David Swords

Robotic Ubiquitous Cognitive Ecology for Smart Homes

Robotic ecologies are networks of heterogeneous robotic devices pervasively embedded in everyday environments, where they cooperate to perform complex tasks. While their potential makes them increasingly popular, one fundamental problem is how to make them both autonomous and adaptive, so as to reduce the amount of preparation, pre-programming and human supervision that they require in real world applications. The project RUBICON develops learning solutions which yield cheaper, adaptive and efficient coordination of robotic ecologies. The approach we pursue builds upon a unique combination of methods from cognitive robotics, machine learning, planning and agent-based control, and wireless sensor networks. This paper illustrates the innovations advanced by RUBICON in each of these fronts before describing how the resulting techniques have been integrated and applied to a proof of concept smart home scenario. The resulting system is able to provide useful services and pro-actively assist the users in their activities. RUBICON learns through an incremental and progressive approach driven by the feedback received from its own activities and from the user, while also self-organizing the manner in which it uses available sensors, actuators and other functional components in the process. This paper summarises some of the lessons learned by adopting such an approach and outlines promising directions for future work.

A Programming Framework for Multi-agent Coordination of Robotic Ecologies

Building smart environments with Robotic ecologies, comprising of distributed sensors, actuators and mobile robot devices facilitates and extends the nature and form of smart environments that can be developed, and reduces the complexity and cost of such solutions. While the potentials of such an approach makes robotic ecologies increasingly popular, many fundamental research questions remain open. One such question is how to make a robotic ecology self-adaptive, so as to adapt to changing conditions and evolving requirements, and consequently reduce the amount of preparation and pre-programming required for their deployment in real world applications. This paper presents a framework for the specification and the programming of robotic ecologies. The framework extends an existing agent system and integrates it with the pre-existing and dominant traditional robotic and middleware approach to the development of robotic ecologies. We illustrate how these technologies complement each other and offer a candidate technology to pursue adaptive robotic ecologies.

A study of effective social cues within ubiquitous robotics

Ubiquitous computing is the execution of computational tasks through everyday objects. Ubiquitous robotics augments the capabilities of one or more robots by leveraging ubiquitous computational and/or sensorial resources. Augmentation complements and/or enhances the capabilities of one or more robots while such robots can simultaneously serve as intermediaries or social interfaces to ubiquitous services. This paper posits the importance of conducting user studies to validate related HRI results within ubiquitous robotics. Specifically, the paper presents a pilot study designed to test the effectiveness of acknowledging human presence via non-verbal social cues and its impact on the users acceptance and engagement with a ubiquitous robotic system.

Ubiquitous human perception for real-time gender estimation

In environments where robotic systems are deployed people often have different requirements for the robotic services and human-robot interaction methods. This paper presents a robotic system that exploits the advantages of ubiquitous perception in order to gather knowledge from multiple sensors and various modalities. This ubiquitous human perception will facilitate user profiling in order to support personalised services and individual human-robot interaction. This system combines ubiquitous smart sensing, methods of multi-modal human perception and existing human recognition algorithms from the field of biometrics to collectively work towards a real-time, robust and scalable solution for gender estimation.

Electroencephalograms for Ubiquitous Robotic Systems

Abstract Ubiquitous robotics augments the capabilities of one or more robots by leveraging ubiquitous computational and/or sen- sorial resources. Augmentation complements and/or enhances the capabilities of one or more robots while such robots can simultaneously serve as intermediaries to ubiquitous services. Electroencephalograms (EEG) are Brain-Computer Interfaces that consist of a series of conductors placed on the scalp. These conductors measure voltage fluctuations in the brain, and using machine learning techniques can be classified and used to command ubiquitous robotic systems. The purpose of our work is to increase the collaboration between humans and surrounding robotic components while fulfilling a certain goal or requirement. We aim to do that by granting humans more precise manipulation, (i.e., brain- driven), over part or all of the involved robotic components. This paper presents our approach on the integration and benefits of an EEG interface within ubiquitous robotic systems.

BarterCell: An Agent-Based Bartering Service for Users of Pocket Computing Devices

The rising integration of pocket computing devices in our daily life duties has taken the attention of researchers from different scientific backgrounds. Todays amount of software applications bringing together advanced mobile services and literature of Artificial Intelligence AI is quite remarkable and worth investigating. In our research, software agents of BarterCell can operate in wireless networks on behalf of nomadic users, cooperate to resolve complex tasks and negotiate to reach mutually beneficial bartering agreements. In this paper, we introduce BarterCell that is an agent-based service application for users of pocket computing devices. We introduce new negotiation algorithms dedicated to bartering services in specific. We examine our approach in a scenario wherein it is essential for a multi-agent system to establish a chain of mutually attracted agents seeking to fulfill different bartering desires. And, we demonstrate and analyze the obtained results.

Oculus Rift Application for Training Drone Pilots

The research described in this paper, focuses on a virtual reality headset system that integrates the Oculus Rift VR headset with a low cost Unmanned Aerial Vehicle (UAV) to allow for drone teleoperation and telepresence using the Robot Operating System (ROS). We developed a system that allows the pilot to fly an AR Drone through natural head movements translated to a set of flight commands. The system is designed to be easy to use for the purposes of training drone pilots. The user simply has to move their head and these movements are translated to the quadrotor which then turns in that direction. Altitude control is implemented using a Wii Nunchuck joystick for altitude adjustment. The users use the Oculus Rift headset a 2D video stream from the AR Drone, which is then turned into a 3D image stream and presented to them on the headset.

Electroencephalogram training phase reduction for ubiquitous robotic brain symbiosis

Electroencephalograms are brain-computer interfaces that consist of a series of conductors placed on the scalp, using machine-learning techniques, the P300 signal can be classified and used to command ubiquitous robotic systems. For both able-bodied and disabled subjects, the collection of training data can be an exhaustive exercise. It is the goal of this work-in-progress to substitute an extended training phase with a more generalized approach involving electroencephalogram data from multiple subjects, in an attempt to eliminate classification redundancy.