Comprehensive Evaluation of an Intelligent Feeding Robot for the Elderly: Effectiveness, Safety, and Human-Robot Interaction

Abstract

To address the growing demand for assisted feeding in aging societies, our team developed an intelligent feeding robot named “Xiao Xi”. This robot integrates multimodal interaction (voice control, handheld button, foot pedal, and mechanical button), deep learning-based food recognition and mouth positioning, and a novel spoon-chopstick integrated mechanism capable of handling both solid and semi-solid foods. To systematically evaluate its clinical value, we enrolled 40 healthy elderly participants in a randomized crossover trial, comparing a robot-assisted feeding session (RFS) with a human-assisted feeding session (HFS). Outcome measures included food intake percentage, successful feeding percentage, average feeding duration, QUEST 2.0 satisfaction score, and safety outcomes. RFS showed a lower food intake percentage than HFS (adjusted mean difference = −33.90%, 95% CI: −35.57 to −32.23, p < 0.001) and required a longer average feeding duration (adjusted mean difference = 2.78 s, 95% CI: 2.35 to 3.21, p < 0.001). No significant differences were observed in the successful feeding percentage or QUEST 2.0 satisfaction score. No adverse events occurred during either feeding condition. These findings suggest that “Xiao Xi” is safe and acceptable for healthy elderly users, but its feeding efficiency remains lower than HFS. Further optimization and validation in elderly individuals with real feeding assistance needs are required.

Keywords

Intelligent feeding robot / Multimodal interaction / Randomized crossover trial / Assistive technology / Evaluation / Elderly

References

[1] World Health Organization.Secondary Ageing and Health Financing; World Health Organization: Geneva, Switzerland, 2023.

[2] Harwood RH, Sayer AA, Hirschfeld M. Current and future worldwide prevalence of dependency, its relationship to total population, and dependency ratios. Bull. World Health Organ. 2004, 82, 251-258. Available online: https://www.scielosp.org/pdf/bwho/2004.v82n4/251-258/en (accessed on 22 July 2026).

[3] Simmons SF, Schnelle JF. Individualized Feeding Assistance Care for Nursing Home Residents: Staffing Requirements to Implement Two Interventions. J. Gerontol. Ser. A Biol. Sci. Med. Sci. 2004, 59, M966-M973. DOI: 10.1093/gerona/59.9.M966

[4] Morrison-Koechl J, Wu SA, Slaughter SE, Lengyel CO, Carrier N, Keller HH . Hungry for more: Low resident social engagement is indirectly associated with poor energy intake and mealtime experience in long-term care homes. Appetite 2021, 159, 105044. DOI: 10.1016/j.appet.2020.105044

[5] Avraham R, Lev N, Deutsch JM, Davidovitch N, Shapira S . Older Adults’ Experiences of Institutional Eating and Dining: A Qualitative Study on Mealtimes in Adult Day Centers. Nutrients 2025, 17, 420. DOI: 10.3390/nu17030420

[6] Ji EK, Wang HH, Jung SJ, Lee KB, Kim JS, Jo L, et al. Graded motor imagery training as a home exercise program for upper limb motor function in patients with chronic stroke. Medicine 2021, 100, e24351. DOI: 10.1097/MD.0000000000024351

[7] Prince MJ, Wu F, Guo Y, Gutierrez Robledo LM, O’Donnell M, Sullivan R, et al. The burden of disease in older people and implications for health policy and practice. Lancet 2015, 385, 549-562. DOI: 10.1016/S0140-6736(14)61347-7

[8] Antonini A, Barone P, Bonuccelli U, Annoni K, Asgharnejad M, Stanzione P, et al. ICARUS study: Prevalence and clinical features of impulse control disorders in Parkinson’s disease. J. Neurol. Neurosurg. Psychiatry 2017, 88, 317-324. DOI: 10.1136/jnnp-2016-315277

[9] Nayar SK, Alcock HMF, Edwards DS. Primary amputation versus limb salvage in upper limb major trauma: A systematic review. Eur. J. Orthop. Surg. Traumatol. 2022, 32, 395-403. DOI: 10.1007/s00590-021-03008-x

