Community Research and Development Information Service - CORDIS

H2020

ACANTO Report Summary

Project ID: 643644
Funded under: H2020-EU.3.1.

Periodic Reporting for period 1 - ACANTO (ACANTO: A CyberphysicAl social NeTwOrk using robot friends)

Reporting period: 2015-02-01 to 2016-01-31

Summary of the context and overall objectives of the project

"The overarching goal of ACANTO is the develop a combination of technologies to spur older adults into a regular and sustained level of physical activity. ACANTO's solution rests on two pillars:
1. the development of a robotic friend (the FriWalk) to support the execution of everyday activities, 2. the development of an intelligent system that produces recommendation for social activities matching the profile of the users,
as they result from the observation collected on the ground through the FriWalk. Owing to the physical nature of these observation and of the resulting recommended activities, we call our system a Cyberphysical Social Network (CPSN).

The FriWalk is robotic walker embedding a large portfolio of solutions to sense the surrounding environment, plan the most comfortable and safe routes to the user's destination, and, where required, gently guide the user in her navigation of the space. The robot constantly observes its user noting all relevant changes in her physical and emotional state.
The way the FriWalk stimulates the user's physical activity is by lowering the barriers raised by user's fears and lack of confidence. Furthermore, the FriWalk keeps track of the users' physical exercises, and monitors the evolution of the strength and the possible improvement of the gait. Finally, the robot notes the emotional state of the user during each activity generating useful information to fill in her profile.

The CPSN collects the profiles of the user and aggregates them into circles. By putting together the description of the circles and of the environment the recommendation system is in condition to recommend social activities. The objective of the CPSN is to stimulate the user social life offsetting the effects of loneliness, which is both cause and consequence of the user's withdrawal from every day activities. Another important way for the system to lower the user's barriers to physical activity is by helping the user translate the intention of an activity into the so called "implementation intentions", a concrete plan detailing logistic and practical aspects.

In the context outlined above, the concrete goals of the project are:
1. development of the FriWalk: from the sensing subsystems to the mechatronic components and to the user interface,
2. development of the recommendation system and of all the software components animating the CPSN,
3. development of an external infrastructure (cloud and environment sensing) that supports both the conception and the execution of social activities,
4. large involvement of users and stakeholder in the development of the different components and in the definition of realistic exploitation routes."

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

"During the first year of activities, the ACANTO consortium has:
1. Kickstarted the activities by establishing the project's management structure and by defining data management and quality plans;
2. Studied persuasion and barriers to identify the design principles that will underly the ACANTO activities;
3. Initiated the collection of requirements and the study on Privacy issues; such requirements are related to the application of our both in a "social" context (e.g., a Museum) and
in a clinical environment;
4. Defined the basic procedures for Ethics management and their overarching principles;
5. Identified a first group of functionalities, which will be implemented in the first version of the prototype;
6. developed the functionalities and started their formative evaluation with users, which allows us to refine their implementation during the course of the project; among these it is worth mentioning:
- algorithms for user sensing (e.g., gait recognition and skeleton decomposition),
- algorithms for environment sensing (e.g., heat maps and SLAMMOT) and distributed localisation,
- algorithms for user guidance based on brakes and haptic interfaces,
- algorithms for reactive planning,
- visual interfaces;
7. Defined a software interface that makes for the easy integration of the different components;
8. Studied the state of the art on dynamic models that describe user group motion in competitive and cooperative situations and sketched the ACANTO solution;
9. Sketched a first version of the software models for user profiles, circles and activities;
10. Started a wide range of communication activities toward the scientific community, the stakeholders and the members of the public."

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)

"The project is in its first year of activities and therefore the progress beyond the state of the art and the socio-economic impacts are difficult to fully evaluate at this stage.

