Gheorghe Mogan

Measurement and Geometric Modelling of Human Spine Posture for Medical Rehabilitation Purposes Using a Wearable Monitoring System Based on Inertial Sensors

This paper presents a mathematical model that can be used to virtually reconstruct the posture of the human spine. By using orientation angles from a wearable monitoring system based on inertial sensors, the model calculates and represents the curvature of the spine. Several hypotheses are taken into consideration to increase the model precision. An estimation of the postures that can be calculated is also presented. A non-invasive solution to identify the human back shape can help reducing the time needed for medical rehabilitation sessions. Moreover, it prevents future problems caused by poor posture.

Neural networks based reinforcement learning for mobile robots obstacle avoidance

We propose a new path planning algorithm based on the use of Q-learning and artificial neural networks.We analyze and model in VR the mobile robot PowerBot.We implement and test the proposed algorithm in both VR and real workspaces.The solution converges to collision-free trajectories in dynamic environments. This study proposes a new approach for solving the problem of autonomous movement of robots in environments that contain both static and dynamic obstacles. The purpose of this research is to provide mobile robots a collision-free trajectory within an uncertain workspace which contains both stationary and moving entities. The developed solution uses Q-learning and a neural network planner to solve path planning problems. The algorithm presented proves to be effective in navigation scenarios where global information is available. The speed of the robot can be set prior to the computation of the trajectory, which provides a great advantage in time-constrained applications. The solution is deployed in both Virtual Reality (VR) for easier visualization and safer testing activities, and on a real mobile robot for experimental validation. The algorithm is compared with Powerbots ARNL proprietary navigation algorithm. Results show that the proposed solution has a good conversion rate computed at a satisfying speed.

Evaluating human-robot interaction during a manipulation experiment conducted in immersive virtual reality

This paper presents the main highlights of a Human-Robot Interaction (HRI) study conducted during a manipulation experiment performed in Cave Automatic Virtual Environment (CAVE). Our aim is to assess whether using immersive Virtual Reality (VR) for testing material handling scenarios that assume collaboration between robots and humans is a practical alternative to similar real live applications. We focus on measuring variables identified as conclusive for the purpose of this study (such as the percentage of tasks successfully completed, the average time to complete task, the relative distance and motion estimate, presence and relative contact errors) during different manipulation scenarios. We present the experimental setup, the HRI questionnaire and the results analysis. We conclude by listing further research issues.

Using Eye Blinking for EOG-Based Robot Control

This paper proposes a new approach to real-time robot controlling by integrating an Electrooculography (EOG) measuring device within human-robot interaction (HRI). Our study focuses on controlling robots using EOG for fulfilling elementary robot activities such as basic motor movements and environment interaction. A new EOG-based HRI paradigm has been developed on the specific defined problem of eye blinking. The resulted model is tested using biometric capturing equipment. We propose a simple algorithm for real-time identification and processing of signals produced by eyes during blinking phases. We present the experimental setup and the results of the experiment. We conclude by listing further research issues.

NAO Robots Collaboration for Object Manipulation

This paper proposes a new method of collaboration within a team of twoindividual NAO robots that should execute together a complex operation. The Naorobots are developed so as not only to act individually, but also to cooperatewith other robots if they cannot accomplish the operation alone. This paperpresents a case study demonstrating the integration of the humanoid roboticsplatform Nao within a cooperation application. This specific scenario ofinterest takes place in a small simulated manufacturing environment; while thetask being the storage of a big object, with different shape and weight. Thisscenario is used to observe the impact and performance that this particularteam of humanoid robots has in an industrial environment.Finally we present the successful implementation of robot – robot cooperationcapabilities inspired by human behaviour.

Video-based evaluation of driver's visual attention using smartphones

In the recent period, video processing algorithms emerged as a valid solution to various problems, including the automation of some repetitive processes, for retrieving information from dynamic environments or the inspection of the physical state of human operators. On the other hand, with the latest advancements in the automotive industry, Advanced Driver Assistance Systems (ADASs) are becoming more and more common. It was just a matter of time until ADASs will rely heavily on the bio-cues processed from video steam. We present a system that obtains drivers head orientation, thus inferring the level of visual attention. The result of this research will be included in a Personal Navigation Assistant (PNA) based on dual camera mobile phones. We address the vision algorithms, the system architecture and the main implementation issues implied by the system.

Path and Trajectory Planning for Vehicles with Navigation Assistants

For autonomous vehicles an important problem is to plan and accurately follow the optimal trajectory between the start point and the target, without collision with the obstacles placed in the environment. In order to obtain a continuous motion along the planned path for a vehicle with navigation assistants, especially when avoiding obstacles, the transition between a straight segment and circle arcs has to be done through using an additional curve. This paper present an algorithm based on clothoid curves for optimal steering using as case a vehicle with navigation assistants. The developed algorithm has been tested in a real environment and results have been presented.

Control Interfaces for a Collaborative System Using LabView Package

In-robotics functions, performed by the software, include data acquisition, motor control, sensor signals processing, perception of objects and navigation through environment. LabView provides a solution to the limited skills and the limited time problem that appears when we use programming environments like C++ or Java. This document introduces the implementation of a communicative mobile robotic system that is based on two collaborative Pioneer robots controlled by user friendly interfaces developed in LabView. The purpose of developing this type of interfaces was to allow a complex collaborative system to adapt to any platform and be used by any type of user, without depending on his robotics knowledge level.

AR-Based Off-Line Programming of the RV-M1 Robot

This paper presents a prototype system for off-line programming of industrial robot RV-M1 using augmented reality technology. The system allows controlling a virtual model of the industrial robot co-located in the real environment, planning configurations, generating robot program and simulating the robot actions. The proposed architecture makes it possible to manipulate, pick or place the objects in the scene. The advantage of this system is use of inexpensive equipment for intuitive off-line programming of an industrial robot.

An Inteligent Tasks Planning System for Industrial Mobile Robots

In this paper we present a general structure of an automatic task planner for a multirobot system. Our focus in this paper is to develop an intelligent complex task planning system that uses both model and case - based approach, while trying to come up with actions that support end goals. We provide an overall description of the proposed system and its integration in an implemented architecture.