp. 3-25 ◽  
Author(s):  
Daniel Hernández García ◽  
Concepción A. Monje ◽  
Carlos Balaguer
Keyword(s):  
Humanoid Robot ◽  
Cognitive Architecture ◽  
Task Oriented

scholarly journals Improving Street Object Detection Using Transfer Learning: From Generic Model to Specific Model

2018 ◽  
Vol 22 (6) ◽  
pp. 869-874
Author(s):  
Wei Liu ◽  
◽  
Shu Chen ◽  
Longsheng Wei
Keyword(s):  
Object Detection ◽  
Transfer Learning ◽  
Specific Model ◽  
Intelligent Vehicles ◽  
Fine Tuning ◽  
Generic Model ◽  
Learning Methods ◽  
Urban Street ◽  
General Object ◽  
Objects Detection

A high accuracy rate of street objects detection is significant in realizing intelligent vehicles. Algorithms based on convolution neural network (CNN) currently exhibit reasonable performance in general object detection. For example SSD and YOLO can detect a wide variety of objects in 2D images in real time; however the performance is not sufficient for street objects detection, especially in complex urban street environments. In this study, instead of proposing and training a new CNN model, we use transfer learning methods to enable our specific model to learn from a generic CNN model to achieve good performance. The transfer learning methods include fine-tuning the pretrained CNN model with a self-made dataset, and adjusting the CNN model structure. We analyze the transfer learning results based on fine-tuning SSD with self-made datasets. The experimental results based on the transfer learning method show that the proposed method is effective.

Sign in / Sign up

Export Citation Format

Share Document