Robotic Intelligence Lab
| Eyeshots | Grasp | Guardians | RAUVI | TRIDENT | MANIP | MANIFA | RETA |
EYESHOTS: Heterogeneous 3D Perception across Visual Fragments.
The goal of EYESHOTS is to investigate the interplay existing between vision and motion control, and to study how to exploit this interaction to achieve a knowledge of the surrounding environment that allows a robot to act properly. Robot perception can be flexibly integrated with its own actions and the understanding of planned actions of humans in a shared workspace. The research relies upon the assumption that a complete and operative cognition of visual space can be achieved only through active exploration of it: the natural effectors of this cognition are the eyes and the arms.
Crucial but yet unsolved addressed issues are object recognition, dynamic shifts of attention, 3D space perception including eye and arm movements including action selection in unstructured environments. The project proposes a flexible solution based on the concept of visual fragments, which avoids a central representation of the environment and rather uses specialized components that interact with each other and tune themselves on the task at hand.
In addition to a high standard in engineering solutions the development and application of novel learning rules enables the system to acquire the necessary information directly from the environment.Further information can be found in the official website.
GRASP: Emergence of Cognitive Grasping through Introspection, Emulation and Surprise.
GRASP is an Integrated Project funded by the European Commission through its Cognition Unit under the Information Society Technologies of the seventh Framework Programme (FP7). The project was launched on 1st of March 2008 and will run for a total of 48 months.
The aim of GRASP is the design of a cognitive system capable of performing grasping and manipulation tasks in open-ended environments, dealing with novelty, uncertainty and unforeseen situations. To meet the aim of the project, studying the problem of object manipulation and grasping will provide a theoretical and measurable basis for system design that is valid in both human and artificial systems. This is of utmost importance for the design of artificial cognitive systems that are to be deployed in real environments and interact with humans and other agents. Such systems need the ability to exploit the innate knowledge and self-understanding to gradually develop cognitive capabilities. To demonstrate the feasibility of our approach, we will instantiate, implement and evaluate our theories and hypotheses on robot systems with different embodiments and complexity.
GRASP goes beyond the classical perceive-act or act-perceive approach and implements a predict-act-perceive paradigm that originates from findings of human brain research and results of mental training in humans where the self-knowledge is retrieved through different emulation principles. The knowledge of grasping in humans can be used to provide the initial model of the grasping process that then has to be grounded through introspection to the specific embodiment. To achieve open-ended cognitive behaviour, we use surprise to steer the generation of grasping knowledge and modelling.
Further information can be found in the official website.
The GUARDIANS are a swarm of autonomous robots applied to navigate and search an urban ground. The project's central example is an industrial warehouse in smoke, as proposed by the Fire and Rescue Service. The job is time consuming and dangerous; toxics may be released and humans senses can be severely impaired. They get disoriented and may get lost. The robots warn of toxic chemicals, provide and maintain mobile communication links, infer localisation information and assist in searching. They enhance operational safety and speed and thus indirectly save lives.
The major aim of the project is to develop a swarm of autonomous robots that is able to adequately assist and safeguard a human squad leader. The project organises workshops with end-users (rescue workers and fire-fighters) and the advisory board, to assess the demonstrations and to disseminate research results. The workshops, moreover, aim at exploring additional exploitation of results.
Further information can be found in the official website.
RAUVI: Reconfigurable AUV for Intervention missions
The main goal of the RAUVI project is to develop and improve the necessary technologies for autonomously performing an intervention mission in underwater environments.
RAUVI project aims to design and develop an Underwater Autonomous Robot, able to perceive the environment by means of acoustic and optic sensors, and equipped with a robotic arm in order to autonomously perform simple intervention tasks.
Due to the complexity and multidisciplinary nature of the proposed goals, this project has been structured into three subprojects, including the I-AUV development, the robotic arm development, and the implementation of computer-based vision systems for vehicle and arm control.
Further information can be found here or in the official website.
