Objectives

Haptics, or the sense of touch, enables humans to interact with their environment and is crucial to manipulation challenges in everyday life. It enables grasping, manipulation, learning, and decision-making based on the information from mechanoreceptors distributed in muscles and over the skin. Humans use haptic exploration to interact with their environment, e.g. to recognise an object's shape and mechanical properties.

Haptic sensing is a capability that robotic systems need to acquire for safely and efficiently interacting with their environment and with humans. Haptic sensing is essential to perform a variety of tasks in industrial applications, consumer services, and other highly dynamic environments such as assistance and care for elderly, housekeeping, etc. However, it is still challenging for robots to carry out haptic exploration smoothly and recognise objects efficiently, especially in an unstructured environment with soft materials and different textures, inherent sensor and motor noise, and delay in sensory signal processing. Using a predictive coding framework to carry out haptic exploration could enhance robot's capability in making it robust and versatile, by learning to prepare an action based on the expectation of sensory information to encounter during interaction with the environment. This means that the human/robot will be able to use sensory information in real time and check whether the expectations are verified and react quickly.

Thus, this year’s workshop theme is on visuo-tactile predictive coding and active inference for grasp and manipulation. Similar to the sense of touch in humans, robot sensation and the resulting capabilities should not end at the fingertip. Rather, robot sensation can be viewed as a complex process which is based on the interplay of a variety of components. This workshop will focus on approaches to develop such abilities in robots. It will bring together well-established speakers and young talents across all technical disciplines involved in developing tactile sensing. It will provide a platform for researchers working in diverse fields of robotics such as material and technology development, perception, haptics and also high level tasks such as manipulation and control strategies and learning, to get an insight into the vast expanse of work done in the respective fields. The idea is to connect excellent researchers from different domains to foster fresh ideas through interdisciplinary discussions while paving the way for future collaborations.

Topics of interest (but not limited to)

       Human Sense of Touch  

• Touch physiology from skin to brain
• Haptic Perception 
• Action and Perception Loop
• Perception for Learning

   Tactile Sensing Technologies

• Conformable and compliant materials
• Features enabled by conformable sensors
• Biomimetics
• Sensor effects
• Integration and read-out strategies
• Self-healing properties and strategies
• Sensor skins: design, fabrication and integration strategies
• Integration strategies for sensors in robotics
• Enabling technologies for fully integrated robotic systems

       Visuo-Tactile Predictive Coding and Active Inference

• Exploitation of contact constraints
• Novel contact models
• Object perception for the exploitation of contact
• Tactile information processing
• Tactile feature extraction / feature learning 
• Tactile-based object modelling 
• Tactile object localization
• Tactile shape reconstruction and recognition
• Tactile object classification
• Tactile exploration
• Trends in combining of vision and touch sensing
• Roles of vision and touch sensing in different object perception tasks
• Modelling and representation of sensing modalities
• Integration of visuo-tactile sensing modalities

          Visuo-Tactile Grasp, Prehensile and non- prehensile Manipulation

• Linear/rotational slip detection 
• Grasping planning
• Grasp stability assessment
• Soft manipulation
• In-hand/whole body manipulation
• Tactile planning interplay between touch sensing and vision
• Tactile knowledge/skill transfer  
• Tactile transfer learning
• The meaning and function of different sensing modalities in object manipulation
• Sensing and planning in object manipulation
• Multi-robot manipulation and coordination
• Control strategy for object manipulation and collaborative assembly
• Learning object manipulation skills from human demonstration
• Novel approaches to grasp and manipulation planning
• Whole-body, multi-contact planning and control
• Design and characterization of contact-exploiting, compliant hands

Invited Speakers   

All speakers have confirmed their participation. The confirmations are attached beow.

Tactile Sensing Technologies

• Prof. Takao Someya  Department of Electrical and Electronic Engineering, School of Engineering, the University of Tokyo, Japan

Human Sense of Touch

• Prof. Vincent Hayward  Professor, Sorbonne Université / Actronika SAS, France
• Prof. Etienne Burdet Chair in Human Robotics, Interface labs, Imperial College London, UK

Predictive visuo–tactile coding and active inference

• Prof. Thrishantha Nanayakkara Faculty of Engineering, Dyson School of Design Engineering, Imperial College London, UK
• Prof. Jun Tani Cognitive Neurorobotics Research Unit, Okinawa Institute of Science and Technology Graduate University (OIST), Japan
• Prof. Henrik Jörntell Professor Neural Basis of Sensorimotor Control, Lund University, Sweden

Visuo-tactile grasp, prehensile and nonprehensile manipulation

Organizers

• Mohsen Kaboli, Assistant Professor and Head of RoboTac Lab BMW Group and Donders Institute for Brain and Cognition, Radboud University , the Netherlands  Email: mohsen.kaboli@bmwgroup.com, Web: Dr M. Kaboli (Mohsen) - Radboud University
• Etienne Burdet, Professor. Chair of Human Robotics, Interface labs, Imperial College London, UK E-mail: eburdet@ic.ac.uk, We https://www.imperial.ac.uk/human-robotics
• Vincent Hayward, Professor, Sorbonne Université / Actronika SAS, France, E-mail: hayward@isir.upmc.fr  Web https://en.wikipedia.org/wiki/Vincent_Hayward
• Henrik Jörntell, Professor Neural Basis of Sensorimotor Control,  Department of Experimental Medical Science, Lund University, Sweden, E-mail: henrik.jorntell@med.lu.se Web https://portal.research.lu.se/en/persons/henrik-jörntell
•  Anirvan Dutta, PhD Candidate, BMW Group BMW Group and Imperial College London,mail:Anirvan.Dutta@bmwgroup.com Web: https://www.anirvandutta.com/