Vishnu K. Narayanan

I am a post-doctoral researcher at ATR Intelligent Robotics and Communication Labs. in Kyoto, Japan.
I am currently working on end to end perception and navigation for networked service and social robots in operating human populated environments.

Until Dec. 2016, I was a Ph.D. student in Computer Science affiliated with INRIA Rennes - Bretagne Atlantique, while working with the Lagadic Team.
I was advised by Dr. Marie Babel and also worked in close collaboration with Dr. Anne Spalanzani who is with the Chroma team at INRIA Grenoble.
I also spent 3 months at the NTU-iCeiRA Laboratory at National Taiwan University during this period.

In 2013 I received a Master's degree in Mechanical Engineering from University of Florida, and in 2011 I received a Bachelors's degree in Mechanical Engineering from Amrita Vishwa Vidyapeetham in India.

Email : email
Research

I work in the broad field of Robotics, and I am specifically interested in developing algorithms that will allow a robot to naturally interact with/assist us human beings in order to accomplish complicated and tedious tasks. Therefore, my long term research goal, in general, is to develop sensing and control strategies that facilitates seamless and adaptive interaction between humans and robots, and apply the said strategies to current real world robots like intelligent vehicles, assistive robots and rehabilitation robots, that operate in human populated enviroments.

My present and short-term future work deals with:

  • Integrating communication constraints within autonomous indoor navigation: Robots, especially indoor mobile robots operating in large environments like shopping malls & airports, inadvertently communicate via wireless networks for enhanced perception and decision making capabilities. Owing to highly dynamic signal attenuation characteristics in such environments, connectivity issues may arise during robotic navigation, leading to disruption in information flow which can cause potential danger. Moreover, disturbances like pedestrian flows can also add a layer of temporal wireless signal variation complexities. Therefore the goal here is to design generative approaches for embedding radio signal strength constraints within indoor mobile robot navigation.
  • Functional Pedestrian-aware Navigation: By exploiting the utility of both modeled and learnt social navigation behaviours, the goal here is to lay the algorithmic foundations of a unifying strategy for pedestrian-aware navigation that is aimed at robots deployed in human-crowded environments.
  • Exploring the question of how to share control among human users and assistive robots: The objective here is to investigate shared control strategies, especially shared control strategies for personal mobility. With the recent advances in self-driving cars that are also envisoned to function as semi-autonomous machines, this has become an important research issue within the robotics community.

Interests: Robotics, Human-Robot Interaction/Collaboration, Applied Computer Vison and Machine Learning.

Selected Publications

Please click on the paper title to obtain the .pdf file.

Academic Journals

International Conferences

Thesis



Address
ATR Intelligent Robotics and Communication Laboratories
2-2-2 Hikaridai, Keihanna Science City
Kyoto 619-0288, Japan.
Tel : +81 774 95 2626
Fax : +81 774 95 1408