social linkedin box blue 32
social facebook box blue 32
social twitter box blue 32
social facebook box blue 32
iit-banner-logo
Persone ■ Vishwanathan Mohan
Vishwanathan Mohan's foto

Vishwanathan Mohan

Post Doc

RBCS / Cognitive Humanoids Lab


Address Robotics, Brain and Cognitive sciences dept, Via Morego 30
City Genova ZIP Code 16162
Mobile Phone 393495107766
IM Address vishuu (Skype)

Bio

  Vishwanathan Mohan was originally trained in the field Microelectronics and VLSI design at the Indian Institute of Technology Madras and began his scientific career playing with neuromorphic VLSI models of associative memories. While memory is the capacity of the nervous system to benefit from experience, to gain experience there is a need for physical interactions between the body and the world, coupled with mechanisms that abstract useful information in such interactions and organize them into our memories. This resulted in his parallel research training in the field of cognitive robotics at the Italian Institute of Technology, where he has been a learning/playing partner to the humanoid iCub since its inception, helping it to gradually expand its cognitive horizons and at the same time trying to understand the computational principles that endow us with similar capabilities. A distinctive feature of his research so far has further been the emphasis on both ‘green’ learning and ‘green’ computing: or efficiently recycling learnt ‘experiences’ of the past in novel tasks/contexts and efficiently recycling ‘energy’ while performing the underlying computations (and the associated field of reversible logic). Most of his present research is funded through the EU's Seventh Framework program (FP7) projects iTalk, DARWIN, EFAA and the Robotics, Brain and Cognitive sciences department of IIT. From a long term perspective, he is curious to understand the fundamental principles that underlie transformations between three major forms of causality in nature: the physical, the neural and the mental.

 

  Vishwanathan Mohan was originally trained in the field Microelectronics and VLSI design at the Indian Institute of Technology Madras and began his scientific career playing with neuromorphic VLSI models of associative memories. While memory is the capacity of the nervous system to benefit from experience, to gain experience there is a need for physical interactions between the body and the world, coupled with mechanisms that abstract useful information in such interactions and organize them into our ...

●•. Read More

Projects

 

 

Selected Publications

Selected Publications

Mohan V,  Morasso P, Sandini G,  Kasderidis S (2013) Inference through embodied simulation in cognitive robots. Cognitive Computation (in press).

Mohan V,  Morasso P, Sandini G (2013) . A neural framework for organization and flexible utilization fo episodic memory in cumulatively learnign baby humanoids. Neural Computation, MIT Press (in press). Preliminary draft.

Mohan V, Sandini G (2013). On the interplay between learning, memory, prospection and abstraction in cumulativley learning baby humanoids, Invited article for IJCNN 2013.

Mohan V and Morasso P (2011Passive motion paradigm: an alternative to optimal control. Frontiers in Neurorobotics. 5:4. doi: 10.3389/fnbot.2011.00004.

Mohan V and Morasso P (2012) How past experience, imitation and practice can be combined to swiftly learn to use new tools: Insights from skill learnign experiments with baby humanoids, Living Machines 2012, Lecture Notes in Artificial Intelligence, Springer Verlag.

 Mohan V, Morasso P, Zenzeri J, Metta G, Chakravarthy VS, Sandini G (2011) Teaching a humanoid robot to draw 'Shapes'. Autonomous Robots, 31(1), 21-53.

Mohan V, Morasso P (2011) Can Passive Motion be used for Active Inference? Revisiting the Chicken or Egg dilemma. Comment to the article “What is optimal about Motor Control?” by Karl Friston, Neuron,Vol.  72, Issue 3, 488-498, 3 November 2011.

 Mohan V,  Morasso P, Metta G,  Kasderidis S (2011) The distribution of rewards in growing sensory-motor maps acquired by cognitive robots through explorationNeurocomputing,  doi:10.1016/j.neucom.2011.06.009.

 Morasso P, Casadio M, Mohan V, Zenzeri J (2010)  A neural mechanism of synergy formation for whole body reaching. Biological Cybernetics 102:45-55.

 Mohan V,  Morasso P, Metta G,  Sandini G (2009) A biomimetic, force-field based computational model for motion planning and bimanual coordination in humanoid robots. Autonomous Robots, 27:291-307.

Mohan V, Morasso P (2007) Towards reasoning and coordinating action in the mental space. International Journal of Neural Systems, 17, 4,1-13.

PhD thesis (2009) Cognitive Robots: From affordance to action & back :  under the guidance of Prof Pietro Morasso, Prof Giorgio Metta and Prof Vittorio Sanguineti

 

 

 

Selected Publications

Mohan V,  Morasso P, Sandini G,  Kasderidis S (2013) Inference through embodied simulation in cognitive robots. Cognitive Computation (in press).

Mohan V,  Morasso P, Sandini G (2013) . A neural framework for organization and flexible utilization fo episodic memory in cumulatively learnign baby humanoids. Neural Computation, MIT Press (in press). Preliminary draft.

Mohan V, Sandini G (2013). On the interplay between learning, memory, prospection and abstraction in ...

●•. Read More