[10] Simões P, Amaral AP, Rocha C . Malnutrition in elderly: Relationship with depression, loneliness and quality of life. Eur. J. Public Health 2021, 31, ckab120-093. DOI: 10.1093/eurpub/ckab120.093

[11] Yang C, Zhao F, Xie C, Zhang Y, Dou Z, Wei X. Community-based group rehabilitation program for stroke patients with dysphagia on quality of life, depression symptoms, and swallowing function: A randomized controlled trial. BMC Geriatr. 2023, 23, 876. DOI: 10.1186/s12877-023-04555-0

[12] Horn J, Simpson KN, Simpson AN, Bonilha LF, Bonilha HS. Incidence of Poststroke Depression in Patients with Poststroke Dysphagia. Am. J. Speech Lang. Pathol. 2022, 31, 1836-1844. DOI: 10.1044/2022_AJSLP-21-00346

[13] Yang X, Hao Y, George SM, Wang L. Factors associated with health-related quality of life among Chinese caregivers of the older adults living in the community: A cross-sectional study. Health Qual. Life Outcomes 2012, 10, 143. DOI: 10.1186/1477-7525-10-143

[14] Liu F, Xu P, Yu H. Robot-assisted feeding: A technical application that combines learning from demonstration and visual interaction. Technol. Health Care 2021, 29, 187-192. DOI: 10.3233/THC-202527

[15] Kim K, Kim JH, Kim JB. Design, control, and evaluation of a meal-assistive robot based on gravity compensation for elderly people with muscle weakness. Gerontechnology 2022, 21, 7. DOI: 10.4017/gt.2022.21.s.541.7.sp1

[16] Turgeon P, Dubé M, Laliberté T, Archambault PS, Flamand VH, Routhier F, et al. Mechanical design of a new device to assist eating in people with movement disorders. Assist. Technol. 2022, 34, 170-177. DOI: 10.1080/10400435.2020.1734111

[17] Dubé M, Laliberté T, Flamand V, Routhier F, Campeau-Lecours A. Mechanical design improvement of a passive device to assist eating in people living with movement disorders. arXiv 2021, arXiv:2010.06752. DOI: 10.48550/arXiv.2010.06752

[18] Turgeon P, Laliberte T, Routhier F, Campeau-Lecours A. Preliminary Design of an Active Stabilization Assistive Eating Device for People Living with Movement Disorders. In Proceedings of the 2019 IEEE 16th International Conference on Rehabilitation Robotics (ICORR), Toronto, ON, Canada, 24-28 June 2019; pp. 217-223.

[19] Hong W, Lee J, Lee WG. A Dual-Padded, Protrusion-Incorporated, Ring-Type Sensor for the Measurement of Food Mass and Intake. Sensors 2020, 20, 5623. DOI: 10.3390/s20195623

[20] Mokhtari M, Feki MA, Abdulrazak B, Grandjean B . Toward a Human-Friendly User Interface to Control an Assistive Robot in the Context of Smart Homes. In Advances in Rehabilitation Robotics; Bien ZZ, Stefanov D, Eds.; Springer: Berlin/Heidelberg, Germany, 2004; Volume 306, pp. 47-56.

[21] Topping M. Flexibot-A multi-functional general purpose service robot. Ind. Robot Int. J. 2001, 28, 395-401. DOI: 10.1108/01439910110401466

[22] Irving M. Obi Robot Arm Gives Disabled Diners a Helping Hand. New Atlas. 2016. Available online: https://newatlas.com/obi-robot-feeding-arm/44394/ (accessed on 23 July 2026).

[23] Soyama R, Ishii S, Fukase A. Selectable operating interfaces of the meal-assistance device “My Spoon”. In Advances in Rehabilitation Robotics; Bien ZZ, Stefanov D, Eds.; Springer: Berlin/Heidelberg, Germany, 2004; Volume 306, pp. 47-56.

