Organized by Matteo Bianchi - UNIPI and IIT

speakers from the SOMA Consortium

M. Bianchi (University of Pisa and Istituto Italiano di Tecnologia): An open-access repository to share data and tools for the study of human and robotic hands: the HandCorpus initiative

H. Marino/M. Gabiccini (University of Pisa). Datasets (and tools) from disconnected markers to organized behaviors: a path towards autonomous manipulation    



The half-day workshop will focus on promoting open-access grasping and manipulation related datasets and identifying the critical needs on new datasets and a methodology on utilizing the data. The scopes of the datasets in this workshop would include human motion datasets, instrumental activities of daily living (IADL) datasets, other activity datasets, object geometry and motion datasets, haptics interaction datasets, as well as any other datasets on human and robot grasping and manipulation. The datasets are not only crucial for evaluating and comparing the performances of novel methods, but also extremely valuable for offline robotic learning and training. Recently, there is a worldwide trend on providing and using high-quality open-access grasping and manipulation datasets. Many different datasets were recently collected by a number of groups and shared for different research purposes. The workshop will bring together researchers from different domains for their common interests in grasping and manipulation related datasets. The objective of the workshop is to address the need to promote the use of open-access datasets, coordinating the efforts and resources and avoid pitfalls in collecting high-quality datasets, clearing up confusion in selecting suitable datasets, and identifying new demands in datasets.

The workshop will be comprised of two oral sessions and one addition session of summary and panel discussion to encourage Half of the presentations in the oral sessions are invited and the other half are openly solicited and reviewed to attract broader participations and facilitate vibrant discussions. The presentations will be concise and limited to 10 to15 minutes and the speakers will be encouraged to include interactive demos.

In the summary and panel session, an overview of the datasets that are not covered by the speakers will be presented by one of the organizers and then a panel discussion will be organized to discuss open questions that will be raised during the talks and more broader questions such as "What is missing in the existing datasets?" and "Can we merge the existing datasets and how?"