Tauseef Gulrez

Brain-computer interface: Next generation thought controlled distributed video game development platform

In this paper we present a system that uses the human ability to control a video game on a mobile device using electroencephalographic (EEG) Mu rhythms. The signals were obtained using a specially designed electrode cap and equipment, and sent through a Bluetooth connection to a PC that processes it in real time. The signal was then mapped onto two control signals and sent through wireless connection to a mobile gaming device BreakOut. We have also investigated the humans ability to play the video game by manipulating neuronal motor cortex activity in the presence of a visual feedback environment. The participants played the video game by using their thoughts only with up to 80% accuracy over controlling the target.

Opportunistic information fusion: a new paradigm for next generation networked sensing systems

Traditionally, information fusion systems assume that the information is gathered from known sensors over proprietary communication networks and fuse using fixed rules of information fusion and designated computing and communication resources. Emerging technologies like wireless sensor networks, TEDS enabled legacy sensors, ubiquitous computing devices and all IP next generation networks are challenging the rationale of conventional information fusion systems. The technology has matured to a point where it is reasonable to discover sensors based on the context, establish relevance, query for appropriate data, and fuse it using the most appropriate fusion rule, using ubiquitous computing and communication environment in an opportunistic manner. We define such fusion systems as opportunistic information fusion systems. In this paper we introduce this new paradigm for information fusion and identify plausible approaches and challenges to design, develop and deploy the proposed next generation opportunistic information fusion systems.

Probabilistic road maps with obstacle avoidance in cluttered dynamic environment

The paper presents an experimental study of a probabilistic road map (PRM) based obstacle avoiding algorithm, for motion planning of a non-holonomic mobile robot in a cluttered dynamic environment. The PRM approach uses a fast and simple local planner to build a network representation of the configuration space. It trades off the distance to both static objects and moving obstacles in computing the travelled path. Our work has been implemented and tested on Player/Stage, a real time robotic software, in extensive simulation runs. The different experiments demonstrate that our approach is well suited to control the motions of a robot in a cluttered environment and demonstrates its advantages over other techniques.

A Sensorized Garment Controlled Virtual Robotic Wheelchair

This paper presents the design and performance of a body-machine-interface (BoMI) system, where a user controls a robotic 3D virtual wheelchair with the signals derived from his/her shoulder and elbow movements. BoMI promotes the perspective that system users should no longer be operators of the engineering design but should be an embedded part of the functional design. This BoMI system has real-time controllability of robotic devices based on user-specific dynamic body response signatures in high-density 52-channel sensor shirt. The BoMI system not only gives access to the user’s body signals, but also translates these signals from user’s body to the virtual reality device-control space. We have explored the efficiency of this BoMI system in a semi-cylinderic 3D virtual reality system. Experimental studies are conducted to demonstrate, how this transformation of human body signals of multiple degrees of freedom, controls a robotic wheelchair navigation task in a 3D virtual reality environment. We have also presented how machine learning can enhance the interface to adapt towards the degree of freedoms of human body by correcting the errors performed by the user.

Precision Position Tracking in Virtual Reality Environments using Sensor Networks

In an immersive interactive virtual reality (VR) environment a real human can be incorporated into a virtual 3D scene to navigate a robotic device within that virtual scene. This has useful applications in rehabilitation. The non-destructive nature of VR makes it an ideal testbed for many applications and a prime candidate for use in rehabilitation robotics simulation. The key challenge is to accurately localise the movement of the object in reality and map its corresponding position in 3D VR. To solve the localisation problem we have formed an online mode vision sensor network, which tracks the objects real Euclidean position and sends the information back to the VR scene. A precision position tracking (PPT) system has been installed to track the object. We have previously presented the solution to the sensor relevance establishment problem where from a group of sensors the most relevant sensing action is obtained. In this paper we apply the same technique to the VR system. The problem can be broken down in two steps. In step one, the relevant sensor type is discovered based upon the IEEE 1451.4 Transducers Electronic Data Sheets (TEDS) description model. TEDS is used to discover the sensor types, their geographical locations, and additional information such as uncertainty measurement functions and information fusion rules necessary to fuse multi-sensor data. In step two, the most useful sensor information is obtained using the Kullback-Leibler Divergence (KLD) method. In this study we conduct two experiments that address the localisation problem. In the first experiment a VR 3D environment is created using the realtime distributed robotics software Player/Stage/Gazebo and a simulated PPT camera system is used to localise a simulated autonomous mobile robot within the 3D environment. In the second experiment, a real user is placed in a cave-like VR 3D environment and a real PPT camera system is used to localise the users physical actions in reality. The physical actions of the real user are then used to control the robotic device in VR.

