INESC TEC  wants to explore research in deep-learning for field robotics applications following the trend in Europe Industry 4.0. For addressing these challenges, core competencies in deep-learning robotics applications need to be acquired and develop from a new scientific and technological perspective. Robotics research areas of interest such as: autonomous underwater intervention, underwater scene understanding, semantic mapping, multi-robot cooperation and aerial mapping, can benefit tremendously from deep-learning research by bringing a new approach and fresh perspective on how to solve some of the problems in this type of robotic applications.

Besides improving knowledge in their field, INESC TEC researchers and, specially, INESC TEC young researchers will need to acquire new knowledge in deep-learning field of expertise and work together with other researchers that have broader and deeper scientific knowledge and understand better the requirements of the stakeholders. This will be of utmost importance to raise the levels of knowledge of all INESC TEC researchers and generate new ideas with higher scientific and economic impact, as well as to successfully address the challenges of applied research and work at different Technology Readiness Levels.

The implementation of the DEEPFIELD concept will be done by means of two complementary set of coordination and support activities with the aim of contributing to the two ultimate goals of this twinning action: 1) raise the scientific knowledge of INESC TEC researchers in key areas of deep-learning in field robotics; 2) improve the INESC TEC researcher profile in deep-learning applied to field applications.

Coordination activities

Coordination activities will materialize what has been described in the five major actions from the DEEPFIELD concept, such as:

  • Joint organisation of conferences and workshops
  • Organisation of “hands-on” laboratory/field sessions
  • Scientific/Networking meetings
  • Joint participation of researchers in selected international scientific events
  • Identify and select the most relevant scientific events for joint participation.
  • Joint organisation of and participation in exploitation events: 1)brokerage events with the stakeholders; 2) participation in international trade fairs; 3) organisation of meetings with international buyers; 4) organisation of meetings with regional and national authorities.
  • Joint outreach activities: 1) participation in conference and seminars targeting non scientific audiences; 2) dissemination in the media, namely the preparation of press releases and press conferences, participation in TV programs addressed to science issues.

Support Activities

Supporting activities will be side activities that will support and enhance the major pillars of the project.

  • Creation of a sustainable collaboration network involving several EU research institutions with expertise in deep learning area.
  • Invitation of one permanent visiting expert (senior research, professor), for networking meetings.
  • Creation of an Counseling Board for the young researcher career development including two expert from each top institution to form the Counseling Board that will work in close cooperation with the coordinators of the INESC TEC's research centres involved.
  • Invitation of the members of the Counseling Board for short-term visits to participate in the coordination of the INESC TEC's research centres in loco.

Five main actions support this overall concept:

Broad and focused training

A training strategy based on sessions touching deep-learning robotics aspects followed by sessions focused on specific fields of expertise, allowing researchers to improve their knowledge in a specific field of expertise while taking into account the context and interrelations with other fields of expertise and preparing them for the research and implementation challenges in the field with harsh environment. From this pillar, 4 thematic workshops will be promoted.

Work Abroad

Short period of time (2-3 months) where researchers are invited to stay in the partnering institution and work with them in order to learn, by experience, the acquired theoretically in the thematic workshop. From this pillar, 4 short-term scientific missions (STSM) will be promoted. This activity will be mentored by an assigned tutor selected by the counseling board.

Hands-on Missions

A training strategy targeting hands-on training will be pursued, enabling direct application of the knowledge acquired in theoretical sessions and in the short-term scientific missions and improve their understanding of the actual requirements of the stakeholders, allowing them to design solutions with higher economic potential. From this pillar, 4 hands-on summer/winter schools will be promoted.

Multidisciplinary Collaboration Network

A new collaboration network involving top EU research institutions in the deep-learning area, including the key fields of expertise required to address the challenges identified above, articulated with existing networks in specific fields of expertise, such as EIT, euRobotics, ETP NetWorld2020 and Raw Materials. From this pillar, networking meetings will be promoted.

Cross-fertilization among deep-learning in robotics fields of expertise

Interchange and interaction among different fields of expertise is fundamental to address the deep-learning robotics challenges (such as, grasping, semantic mapping, multi-robot cooperation, etc.), due to the multidisciplinary nature of the application area. The interchange and interaction between researchers from different institutions and different fields of expertise will therefore be targeted. From this pillar, conferences and scientific events will be attended and promoted.