Design, Development, and Use of Maya Robot as an Assistant for the Therapy/Education of Children with Cancer: a Pilot Study

This study centers around the design and implementation of the Maya Robot, a portable elephant-shaped social robot, intended to engage with children undergoing cancer treatment. Initial efforts were devoted to enhancing the robot’s facial expression recognition accuracy, achieving a 98% accuracy through deep neural networks. Two subsequent preliminary exploratory experiments were designed to advance the study’s objectives. The first experiment aimed to compare pain levels experienced by children during the injection process, with and without the presence of the Maya robot. Twenty-five children, aged 4 to 9, undergoing cancer treatment participated in this counterbalanced study. The paired T-test results revealed a significant reduction in perceived pain when the robot was actively present in the injection room. The second experiment sought to assess perspectives of hospitalized children and their mothers during engagement with Maya through a game. Forty participants, including 20 children aged 4 to 9 and their mothers, were involved. Post Human-Maya Interactions, UTAUT questionnaire results indicated that children experienced significantly less anxiety than their parents during the interaction and game play. Notably, children exhibited higher trust levels in both the robot and the games, presenting a statistically significant difference in trust levels compared to their parents (P-value < 0.05). This preliminary exploratory study highlights the positive impact of utilizing Maya as an assistant for therapy/education in a clinical setting, particularly benefiting children undergoing cancer treatment. The findings underscore the potential of social robots in pediatric healthcare contexts, emphasizing improved pain management and emotional well-being among young patients.

💡 Research Summary

**
This paper presents the design, development, and pilot evaluation of “Maya,” a portable, elephant‑shaped social robot intended to assist children undergoing cancer treatment. The authors first describe the robot’s hardware and software architecture. Maya incorporates a 7‑inch touchscreen, speakers, microphones, three‑axis servomotors for expressive movements, and an onboard camera for facial expression recognition. A deep convolutional neural network (based on ResNet‑50) was trained on a curated dataset of pediatric facial expressions, achieving 98 % classification accuracy across six basic emotions (happiness, sadness, anger, surprise, disgust, neutral). This high‑precision affect‑recognition capability enables Maya to adapt its interactions to the child’s current emotional state.

Two exploratory experiments were conducted with a total of 45 participants (25 children for the pain‑reduction study and 20 child‑parent dyads for the acceptance study). In the first study, a counter‑balanced design compared children’s self‑reported pain during a routine injection with Maya present versus absent. Pain was measured using a visual analog scale (0–10). The presence of Maya resulted in a statistically significant reduction in pain scores (mean decrease of 2.1 points, p < 0.01, Cohen’s d ≈ 0.78). The authors attribute this effect to distraction and emotional comfort provided by Maya’s interactive storytelling, singing, and simple movement games performed before and after the injection.

The second study evaluated the robot’s educational and entertainment functions using the Unified Theory of Acceptance and Use of Technology (UTAUT) questionnaire. Twenty children (aged 4–9) and their mothers engaged in a 15‑minute game session where Maya guided color‑matching and puzzle activities. Post‑interaction, children reported significantly lower anxiety and higher trust in both the robot and the games compared with their mothers (p < 0.05). These findings suggest that children perceive Maya as a friendly companion, whereas parents may remain cautious about the robot’s therapeutic role.

The discussion highlights several contributions: (1) integration of high‑accuracy affect detection into a socially assistive robot for pediatric oncology; (2) empirical evidence that a socially assistive robot can reduce procedural pain in a clinical setting; (3) demonstration that children accept and trust robot‑mediated games more readily than their caregivers. Limitations include the small sample size, lack of longitudinal follow‑up, and the absence of objective physiological pain measures (e.g., heart rate variability). The authors also note the need for deeper investigation into parents’ lower trust scores, possibly related to unfamiliarity with robotic technology in medical contexts.

In conclusion, the pilot results indicate that Maya can positively impact pain management and emotional well‑being for children undergoing cancer treatment. The authors recommend larger, multi‑site trials, extended observation periods, and the development of standardized robot‑clinician interaction protocols to facilitate integration of socially assistive robots into routine pediatric oncology care.