The single overarching goal of the SF consortium is to identify the neuronal, cognitive and behavioural principles underlying optimal foraging in rodents and to implement these principles in a real-world foraging artefact or the Synthetic Forager (SF.01). SF.01 constitutes a novel biologically based cognitive technology for autonomous exploration and foraging in real-world man-made indoor and outdoor environments. SF exploits our growing understanding of exploration and foraging behaviour in rodents, advances current theories of the neuronal and behavioural organization of foraging and transfers this understanding towards the construction of novel realworld synthetic cognitive technologies.

The behaviour and neurophysiology of foraging will be studied in rodents behaving in automatically controlled multi-modal environments. The physical features of these environments can be fully controlled in real-time in relation to the behavioural and/or physiological state of the animal using an advanced experimental technology developed by the consortium. The overall integration of the perceptual, cognitive and behavioural control systems of SF will be accomplished using a well established robot based cognitive architecture, called Distributed Adaptive Control (DAC) further informed by the formal analysis of rodent foraging. The perceptual, cognitive and behavioural control systems of SF will be based on statistical analysis and detailed game theoretic models of the behavioural and neurophysiological data. The SF control systems are validated against the behavioural and physiological data. The SF phenotype comprises a high-mobility robotic platform equipped with visual, auditory, olfactory and tactile sensors. The SF will be evaluated in a number of stringent benchmarks ranging from robot equivalents of rodent foraging tasks to simulated de-mining.

Although the goal of the project is to demonstrate the SF technology for autonomous exploration and foraging, we expect that the approach and technologies developed in SF will have long-term implications to a number of other application areas including: cleaning robots, search and rescue systems, terrestrial and planetary exploration, delivery systems, autonomous transportation systems, military intelligence and battle field information control systems, environmental monitoring, internet information analysis and retrieval, information and communication networks and humanitarian de-mining.

The rehabilitation gaming system is a virtual reality (VR) based training device that provides new prospects for the rehabilitation of patients suffering from motor disabilities after stroke or brain injury. The developed RGS training tool supports restoring motor functions of the upper limbs that is essential in a patient's every day life. Therapeutic approaches towards relearning of motor activity rely on brain plasticity that is maintained throughout life. This adaptive mechanism is based on a reorganisation of affected brain regions and leads to a neurological recovery of damaged motor areas. Recent studies suggest that regaining of motor functions strongly depend on the starting point and frequency of training sessions after brain lesion hence making access to rehabilitation units fundamental requirements for successful motor function relearning.

The VR training environment enables patients to perform rehabilitation at home and thereby supports supplemental long-term training in addition to conventional therapies. The VR gaming scenarios implemented in the RGS system feature a first person perspective of the upper limbs where the motion of a patient’s arms is correlated to the movement of virtual limbs on the computer screen. The user is prompted to perform various motional tasks on different levels of difficulty dependent on the patients’ motor dysfunction. The movement of arms is monitored via a camera based tracking system together with performance of hand flexion and extension with an interactive hand training device. Biosignals are additionally recorded throughout the training session to monitor brain activity and physiological conditions of practicing patients. A feedback of performance parameters guarantees optimal training settings and also assists to keep the motivation of users at a high level. The RGS will be connected to a medical information web platform that allows for continuous monitoring of gaming sessions of patients and helps physicians or therapists to remotely supervise the individual training improvements. The impact of the RGS system on the improvement of motor functions will be evaluated in a clinical trial using also physiological parameters.

BrainAble will conceive, research, design, implement and validate an ICT-based human computer interface (HCI) composed of BNCI sensors combined with affective computing and virtual environments. This combination will dramatically improve the quality of life of people with disabilities by overcoming the two main shortcomings they suffer - exclusion from home and social activities - by providing inner functional independence for daily life activities and autonomy (HCI connected to accessible and interoperable home and urban automation) and outer social inclusion (HCI connected to advanced and adapted social networks services).

In terms of HCI, BrainAble will improve both direct and indirect interaction with computers. Direct control will be upgraded by creating tools that allow people to control those inner and outer environments using a “hybrid” Brain Computer Interface (BCI) system (BCIs, Electro Oculogram (EOG), Electromyography (EMG), and Heart Rate). Furthermore, BNCI information will be used for indirect interaction, such as by changing interface or overall system parameters based on measures of boredom, confusion, frustration, or information overload. These self-adaptive tools will increase effective bandwidth because users will be able to use a plurality of signals to effect control, and also because adaptation will reduce errors and help provide the user with the desired control.

BrainAble’s HCI will be complemented by an intelligent Virtual Reality-based user interface with avatars and scenarios that will help disabled people to move around on their wheelchairs, interact with all sort of devices, create self-expression assets using music, pictures and text, communicate online and offline with other people, play games to counteract cognitive decline, and get trained in new functionalities and tasks

Most promising interventions to restore walking function in stroke are based on robotic systems that intend to restore function by focusing on actions at periphery of the body (a BOTTOM-UP approach). By imposing gait-like movements at a more normal speed and without restricted duration, such robotic devices are thought to provide many of the afferent cues regarded as critical to retraining locomotion. BETTER is a European project that will develop a new approach for gait training in which such assistive technologies (ATs) might be improved if combined with non-invasive BNCI in order to increase the effectiveness in recovering function.

The principal goal of BETTER is to improve physical rehabilitation therapies of gait disorders in stroke patients based on BNCI assistive technologies, producing improved systems, providing guidelines for improving future systems, and developing benchmarking and evaluation tools. The project will validate, technically, functionally and clinically, the concept of improving stroke rehabilitation with wearable exoskeletons and robotic gait trainers based on a TOP-DOWN approach: The robot exerts physical stimulation -at the periphery- as a function of targeted neural activation patterns (related to user involvement). This intervention is expected to result in reorganizations in the cortex. Such Top-Down therapeutic treatment would aim to encourage plasticity of the affected brain structures to improve motor function.

	The system will provide means to assess compliance through a multimodal BNCI
	The proposed BNCI will combine CNS and PNS data with biomechanical data.
	It will determine if training the activation of signals that control lower limb tasks in combination with robotics devices is beneficial for restoring lower limb function.
	BETTER will provide means for objective evaluation of the BNCI-based physical rehabilitation therapy and its usability and acceptability.
	BETTER proposes a multimodal BNCI which main goal is to explore the representations in the cortex, characterize the user involvement and modify the intervention at the periphery with ambulatory and non-ambulatory robotic gait trainers.