Relevant opportunistic information extraction and scheduling in heterogeneous sensor networks

Determining the output of the most relevant sensor is of crucial importance when heterogeneous sensors are available for measuring a given process in an environment. In this paper, we describe an IEEE 1451 TEDS (transducer electronic data sheets) compliant sensor model for heterogeneous sensor networks. The proposed model uses the relevance feedback method to understand the context of a sensor learning application. We present results of a real time implementation of heterogeneous sensor networks using distributed multi-sensing 3D real-time robotics software player/gazebo on an autonomous mobile robots navigation problem. The results show that the proposed model can be utilised in the real-time scenario and can help reduce the computational cost of a system

Sensorized Garment Augmented 3D Pervasive Virtual Reality System

Virtual reality (VR) technology has matured to a point where humans can navigate in virtual scenes; however, providing them with a comfortable fully immersive role in VR remains a challenge. Currently available sensing solutions do not provide ease of deployment, particularly in the seated position due to sensor placement restrictions over the body, and optic-sensing requires a restricted indoor environment to track body movements. Here we present a 52-sensor laden garment interfaced with VR, which offers both portability and unencumbered user movement in a VR environment. This chapter addresses the systems engineering aspects of our pervasive computing solution of the interactive sensorized 3D VR and presents the initial results and future research directions. Participants navigated in a virtual art gallery using natural body movements that were detected by their wearable sensor shirt and then mapped the signals to electrical control signals responsible for VR scene navigation. The initial results are positive, and offer many opportunities for use in computationally intelligentman-machine multimedia control.

Advances in Robotics and Virtual Reality

A beyond human knowledge and reach, robotics is strongly involved in tackling challenges of new emerging multidisciplinary fields. Together with humans, robots are busy exploring and working on the new generation of ideas and problems whose solution is otherwise impossible to find. The future is near when robots will sense, smell and touch people and their lives. Behind this practical aspect of human-robotics, there is a half a century spanned robotics research, which transformed robotics into a modern science. The Advances in Robotics and Virtual Reality is a compilation of emerging application areas of robotics. The book covers robotics role in medicine, space exploration and also explains the role of virtual reality as a non-destructive test bed which constitutes a premise of further advances towards new challenges in robotics. This book, edited by two famous scientists with the support of an outstanding team of fifteen authors, is a well suited reference for robotics researchers and scholars from related disciplines such as computer graphics, virtual simulation, surgery, biomechanics and neuroscience.

Sensor Relevance Establishment Problem in SharedInformation Gathering Sensor Networks

In a city area network hundreds of video cameras, infrared and laser sensors are deployed for online monitoring of physical phenomenon over a geographical area. This is a popular application of sensor networks. Next generation intelligent sensing systems and networks are divided into two categories, an always-on mode -where every sensor information is piped to a base station (for resolution of a problem), and a snapshot mode -where a user queries the network for an instantaneous summary of the observed environment. Snapshot mode sensor networks are highly dependent on relevant sensing due to the accuracy required in a short time and the sensitive nature of the problem (query). This paper summarises the sensor relevance establishment problem in data acquisition. We describe its use in a framework that models the observed environment at each sensor node as a function of time, and uses an adaptive learning method to sample data with the corresponding relevance metric. We take the sensor network towards the problem by considering the relevance metric at given time step. The sensor relevance establishment problem has been split into two steps. In step one, the relevant sensor type is discovered based upon the IEEE 1451.4 Transducers Electronic Data Sheets (TEDS). TEDS description model can be used to discover the sensor type and their geographical locations and other important information such as uncertainty measurement functions and information fusion rules necessary to fuse multi-sensor data. In step two, the most useful sensor selection is determined using the relevant information data metric. This step is modelled using the Kullback-Leibler Divergence (KLD) method to measure the information relevance distance between the TEDS modelled relevant sensors determined in step one. As proof of our concept we have simulated the 3D environment using a real-time distributed robotics software Player/Stage/Gazebo. The preliminary results have been demonstrated on a simple autonomous robot navigation problem.

Bézier curve based dynamic obstacle avoidance and trajectory learning for autonomous mobile robots

This paper addresses the problem of avoiding dynamic obstacles while following the learned trajectory through non-point based maps directly through laser data. The geometric representation of free configuration area changes while a moving obstacle enters into the safety region of autonomous mobile robot. We have applied the Be´zier curve properties to the free configuration eigenspaces to satisfy the dynamic obstacle avoidance path constraints. The algorithm is designed to accurately represent the mobile robots characteristics while avoiding obstacle such as minimum turning radius. Moreover, we also discuss the obstacle avoided path feasibility as a vectorial combination of free configuration eigen-vectors at discrete time scan-frames to manifest a trajectory, which once followed and mapped onto the two control signals of mobile robot will enable it to build an efficient and accurate online environment map. Preliminary results in Matlab have been shown to validate the idea, while the same has been implemented in Player/stage (robotics real-time software) to analyze the performance of the proposed system.