Adaptive Vision for Human Robot Collaboration
9 dicembre 2019 alle 12:00
Sala Riunioni 4 Piano, via Celoria 18
Speaker: Dimitri Ognibene, University of Essex, UK
Persona di riferimento: Giuseppe Boccignone
The design principles of systems that adaptively find and selects relevant information are important for both Robotics and Cognitive Neuroscience. Unstructured social environments, e.g. building sites, release an overwhelming amount of information yet behaviorally relevant variables may be not directly accessible. Currently proposed solutions for specific tasks, e.g. autonomous cars, usually employ over redundant, expensive, and computationally demanding sensory systems that attempt to cover the wide set of sensing conditions which the system may have to deal with. Adaptive control of the sensors and of the perception process is a key solution found by nature to cope with such problems, as shown by the foveal anatomy of the eye and its high mobility and accuracy.
At the same time, collaborative robotics has recently progressed to human-robot interaction in real manufacturing. Measuring and modeling task specific gaze behaviours is mandatory to support smooth human robot interaction. Indeed, anticipatory control for human-in-the-loop architectures, which can enable robots to proactively collaborate with humans, heavily rely on observed gaze and actions patterns of their human partners.
The talk will describe several systems employing adaptive vision to support robot behavior and their collaboration with humans employing different strategies:
- model based systems using information theoretical measures to select perception parameters;
- neural and bio-inspired perception controllers trained to support task execution;
- imitation based attention control.
Dimitri Ognibene , PhD, has joined University of Essex as Lecturer in Computer Science and Artificial Intelligence in October 2017. He was Marie Curie Fellow at Universitat Pompeu Fabra, focusing on the development of algorithms for intelligent social agents with bounded computational and sensory resources. Before he has been developing algorithms for active vision in industrial robotic tasks as a Research Associate (RA) at Centre for Robotics Research, Kings College London; devising Bayesian methods and robotic models for attention in social and dynamic environments as a RA at the Personal Robotics Laboratory in Imperial College London. During his PhD he studied the interaction between active vision and autonomous learning in neuro-robotic models at the Institute of Cognitive Science and Technologies of the Italian Research Council (ISTC CNR). He also collaborated with Wellcome Trust Centre for Neuroimaging (UCL) to address the exploration issue in Predictive Coding, the currently dominant neurocomputational modelling paradigm. Dr Ognibene has also been Visiting Researcher at Bounded Resource Reasoning Laboratory in UMass and at University of Reykjavik (Iceland) exploring the symmetries between active sensor control and active computation or metareasoning. Dr Ognibene presented his work in several international conferences on artificial intelligence (IJCAI), adaptation (SAB), and development (ICDL) and published on international peer-reviewed journals. Dr Ognibene was invited to speak at the International Symposium for Attention in Cognitive Systems (2013 and 2014) as well as in other various neuroscience, robotics and machine-learning international venues. He organised several editions of the tutorial on Adaptive Vision for Human Robot Collaboration. Dr Ognibene is Associate Editor of Paladyn, Journal of Behavioral Robotics, Review Editor for Frontiers in Bionics and Biomimetics, as well as in Computational Intelligence. He has been part of the chair or program committee member of several international conferences and symposiums.