Our best assessment on ACANTO's progress beyond the state of the art so far can be condensed in the following lines:
1. Our studies in the WP1 have revealed new pathways to the analysis of the main barriers and to the development of motivation strategies that can spur older adults into physical activity. The most important finding is that contrary to the conventional wisdom older adults tend to remain active and open to social relations and activities, until a steep decline takes over (the frailty curve). Thereby, our efforts have to be concentrated in this phase to slow down decline and push forward the "frailty" descent as much as possible.

2. No suitable model exists to the date that captures the older adults' requirement on Privacy. This is crucial in for our project and for any project aiming to use technology for active ageing. Our first activities suggest that older have strong privacy concerns and require an easy interface to use to express how much privacy they want to trade to get engaged in exciting activities.

3. The massive amount of research produced so far to study collaborative and cooperative interaction does not seem results directly usable for motion planning and trajectory control. Our work in this area aims to identify the most natural "motion" primitives (e.g., clothoids) that can be combined to generate comfortable motion plans.

4. Clinical diagnostic evaluation to identify the risk of falls or of accidents are currently based on qualitative or semi-quantitative observations, made during short tests executed under the supervision of the medical staff. In limited cases (e.g., gait evaluation or stride measurements) it is possible to use usually expensive devices to obtain quantitative measurements. The use of our vision based solution embedded on the walker promises to produce highly accurate measurements on the most important parameters with a low cast device (which can be incidentally used for other purposes). This is a potential breakthrough both form a scientific and from a commercial viewpoint (one for which IPR protection actions have been undertaken).

5. New algorithms for guidance based on the application of hybrid control systems have allowed us to implement guidance solutions based on the differential action of brakes.

6. Haptic interfaces have shown themselves to be a promising solution for both guidance and control of the correct "pace" (also in this case we are studying IPR protection actions).

As regards the potential impacts determined at proposal time, we do not observe significant deviations (except for a possible additional emphasis on the viability and on the efficacy of the clinical application of our device). More in detail, the most important impacts that we expect to have are the following.

a. Evidence for the benefits of service robotics, based on proof of concept and involvement of stakeholders
The project initial goal is toward the production of a sequence of prototypes, which will be co-developed and evaluated by users and stakeholders. We have produced a first (low-fi) version of the walker used for requirements collection (with users, therapists and stakeholders).
At the moment of this writing we have involved 25 users (out of a total of 100 users that we planned to engage during the project proposal phase) and about 10 caregivers (target for the entire project is 25).
Besides, a number of public appearances has increased the project visibility among different classes of stakeholders, which has further been amplified by our website and by our participation to the social media.
The first version of the prototype is currently under construction. We expect a much larger involvement of users during the formative evaluation phase and during the second collection of requirements.

b. Reduction of admissions and days spent in care institutions and prolongation of time spent in own home
This performance indicator is connected with the number of people who can be spurred into a regular physical activity. Good observations can be made looking at the population of patient followed by the hospital of Getafe and
at the users engaged.
Key to identify these numbers will be the result of the clinical trials and of the longitudinal observation that we will collect throughout the project duration. At this early stage any evaluation would be premature.
Nonetheless, the possibility suggested by the adoption of the FriWalk as a clinical tool makes us believe that the same medical and paramedical staff could be used to follow at least twice as many patient as they
can now. This could make target states in the proposal (200% increase in the duration of the training programmes and 100% increase in the number of patients followed) reachable targets.

c. Improvement in Quality of Life of older persons and of their carers
As for the second impact, also in this case a precise assessment can only me made at the end of the project (after the longitudinal studies and the summative evaluation). The project goal is that the
30% of participants will perceive a reduction of loneliness and this will be evaluated by administering questionnaires.

d. Global leadership in advanced solutions for active and healthy ageing.
Although the project is at an early stage, the attention attracted from international media suggest a potential public appreciation on the relevance of ACANTO's challenges ad on the originality of ACANTO's approach.
The number of scientific publications in reputable venues is in line with our initial expectations. The production of a first patent during the first year of activity and the serious possibility of submitting a second one
suggests a remarkable potential for industrial innovation."

Related information

Record Number: 186692 / Last updated on: 2016-07-14