SOcial Cognitive Robotics in The European Society

Project Information

SOCRATES

Grant agreement ID: 721619

DOI

10.3030/721619

Project closed

EC signature date 12 August 2016

Start date 1 November 2016

End date 31 October 2020

Funded under

• EXCELLENT SCIENCE - Marie Skłodowska-Curie Actions

Total cost

€ 3 874 726,44

EU contribution

€ 3 874 726,44

Coordinated by

UMEA UNIVERSITET
Sweden

Periodic Reporting for period 2 - SOCRATES (SOcial Cognitive Robotics in The European Society)

Reporting period: 2018-11-01 to 2020-10-31

Summary of the context and overall objectives of the project

The SOCRATES project was a European PhD training network for young scientists active in the area of interactive social robotics aiming at eldercare. The unique multidisciplinary project trained researchers with both academic and entrepreneurial spirit and expertise, well suited for a career in both academy and industry.

Eldercare is a major societal challenge for Europe. By 2050 the number of older adults in many countries will exceed 30%. To reduce the social and economic impact, technological solutions are needed and robot technology is expected to play an important role. To achieve acceptable solutions, with natural, ethical, safe, and efficient human-robot interaction, a major push in Social Robotics is necessary.

Social Robotics is an important trend within human-robot interaction (HRI); the goal is to equip robots with cognitive abilities so they can interact with humans by adhering to certain social cues and rules. This requires well-functioning interaction at several levels: exchange of low-level physical information but also exchange of higher-level concepts such as actions, intentions, beliefs, emotions, and attention. The interaction must adapt to changing tasks, environments, and humans, and must be socially acceptable and safe. Social interaction with older adults is even more complex since it must accommodate different levels of physical and cognitive abilities affecting perception, coordination, concentration, focus, and memory. Interaction is still a limiting factor for older adults to accept assistive robots.

To meet these challenges, SOCRATES addressed research in social robotics and focused on Interaction Quality - a term introduced as a way to describe how fit a specific mode of interaction is for a given task, situation, and human. This is a novel research perspective in Social robotics. The research objective was to improve the robots’ ability to interact with older adults in a natural, ethical, safe, and efficient way.
A holistic approach to design and development of socially interacting robots is essential to achieve successful acceptance and adoption of the robotic systems by older adults. Social and psychological aspects must be considered by systematically involving end-users. Successful research training in social robotics must be a multidisciplinary process that integrates technical knowledge of hardware and software, psychological knowledge of interaction dynamics, social knowledge of the users and domain-specific knowledge of the target application. For successful penetration into society, business aspects must also be considered.

The aim of the SOCRATES program was to implement a successful multidisciplinary and intersectoral PhD training program, to develop the field of Social Robotics focusing on Interaction Quality aspects, with a clear application focus on Robotics in Eldercare. This aim has been accomplished by achieving the following objectives:
1. Recruiting 15 early-stage researchers (ESRs) and providing them with interdisciplinary training comprising
a. User-driven research in five key thematic areas: Emotion, Intention, Adaptivity, Design, and Acceptance, focusing on applications of robotics in eldercare,
b. Multidisciplinary and multi-methodological training in the six disciplinary areas Cognitive Science,Computer Science, Social Psychology, Robotics, Systems Integration, and Business Entrepreneurship,
c. Hands-on experience of knowledge transfer, business development, and commercialisation of robots, through training by the industrial and business-oriented partners in the consortium,
2. Training in complementary/transferable skills to promote a career in both academia and industry.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

The project started with a kick-off in Umeå, Sweden 14-15 Nov 2016. The 15 PhD positions were broadly advertised by all beneficiaries. In total we received 409 applications. In most cases recruitment was completed by Oct 2017.
Both ESRs and senior researchers have enjoyed collaboration and networking at several levels and for several purposes. The ITN project format has been a good catalyzer in this respect.
• The preparations for secondments have resulted in bilateral discussions on research and collaborative work that will make the secondments beneficial for all parties.
• The Creative workshop was organized as part of the 1st SOCRATES project meeting 19/10/2017 in Barcelona. Prior to the event, the ESRs had for several months collaborated in smaller groups on defining and solving the projects related to their research. During the meeting, ESRs finalized and presented their collaborative projects.
• SSR-2018, ‘The International PhD Conference on Safe and Social Robotics, was co-located with IROS 2018 (September 29-30), and was a co-arrangement by the two ITN projects SOCRATES and SECURE (https://secure-robots.eu/). The ESRs were responsible for all parts of the event and early organized themselves in workgroups corresponding to different Conference Chairs. The work in these groups involved close and intense collaboration.
• The Student Conference Course was organized as a network wide training event that started during the Summer school April 30-May 4, 2018, in Ein Gedi, Israel. After this, smaller groups of ESRs reviewed each other’s work in a series of Skype meetings mediated by the beneficiaries.
• As part of Workshop 3 ”Safe Robotics”, held in Bristol on Nov 17-22, 2019, Bristol Business School (BBS) worked in groups on preparing a business case, understanding the role of marketing, making a pitch to potential investors. The ESRs prepared a presentation that was delivered and assessed by an expert panel.

The conducted research has resulted in 72 publications at international scientific conferences, workshops, and journals. In addition, a large number of other dissemination activities have been performed during the project. The ESRs have collectively been involved in 416 dissemination activities, reaching in total more than 15.000 people.
Throughout the project, recorded data, test results, and software code were made publicly available through software repositories such as GitHub.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

Scientific progress has been documented in 72 national and international publications. This work has been conducted within the following 15 problem areas:
• Learning face and upper-body emotion recognition
• Learning emotion recognition through auditory cues and language
• Emotion recognition and expression based on human motion
• Implicit intention recognition by integrating speech and task planning
• Implicit Intention Recognition Using Visual Sensors.
• Intention Driven Dialogue Management.
• Social robotic telepresence with sliding autonomy
• Adaption through multimodal interaction and learning
• Robot personalisation
• Interaction design for varying levels of automation
• Adaptive Hardware Design
• Human Robot interaction safety design
• Measuring interaction effectiveness
• Ethical human-robot interaction
• Empathy and Human-Robot Interaction

Continued collaboration between several beneficiaries has been initiated. This will result in joint applications for research grants and also for direct research collaboration between senior researchers in the consortium.
The major socio-economic impact of the project comprises the communication activities described under the previous heading. The progress beyond state-of-the-art in each ESR’s respective research field, contributes to wider societal implications of the project.

The SOCRATES team at Workshop 2