Task-Informed Grasping (TIG-III): mobile manipulation

A Full-day workshop at International Conference on Robotics and Automation
From 31 May to 4 June 2020
Palais des Congrès de Paris – FRANCE

Previous workshops from this series:

TIG-II at RSS 2019 ( https://lcas.lincoln.ac.uk/wp/tig-ii/ )

TIG-I at IROS 2018 (https://www.birmingham.ac.uk/iros18)

 

This workshop is supported by IEEE/RAS Technical Committees on: (1) Mobile Manipulation (2) Algorithms for Planning and Control of Robot Motion, (3) Agricultural Robotics & Automation, (4) Robotics research for practicality, and (5) Robot Learning.

If you require further information on support/endorsement for this workshop, please email: aghalamzanesfahani@lincoln.ac.uk

TIG-I and II workshop IROS 2018 and RSS 2019 can be found at

https://lcas.lincoln.ac.uk/wp/tig-ii/ and https://www.birmingham.ac.uk/iros18

Abstract

Recent advances in robotics research revealed significant improvements in grasping and manipulation.  Although these solutions are not yet fully robust, they are getting mature enough for solving many real-world problems. However, most of the state-of-the-art (SOTA) approaches assume the robot base is fixed and objects are located in the robot workspace. As such, these grasping approaches still need to be remarkably improved before robots can function similar to humans, i.e. to enable robots to move their base to a position suits efficient grasping and manipulation. For instance, a mobile manipulator needs to locate (fix) its base in a proper position allowing its manipulator to (1) pick fruits or (2) pick up some objects in a remote workspace, e.g., in an extreme environment. Cognitive science revealed that primates anticipate how the positioning of their body will affect their perception of the scene and future grasping actions. We identify 4 subtasks of grasping: (g0) suitably positioning of the manipulator base; (g1) reach-to-grasp; (g2) grasp synthesis/form stable contacts; and (g3) manipulative movements. SOTA approaches predominately studied g0, g1, g2 and g3 in isolation. This workshop aims to cover this gap by bringing experts in g0-g3 and discussing a joint analysis and solution to these grasping subtasks.

This workshop brings together researchers working in the area of robotic grasping/manipulation, planning, robot learning, and cognitive robotics; and it discusses the possible solution to the corresponding problems.

Topics of interest include (but not limited to):

  • mobile manipulation,
  • Agri-food manipulation,
  • Manipulation in hazardous/extreme environments,
  • Service robot manipulation,
  • Aerial manipulation,
  • Deep learning for task-informed grasping
  • Affordance informed grasping
  • Grasping and manipulative movements in cluttered environments
  • Task driven robotic perception
  • Active perception
  • joint planning of grasping pose and manipulative movements
  • Benchmarking and dataset for grasping and manipulation
  • Challenges of soft manipulation

 

Paper submission:

Deadline: 5 May 2020 (no extension)

Notification of acceptance: 16 May 2020

Camera ready: 24 May 2020

All papers must be original and not simultaneously submitted to another journal or conference. The following paper categories are welcome:

  • Extended abstract (maximum 2 pages) will be accepted for poster presentation at this workshop.
  • Full papers Contributed papers (maximum 6 pages) will be accepted based on their quality, originality, and relevance to the workshop. Submitted papers should not be under consideration for publication anywhere else. Submissions should follow the IEEE/RAS format.

Please submit your paper by emailing it to  workshop.tig@gmail.com

Programme

 Amir Ghalamzan  09:00 — 9:05  Welcome
Siddhartha Srinivasa  09:05 — 9:35 Understanding 3D environment for interactions
Mehmet Dogar  09:35 — 10:10

Improving object grasping and manipulation by exploiting uncertainty and human interaction

 10:10 — 10:45 Learning Compound Tasks through Interaction and Observation
 10:45 — 11:00   Coffee break
Matei Ciocarlie   11:00 — 11:35 DexNet, Perception and grasp synthesis, Deep learning for robust grasping of generic objects
  11:35 — 12:10 Analysis of grippers and grasps for cloth manipulation
  12:10 — 12:20 Robot Learning at Bosch Center for Artificial intelligence
   Lightning talks of posters   12:10 — 12:45 3 mins presentation —
—    12:45 — 13:45  Lunch
Posters   13:45 — 14:30 Interactive poster session and coffee break
  14:30 — 14:45 Coffee break
Nikolaos Tsagarakis    14:45 — 15:15 Human-inspired strategies for grasping with SoftHands
Carme Torras   15:15 — 15:45  Mobile Manipulation – new chances and challenges in industrial automation
Pieter Abbeel   15:45 — 16:15

Learning Models of Language, Action and Perception for Human-Robot Collaboration

Marco Hutter   16:15 — 16:45 A Critical Review of the State of Affairs in Grasping and Manipulation
    16:45 – 17:30 Panel discussion — Closing remark

 

Accepted papers:

  •  

Speakers:

Siddhartha Srinivasa 

Title

Abstract

Bio

Mehmet Dogar

Title

Abstract

Bio

Sven Behnke 

Title

Abstract

Bio

Matei Ciocarlie 

Title

Abstract

Bio

 
Fumiya Iida

Title

Abstract

Bio

Nikolaos Tsagarakis 

Title

Abstract

Bio

Carme Torras

 

Title

Abstract

Bio

 

 

Pieter Abbeel

 

 

Title

Abstract

Bio

Marco Hutter

Title

Abstract

Bio

Andras Kupcsik

Title

Abstract

Bio

   

Organisers

Dr Sariah Mghames  
Tomaso Pardi  
Dr Manolis Chiou  
S. Hamidreza Kasaei, Ph.D.
FSE Fellow
Faculty of Science and Engineering
The University of Groningen, The Netherlands
Amir Masoud Ghalamzan Esfahani, Ph.D. 
Senior Lecturer
College of Science
The University of Lincoln, The United Kingdom