Picture of Mohsen Kaboli

M.Sc. Mohsen Kaboli

Technical University of Munich

Chair of Cognitive Systems (Prof. Cheng)

Postal address

Karlstraße 45/II
80333 München

Research Interests

We learn much of our tactile perception by interacting with the environment. Observing tactual exploration of human, we carefully interact with the objects in the world, repeatedly trying to pick up an object, learning to perceive the world through our skin. Most of the research in tactile sensing has focused on building and characterizing tactile sensors. Very little work has been done on robot learning from tactile sensors. Such issues are important for robots to be able to learn autonomously and to interact safe with the environment i.e. without causing any harm to it or to the objects with which it is interacting.

My research focus is robot learning from multimodal sensory artificial skin or tactile sensors. In this context, I am using feedback information from electronic skin provided on robot body parts, to learn a robot to acquire human-like skills for fast environment exploration and safe interaction with human through learning algorithms.

Potential research directions and applications emerging from this area are:

  • Research on robot learning for whole body naturally motion by exploiting feed back from electronic skin suit of robots.
  • To learn robots, from multimodal sensory skin to handle and manipulate unknown objects with close contact in humans without hurting.

Currently, I am exploiting a robotic manipulator with a multimodal electronic skin covered end-effector for tacitly surface exploration and fast and smooth reaction in unknown cluttered space.



  • Kunpeng Yao, Mohsen Kaboli, and Gordon Cheng: Tactile-based Object Center of Mass Exploration and Discrimination. IEEE International Conference on Humanoid Robots (Humanoids), 2017 more… BibTeX Full text (mediaTUM)
  • Mohsen Kaboli, Di Feng, Gordon Cheng: Active Tactile Transfer Learning for Object Discrimination in an Unstructured Environment using Multimodal Robotic Skin. International Journal of Humanoid Robotics (IJHR), 2017 more… BibTeX Full text (mediaTUM)
  • Mohsen Kaboli, Di Feng, Kunpeng Yao, Pablo Lanillos, Gordon Cheng: A Tactile-based Framework for Active Object Learning and Discrimination using Multi-modal Robotic Skin. IEEE Robotics and Automation Letters 2 (4), 2017, 2143-2150 more… BibTeX Full text (mediaTUM)


  • Mohsen Kaboli, Kunpeng Yao, and Gordon Cheng: Tactile-based Manipulation of Deformable Objects with Dynamic Center of Mass. IEEE-RAS International Conference on Humanoid Robots 2016, 2016 more… BibTeX Full text (mediaTUM)
  • Mohsen Kaboli, Rich Walker, and Gordon Cheng: Re-using Prior Tactile Experience by Robotic Hands to Discriminate In-Hand Objects via Texture Properties. IEEE International Conference on Robotics and Automation (ICRA 2016), 2016 more… BibTeX Full text (mediaTUM)


  • Mohsen Kaboli and Gordon Cheng: Dexterous Hands Learn To Re-Use The Past Experience To Discriminate In-Hand Objects From The Surface Texture. 33rd Annual Conference of the Robotics Society of Japan (RSJ 2015), 2015 more… BibTeX Full text (mediaTUM)
  • Mohsen Kaboli, Alex Long, Gordon Cheng: Humanoids Learn Touch Modalities Identification via Multi-Modal Robotic Skin and Robust Tactile Descriptors. Advanced Robotics , 2015 more… BibTeX Full text (mediaTUM)
  • Mohsen Kaboli, Armando De La Rosa T, Rich Walker, and Gordon Cheng: In-Hand Object Recognition via Texture Properties with Robotic Hands, Artificial Skin, and Novel Tactile Descriptors. IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids), 2015 more… BibTeX Full text (mediaTUM)
  • Nivasan Yogeswaran, Wenting Dang, William Navaraj, Dhayalan Shakthivel, Saleem Khan, Emre Polat, Shoubhik Gupta, Hadi Heidari, Mohsen Kaboli, Leandro Lorenzelli, Gordon Cheng, Ravinder Dahiya: New Materials and Advances in Making Electronic Skin for Interactive Robots. Advanced Robotics , 2015 more… BibTeX Full text (mediaTUM)


  • Mohsen Kaboli, Philipp Mittendorfer, Vincent Hugel and Gordon Cheng: Humanoids Learn Object Properties From Robust Tactile Feature Descriptors vai Multi-Modal Artificial Skin. IEEE-RAS International Conference on Humanoid Robots, 2014 more… BibTeX Full text (mediaTUM)