Search results for "robotics"

N-QGN: Navigation Map from a Monocular Camera using Quadtree Generating Networks

2022

Monocular depth estimation has been a popular area of research for several years, especially since self-supervised networks have shown increasingly good results in bridging the gap with supervised and stereo methods. However, these approaches focus their interest on dense 3D reconstruction and sometimes on tiny details that are superfluous for autonomous navigation. In this paper, we propose to address this issue by estimating the navigation map under a quadtree representation. The objective is to create an adaptive depth map prediction that only extract details that are essential for the obstacle avoidance. Other 3D space which leaves large room for navigation will be provided with approxi…

Good Old-Fashioned Artificial Consciousness and the Intermediate Level Fallacy

2018

Recently, there has been considerable interest and effort to the possibility to design and implement conscious robots, i.e., the chance that a robot may have subjective experiences. However, typical approaches as the global workspace, information integration, enaction, cognitive mechanisms, embodiment, i.e., the Good Old-Fashioned Artificial Consciousness, henceforth, GOFAC, share the same conceptual framework. In this paper, we discuss GOFAC's basic tenets and their implication for AI and Robotics. In particular, we point out the intermediate level fallacy as the central issue affecting GOFAC. Finally, we outline a possible alternative conceptual framework towards robot consciousness.

Control of a PTZ camera in a hybrid vision system

2014

In this paper, we propose a new approach to steer a PTZ camera in the direction of a detected object visible from another fixed camera equipped with a fisheye lens. This heterogeneous association of two cameras having different characteristics is called a hybrid stereo-vision system. The presented method employs epipolar geometry in a smart way in order to reduce the range of search of the desired region of interest. Furthermore, we proposed a target recognition method designed to cope with the illumination problems, the distortion of the omnidirectional image and the inherent dissimilarity of resolution and color responses between both cameras. Experimental results with synthetic and real …

Smart camera design for intensive embedded computing

2005

Computer-assisted vision plays an important role in our society, in various fields such as personal and goods safety, industrial production, telecommunications, robotics, etc. However, technical developments are still rare and slowed down by various factors linked to sensor cost, lack of system flexibility, difficulty of rapidly developing complex and robust applications, and lack of interaction among these systems themselves, or with their environment. This paper describes our proposal for a smart camera with real-time video processing capabilities. A CMOS sensor, processor and, reconfigurable unit associated in the same chip will allow scalability, flexibility, and high performance.

Deep Learning for Classifying Physical Activities from Accelerometer Data

2021

Physical inactivity increases the risk of many adverse health conditions, including the world’s major non-communicable diseases, such as coronary heart disease, type 2 diabetes, and breast and colon cancers, shortening life expectancy. There are minimal medical care and personal trainers’ methods to monitor a patient’s actual physical activity types. To improve activity monitoring, we propose an artificial-intelligence-based approach to classify the physical movement activity patterns. In more detail, we employ two deep learning (DL) methods, namely a deep feed-forward neural network (DNN) and a deep recurrent neural network (RNN) for this purpose. We evaluate the proposed models on two phy…

Implementation and microbiological stability of dose-banded ganciclovir infusion bags prepared in series by a robotic system.

2018

Objectives The implementation of dose-banding (DB) in centralised, pharmacy-based cytotoxic drug preparation units allows the preparation of standardised doses in series. The aim of this study was to evaluate the feasibility of DB for the prescribing of ganciclovir (GV) infusion solutions and to investigate the microbiological stability of dose-banded, automatically prepared ready-to-administer GV infusion bags by media-fill simulation tests and sterility tests. Methods The frequency of prescription of GV doses was retrospectively analysed before and after implementing the DB scheme. Four dose-ranges or ‘bands’ and the corresponding standard doses (250, 300, 350, 400 mg) were identified. Th…

2019

Despite substantial advances in many different fields of neurorobotics in general, and biomimetic robots in particular, a key challenge is the integration of concepts: to collate and combine research on disparate and conceptually disjunct research areas in the neurosciences and engineering sciences. We claim that the development of suitable robotic integration platforms is of particular relevance to make such integration of concepts work in practice. Here, we provide an example for a hexapod robotic integration platform for autonomous locomotion. In a sequence of six focus sections dealing with aspects of intelligent, embodied motor control in insects and multipedal robots-ranging from comp…

Robotic transanal total mesorectal excision: Is the future now?

2021

Total mesorectal excision (TME) is the standard surgical treatment for the curative radical resection of rectal cancers. Minimally invasive TME has been gaining ground favored by the continuous technological advancements. New procedures, such as transanal TME (TaTME), have been introduced to overcome some technical limitations, especially in low rectal tumors, obese patients, and/or narrow pelvis. The earliest TaTME reports showed promising results when compared with the conventional laparoscopic TME. However, recent publications raised concerns regarding the high rates of anastomotic leaks or local recurrences observed in national series. Robotic TaTME (R-TaTME) has been proposed as a nove…

Robust and Decoupled Position and Stiffness Control for Electrically-Driven Articulated Soft Robots

2022

The control of articulated soft robots, i.e. robots with flexible joints and rigid links, presents a challenge due to their in- trinsic elastic elements and nonlinear force-deflection dependency. This letter first proposes a discrete-time delayed unknown input- state observer based on a nominal robot model that reconstructs the total torque disturbance vector, resulting from the imperfect knowledge of the elastic torque characteristic, external torques, and other model uncertainties. Then, it introduces a robust controller, that actively compensates for the estimated uncertainty and allows bounded stability for the tracking of independent link position and joint stiffness reference signals.…

Intention recognition in manufacturing applications

2015

In this article, we present a novel approach to intention recognition, based on the recognition and representation of state information in a cooperative human-robot environment. States are represented by a combination of spatial relations along with cardinal direction information. The output of the Intention Recognition Algorithms will allow a robot to help a human perform a perceived operation or, minimally, not cause an unsafe situation to occur. We compare the results of the Intention Recognition Algorithms to those of an experiment involving human subjects attempting to recognize the same intentions in a manufacturing kitting domain. In almost every case, results show that the Intention…