Agentic education · Learning science

Actionable companion · Learning design & outcomes

Learning with agency: Therapeutic educational robot enhancing social interactions in the management of obesity

AI-assisted editorial implementation guide, separate from the original research. Proposed actions are not claims or recommendations attributed to the source authors. No independent peer review of this guide is asserted.

Read original paperSearch paper agentCC BY 4.0

Evidence and context

Title and abstract screening; stage labels describe reported settings, not verified numerical ages. Design labels require full-text appraisal. Reported stage(s): Age / stage not established. Verify the participant population and task before transferring the findings.

Original authors’ abstract, reproduced under the linked source license:

Obesity is a chronic multifactorial pathology determined by many factors, including incorrect eating habits and a low level of physical activity. There is an urgent need to promote a persistent change in lifestyle in obese subjects, but very few individuals maintain long-term results achieved after diet therapies. Therapeutic Education (TE) has taken over an important role as a multidisciplinary intervention aimed at improving lifestyle and at acquiring new skills for the management of the disease. However, only a small portion of patients can maintain participation in such programs and fully benefit from them. Assistive technologies, and in particular assistive social robots, are powerful tools to boost independence and improve participation in educational activities. The aim of the research work described in this article is to evaluate the effect of employing a social robot as a therapeutic educational robot helping the expert therapist in the education activity. This article describes the implementation, deployment, and evaluation of a social educational robot used as a TE assistant. Although we cannot provide statistically significant results due to the limited number of people involved in the experimental protocol, all experimental results show a positive trend, indicating that the robot can enhance the social interactions between the patients and the therapist and among the patients, thus bringing to better overall results of the TE sessions, measured with standard tests for obesity management.

What kind of evidence is this?

Embodied learning agents · Design requires full-text appraisal

Stage: Age / stage not established. Screening labels describe reported context and study-design language. They are not a risk-of-bias rating or proof of effectiveness for an age band.

Study methods · source passage

Each TE session is organized in 8 meetings, lasting 2 hours every 2 weeks. The group of participants to each therapy is relatively small, between 8 and 10 patients. The therapy is led by a principal physician, and a co-therapist (psychologist or psychotherapist). Other specialists are invited in some of the meetings to address specific topics. In particular, the principal therapist is responsible for providing educational content to patients and for guiding discussions and interactions between patients and physicians and between patients themselves. As already mentioned, the commitment of the patients in actively attending the entire educational process is very important.

Limitations and uncertainty · source passage

4) Short Form (36) Health Survey (SF36) Taylor and Sirois (2012). It includes 36 items that measure patients’ health status. It is commonly used in health economics to determine the cost-effectiveness of a health treatment. It takes into account two major domains, which contribute to the Quality of Life (QoL): physical and psychological health. Eight subscales can be derived and they represent the weighted sums of the questions in their section: vitality/fatigue, physical functioning, role limitations due to physical problems, role limitations due to emotional problems, general health perceptions, bodily pain, social functioning, general mental health. Each subscale is directly transformed into a 0–100 subscale on the assumption that each question carries equal weight. Moreover, a summary of physical QoL (Physical Component Summary, PCS) and psychological QoL (Mental Component Summary, MCS) can be obtained by working out the average of all of the physically relevant items and of all of the emotionally relevant items mentioned above. For each component summary the mean score is 50 with a standard deviation (SD) of 10. The lower the score, the more severe the disability; the higher the score, the less severe the disability (i.e., a score of zero is equivalent to maximum disability, meaning minimum QoL in that area, and a score of 100 is equivalent to no disability, meaning maximum QoL in that area).

Design the system before the pilot

Compare the embodied interaction with an equivalent human-led or screen-based activity. Separate the effects of novelty and social presence from learning. Review physical access, sensory needs and adult supervision.

  • Specify a measurable learning objective, a comparator and a task without tool assistance before adopting a system.

A 90-day district pilot

  1. Days 1–15 · Appraise. Have the curriculum lead and a teacher read the methods and limitations. Record the study design, sample, comparator, outcomes and evidence gaps. Define a local question that the study can help inform.
  2. Days 16–30 · Design. Treat the paper as background evidence until its population is verified in the full text. Do not assign an age-specific intervention or extend adult results to children. Name an accountable owner and set the baseline, success threshold and budget before implementation.
  3. Days 31–60 · Test. Start with a small voluntary cohort, preserve an accessible non-AI route and require teacher review. Use synthetic or de-identified examples; approve data handling and tool terms through district processes.
  4. Days 61–90 · Decide. Extract the participant ages or education stage, recruitment, task and comparator before selecting a local pilot. If these cannot be established, retain the paper for design discussion rather than age-band efficacy claims. Compare with baseline, document uncertainty and stop or revise if learning worsens, access is unequal or critical errors persist.

The board decision brief

Report the learning problem, evidence quality, participating population, total cost including review time, measured benefit, errors, access differences and remaining uncertainties. Make a dated recommendation to stop, revise or expand. A positive perception survey alone does not establish learning improvement.

Attribution and reuse

Enrico Prosperi; Giada Guidi; Christian Napoli; Lucio Gnessi; Luca Iocchi. Therapeutic educational robot enhancing social interactions in the management of obesity. Frontiers in Robotics and AI (2022-08-17). https://doi.org/10.3389/frobt.2022.895039

Companion prepared 2026-10-30. Original authorship and DOI are preserved. The abstract is an attributed source extract; the implementation plan is new AI-assisted editorial material, offered under the same CC BY 4.0 license. This guide has not undergone independent peer review.