1,720,976 research outputs found
Enhancing Activity Recognition of Self-Localized Robot Through Depth Camera and Wearable Sensors
Full text linkRobots will become part of our everyday life as helpers and companions, sharing the environment with us. Thus, robots should become social and able to naturally interact with the users. Recognizing human activities and behaviors will enhance the capabilities of the robot to plan an appropriate action and tailor the approach according to what the user is doing. Therefore, this paper addresses the problem of providing mobile robots with the ability to recognize common daily activities. The fusion of heterogeneous data gathered by multiple sensing strategies, namely wearable inertial sensors, depth camera, and location features, is proposed to improve the recognition of human activity. In particular, the proposed work aims to recognize 10 activities using data from a depth camera mounted on a mobile robot able to self-localize in the environment and from customized sensors worn on the hand. Twenty users were asked to perform the selected activities in two different relative positions between them and the robot while the robot was moving. The analysis was carried out considering different combinations of sensors to evaluate how the fusion of the different technologies improves the recognition abilities. The results show an improvement of 13% in the F-measure when different sensors are considered with respect to the use of the sensors of the robot. In particular, the system is able to recognize not only the performed activity, but also the relative position, enhancing the robot capabilities to interact with the users
Two-person Activity Recognition using Skeleton Data
Full text linkHuman activity recognition is an important and active field of research
having a wide range of application in numerous fields, including ambient
assisted living. Although most of the researches are focused on the single
user, the ability to recognize two-person interactions is perhaps more
important for its social implications.
This paper presents a two-person activity recognition system that uses
skeleton data extracted from a depth camera. The human actions are encoded
using a set of a few basic postures obtained with an unsupervised
clustering approach. Multiclass Support Vector Machines (SVMs) are
used to build models on the training set, while the X-means algorithm
is employed to dynamically find the optimal number of clusters for each
sample during the classification phase. The system is evaluated on the
ISR-UoL and SBU datasets, reaching an overall accuracy of 0.87 and 0.88
respectively. Although the results show that the performances of the system
are comparable with the state-of-the-art, recognition improvements
are obtained with the activities related to health-care environments, showing
promise for applications in the assisted-living realm
Enabling Global Robot Navigation Based on a Cloud Robotics Approach
Full text linkIn the future, social robots will permeate our daily life. An autonomous robot that has to move among different buildings needs to manage huge amount of data, as a consequence it is clear that the configuration of the navigation
system becomes hard to manage. This paper presents a system, based on a cloud robotics paradigm, conceived to allow autonomous robots to navigate in indoor environment, which are not known a priori. The environment is divided into sub-maps and all the necessary information and the topological representation of the world, are stored into a remote cloud infrastructure. By means of specific environmental tags, composed of a set of ARTags and QR codes, the robot gets the access to the cloud service and it is able to update its navigation configuration in a dynamic and automatic way. Experiments have been conducted in order to choose an appropriate marker dimension and to demonstrate the feasibility of the proposed procedure
Connecting ROS and FIWARE: Concepts and Tutorial
Full text linkNowadays, the Cloud technology permeates our daily life, spread in various services and applications used by modern instruments, such as smartphones, computer, and IoT devices. Besides, the robotic field represents one of the future emerging markets. Nevertheless, these two distinct worlds seem to be very far from each other, due to the lack of common strategies and standards. The aim of this tutorial chapter is to provide a walkthrough to build a basic Cloud Robotics application using ROS and the FIWARE Cloud framework. At the beginning, the chapter offers step-by-step instructions to create and manage an Orion Context Broker running on a virtual machine. Then, the firos package is used to integrate the ROS topic communication using publishers and subscribers, providing a clear example. Finally, a more concrete use case is detailed, developing a Cloud Robotics application to control a ROS-based robot through the FIWARE framework. The code of the present tutorial is available at https://github.com/Raffa87/ROS_FIWARE_Tutorial, tested using ROS Indigo
Planning for Multiple Robots in a Smart Environment
No full textWe consider configuration planning in a real assistive system that consists of multiple robots embedded in a smart environment. Our configuration plans are fine-grained action plans which specify the causal, temporal, resource and information dependencies between individual sensing, computation, and actuation components. Components reside on-board the robots, like cameras or manipulation components, or they may be distributed in the environment, like presence sensors or elevators. Our configuration planner exhibits closed-loop performance, thanks to the fact that plans are represented as constraint networks, which are shared between the planner and the executor and updated during execution. This mechanism allows our system to react to contingencies at execution time. We illustrate our system on both simulated and real experiments performed in the context of a large EU project on robotics for elderly assistance
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Use Case Evaluation of a Cloud Robotics Teleoperation System (Short Paper)
No full textThe paper describes a generic Cloud Roboticsteleoperation system which allows to control in real-Time arobot (connected with a 4G network) having its video streamas feedback. The proposed system relies on the Azure CloudPlatform and on recent web technologies. Particularly, wepresent an use case experiment in which an operator in Slovakiacontrols a robot situated in Italy in order to evaluate its real-Time feasibility. We test the system to assess its performancesproviding the throughput value of the communication and theaverage delay between consecutive received packets on bothrobot and teleoperation side. Additionally, regarding the videostreaming, we test several packet sizes to establish a suitableimage quality. The results show how the chosen technologyallows to have real-Time performances in terms of video andvelocity commands streaming
Robotic delivery service in combined outdoor–indoor environments: technical analysis and user evaluation
Full text linkRobotic solutions for delivery tasks in urban and unstructured areas have represented a solid and considerable field of research in recent years. The aim of the proposed paper is to present the technical feasibility and usability of a robotic solution able to carry items from outdoor areas up to the user’s apartment and vice-versa. The proposed solution is based on three heterogeneous mobile platforms, working in three different environments (domestic, condominium, outdoor), able to cooperate among themselves and with other machines in the framework (i.e. the elevator of the condominium). The evaluation was performed in realistic environments involving 30 end-users
Design impact of acceptability and dependability in assisted living robotic applications
Full text linkThis paper presents the implementation and investigation of a novel user centred method, adopted to design, develop and test a personal robot system, composed of a mobile robotic platform and a smart environment, for assisting people at home. As robots need to work closely with humans, novel interactive engineering design approaches are required to develop service robots that are adherent to end users’ needs and that can be quickly employed in daily life. Particularly, this paper presents a methodology based on the simultaneous evaluation of dependability and acceptability, thus leading to an innovative approach for metrics and benchmarks that includes not only the main technical attributes of dependability, but also the parameters of acceptability, both implemented via a user-centered design and co-creative approach. Additionally, dependability and acceptability form the basis for defining standardized methodologies to test and evaluate robotic systems in dedicated experimental infrastructures (or robotic facilities), which are conceived to facilitate engineers in their studies and assessments
- …
