Description

PaMMO is a half-day workshop that will take place during ICPR 2020 in Milan, Italy. Due to the COVID-19 pandemic, the workshop will be fully virtual.

Object recognition, modelling, and pose estimation of objects for robot manipulation has achieved great advances in recent vision and robotics conferences (e.g., 6D pose challenges at vision conferences). However, vision still struggles with recognition under partial occlusions (e.g., in clutter or when an object is held by a human) and robots are still unable to handle everyday objects under realistic conditions in home, care, and service settings. Despite significant recent advances in data-driven grasping and manipulation, there are still considerable challenges to be addressed at the intersection of perception, robotics hardware, learning and grasp prediction. For example, learning to approach and grasp objects does not generalize beyond constrained objects and settings, object grasps are limited to specific robot embodiments,and perception does not generalize to cluttered scenes and objects touching or partially occludingeach other. Furthermore, evaluation and benchmarking (e.g., with the YCB object set and the YCB and Amazon challenges) is yet to become a standard for publishing advances in this domain.

PaMMO will focus on recent advances, open problems, and next steps to be taken in recognitionand modelling for the handover and manipulation of everyday objects. The Workshop includes invited talks by prominent researchers from different disciplines (e.g., vision and robotics for object manipulation), an open discussion, interactive videos and demos accompanied by posters.

Invited speakers

Perception for grasping:

• Predicting human grasp affordances in multi-object scenes (Francesc Moreno-Noguer, UPC Barcelona)

• On the fly object learning and modelling for grasping with the iCub robot (Lorenzo Natale, IIT)
  

Interactive perception:

• Interactive perception-action-learning for modelling objects (Ville Kyrki, Aalto University)

• 6D Object Pose Estimation on Point Clouds for Robotics (Mikko Lauri / Ge Gao, U Hamburg)
  

Reasoning:

• Object recognition (across domains) with 2D and 3D self-supervision (Tatiana Tommasi, U Torino)

• Self-supervised perceptual reasoning for manipulation (David Held, CMU)
  

Perception for manipulation:

• Perception and manipulation of textiles (Guillem Alenya, CIRC)

• Deep Dynamics Models for Dexterous Manipulation (Vikash Kumar, FAIR)

Program

14:00 Welcome and opening

14:10 Predicting human grasp affordances in multi-object scenes (Francesc Moreno-Noguer, UPC Barcelona)
14:30 On the fly object learning and modelling for grasping with the iCub robot (Lorenzo Natale, IIT)
14:50 Interactive perception-action-learning for modelling objects (Ville Kyrki, Aalto University)
15:10 6D Object Pose Estimation on Point Clouds for Robotics (Mikko Lauri / Ge Gao, U Hamburg)

15:30 Coffee break

16:00 Object recognition (across domains) with 2D and 3D self-supervision (Tatiana Tommasi, U Torino)
16:20 Self-supervised perceptual reasoning for manipulation (David Held, CMU)
16:40 Perception and manipulation of textiles (Guillem Alenya, CIRC)
17:00 Deep Dynamics Models for Dexterous Manipulation (Vikash Kumar, FAIR)

17:20 Group discussion session

17:50 Closing remarks

18:00 End of the workshop

Important dates

• June 05, 2020 Workshop paper submission deadline

• June 10, 2020 Notification to authors

• June 15, 2020 Camera ready deadline

Program committee

• Antonis Argyros (FORTH)

• Julia Borras Sol (CIRC)

• Mikko Lauri (U Hamburg)

• Mihai Andries (Inria)

• Tatiana Tommasi (U Torino)

• Serena Ivaldi (Inria)

• Timothy Patten (TU Wien)

• Ville Kyrki (Aalto University)

• Edgar Riba (UPC Bercelona)

• Michal Nazarczuk (Imperial College London)

• Yiannis Demiris (Imperial College London)

• Matej Hoffman (Czech Technical University, Prague)

• Karla Stepanova (Czech Technical University, Prague)

• Francesc Moreno-Noguer (UPC Bercelona)

Venue

Due to the COVID-19 pandemic, the workshop will be fully virtual.

MiCo Milan Congress Center

Piazzale Carlo Magno 1

Milan, Italy