[Seminar] "Body perception under the free energy formulation for robots and humans" by Dr. Pablo Lanillos
Dr. Pablo Lanillos, Technical University of Munich
"Body perception under the free energy formulation for robots and humans"
How humans learn, adapt and perceive their body as a unity during interaction with the environment? Can these mechanisms be applied to robots?
Under the umbrella of SELFCEPTION project (www.selfception.eu) we are developing computational models for robotic self/other distinction in order to improve interaction under uncertainty in complex scenarios. This interdisciplinary project, which combines cognitive psychology and robotics, seeks (i) enabling robots to learn to recognize their own body while differentiating it from the rest of the environment; and (ii) investigating the mechanisms of the minimal self in humans using synthetic models.
In this talk, I mathematically introduce body perception as a dynamic approximation inference problem where the latent variables are the body state and the observed variables are the sensor values. Inspired by predictive coding approaches developed by Friston and Tani, the proposed model uses the error prediction (sensed vs expected) to reduce the discrepancy between the belief distribution of the reality and the perceived one. This model was successfully applied to robot body estimation and to replicate the first rubber-hand illusion on a multisensory (visual, tactile, proprioception) humanoid robot. We showed similar drifting patterns when comparing the end-effector estimation displacements with the proprioceptive drift observed in human participants. Finally, I discuss the drawbacks of the proposed method to completely model the sensorimotor self and what is the most prominent research direction according to our latest results.
Pablo Lanillos is a Marie Skłodowska-Curie Postdoc leading the MSCA EU H2020 funded project SELFCEPTION (www.selfception.eu) at the Institute of Cognitive Systems (ICS) of the Technical University of Munich (Germany), directed by Prof. Gordon Cheng, He has a M.Sc. degree in computer sciences and a Ph.D. degree in robotics form Complutense University of Madrid. Prior to joining TUM he has been working in artificial attention and probabilistic decision making in renowned universities, such as the Institute for Systems and Robotics (Portugal), the MIT (USA) or the EPFL (Switzerland). Now his research interests are: embodied artificial intelligence, sensorimotor self, self/other distinction, multisensory models of attention, bio-inspired computational modelling and decision making.
Personal website: www.therobotdecision.com