TRIDENT proposes a new methodology for multipurpose underwater intervention tasks with diverse potential applications like underwater archaeology,oceanography and offshore industries, and goes beyond present-day methods typically based on manned and / or purpose-built systems. Trident is based on new forms of cooperation between an Autonomous Surface Craft and an Intervention Autonomous Underwater Vehicle.
Firstly, the I-AUV performs a path following survey, where it gathers optical and / or acoustic data from the seafloor, whilst the ASC provides geo-referenced navigation data and communications with the end user. The motion of the ASC will be coordinated with that of the I-AUV for precise Ultra Short Base Line positioning and reliable acoustic communications. After the survey, the I-AUV docks with the ASC and sends the data back to a ground station where a map is set up and a target object is identified by the end user. Secondly, the ASC navigates towards a waypoint near the intervention area to search for the object. When the target object has been found, the I-AUV switches to free floating navigation mode. The manipulation of the object takes place through a dextrous hand attached to a redundant robot arm and assisted with proper perception. Particular emphasis will be put on the research of the vehicle's intelligent control architecture to provide the embedded knowledge representation framework and the high level reasoning agents required to enable a high degree of autonomy and on-board decision making of the platform.
The new methodology will allow the user to specify an intervention task to be undertaken with regards to a particular target object, but after that the object is automatically recognised and manipulated by the robot in a completely autonomous way.
Further information can be found in the official website.
MANIP: Compliant Physical Interaction for Robot Manipulation Tasks
Robotic manipulation of everyday objects and execution of household chores are among the most challenging skills for future service robots. Most of current research in robot grasping is limited to pick-and-place tasks, without paying attention to the whole range of different tasks needed in home environments, such as opening doors, interacting with furniture, electrical appliances, etc. The few robots exhibiting such abilities do it in an ad-hoc fashion with very precise models of the environment, and typically planning a trajectory for the end-effector based on such models. They are carefully programmed for the specific task and objects used in the experiments resulting in a very brittle execution. However, nowadays, complex dexterous hands are available as well as precise sensor devices.
The overall goal is to develop and implement the architecture and methods for a robot to be able to perform a variety of tasks involving compliant physical interaction in everyday domestic environments by means of a multifinger hand and using vision, force and tactile sensing. The system should be designed in such a way that tasks are executed robustly without precise models, and new tasks can be easily dealt with. Ideas for neuroscience findings will serve as inspiration.
Further information can be found here.
La Universitat Jaume I está situada en un entorno donde una de las industrias más prominentes ha sido la ligada a la citricultura. Esta industria está sufriendo últimamente varios problemas que provocan que se vayan abandonando progresivamente las explotaciones agrarias. Para tratar de solucionar estos problemas se hace precisa una mecanización autónoma de los trabajos en el campo. Es en este ámbito donde juega un factor muy importante la robótica agrícola.
El presente proyecto pretende mejorar la navegación de equipos de robots en parcelas agrícolas. El proyecto se centra en el problema del mapeado autónomo de la parcela y el método de navegación distribuida por el cual más de un robot navegará por la parcela para cubrir todo el espacio de la misma con el fin de en un futuro poder realizar tareas de mantenimiento agrícola, como puede ser la eliminación de malas hierbas, la recolección, inspección de plagas, etc.
Para obtener más información, pincha aquí.
The main goal of the RETA Project is to study, develop and implement an Ambient Intelligence environment in the context of a specific room inside a house, in order to perform assistive tasks. The system will be composed of a set of distributed sensors (e.g. cameras, microphones), robots (e.g. humanoid robots, mobile manipulators) and other devices (e.g. touchscreens, domotic devices) of different types, all of them integrated in a networked intelligent environment in order to provide assistance in a individualized or synchronized manner. This distributed system, composed of robotic and domotic devices, will be internally connected through a custom network protocol known as SNRP (Siple Network Robot Protocol). This will allow that different robots can be easily connected to the system in a scalable and dynamic manner.