[24] Ha J, Park S, Im CH, Kim L. A Hybrid Brain-Computer Interface for Real-Life Meal-Assist Robot Control. Sensors 2021, 21, 4578. DOI: 10.3390/s21134578

[25] Liu F, Yu H, Wei W, Qin C. I-feed: A robotic platform of an assistive feeding robot for the disabled elderly population. Technol. Health Care 2020, 28, 425-429. DOI: 10.3233/THC-202320

[26] Park D, Hoshi Y, Mahajan HP, Kim HK, Erickson Z, Rogers WA, et al. Active robot-assisted feeding with a general-purpose mobile manipulator: Design, evaluation, and lessons learned. Robot. Auton. Syst. 2020, 124, 103344. DOI: 10.1016/j.robot.2019.103344

[27] Chan SCC, Chan APS. The Validity and Applicability of the Chinese Version of the Quebec User Evaluation of Satisfaction with Assistive Technology for People With Spinal Cord Injury. Assist. Technol. 2006, 18, 25-33. DOI: 10.1080/10400435.2006.10131904

[28] Wang C, Wang K, Li J, Wang X, Chen Y. Structure Design and Trajectory Planning of Meal-assistance Robot. In Proceedings of the 2022 12th International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER), Baishan, China, 25-27 July 2022.

[29] Wentao H, Lan W, Yan L . Meal target detection based on improved YoloV3 Algorithm. In Proceedings of the 2022 12th International Conference on CYBER Technology in Automation, Control, and Intelligent Systems (CYBER), Baishan, China, 25-27 July 2022.

[30] Thompson CJ, Martin-Wagar CA. Cognitive flexibility and emotion regulation in eating disorder patients with comorbid generalized anxiety and posttraumatic stress symptoms. Eat. Disord. 2025, 33, 666-680. DOI: 10.1080/10640266.2024.2405290

[31] Volkert D, Beck AM, Cederholm T, Cruz-Jentoft A, Hooper L, Kiesswetter E, et al. ESPEN practical guideline: Clinical nutrition and hydration in geriatrics. Clin. Nutr. 2022, 41, 958-989. DOI: 10.1016/j.clnu.2022.01.024

[32] Palese A, Bressan V, Hayter M, Watson R. Enhancing independent eating among older adults with dementia: A scoping review of the state of the conceptual and research literature. BMC Nurs. 2020, 19, 32. DOI: 10.1186/s12912-020-00425-x

[33] Yan Z, Drury P, Alananzeh I, Zugai J, Halcomb E. Improving Mealtime Independence for People with Dementia Living in Nursing Homes: A Pilot Study. Nurs. Res. Pract. 2025, 2025, 8948151. DOI: 10.1155/nrp/8948151

[34] Fetherstonhaugh D, Haesler E, Bauer M. Promoting mealtime function in people with dementia: A systematic review of studies undertaken in residential aged care. Int. J. Nurs. Stud. 2019, 96, 99-118. DOI: 10.1016/j.ijnurstu.2019.04.005

[35] Saklani A, Tiwari S, Pannu HS. Ameliorating multimodal food classification using state of the art deep learning techniques. Multimed. Tools Appl. 2024, 83, 60189-60212. DOI: 10.1007/s11042-023-17850-0

[36] Christodoulidis S, Anthimopoulos M, Mougiakakou S . Food Recognition for Dietary Assessment Using Deep Convolutional Neural Networks. In New Trends in Image Analysis and Processing-ICIAP 2015 Workshops; Springer: Cham, Switzerland, 2015; pp. 458-465.

[37] Weng WT, Huang HP, Zhao YL, Lin CY. Development of a Visual Perception System on a Dual-Arm Mobile Robot for Human-Robot Interaction. Sensors 2022, 22, 9545. DOI: 10.3390/s22239545

[38] Blavette L, Dacunha S, Alameda-Pineda X, Hernández García D, Gannot S, Gras F, et al. Acceptability and Usability of a Socially Assistive Robot Integrated with a Large Language Model for Enhanced Human-Robot Interaction in a Geriatric Care Institution: Mixed Methods Evaluation. JMIR Hum. Factors 2025, 12, e76496. DOI: 10.2196/76496