AI-Enabled Citizen-Driven Platforms for Stray Animal Rescue: Architecture, Challenges, and Future Directions

In this paper, the rationale, architectural design, and research setting behind StrayCare – a citizen-led, cloud native platform for stray animal rescue coordination have been presented. Through an organized study of existing technologies related to the theme, it became apparent that one major gap exists in the welfare technology ecosystem – the absence of an integrated, transparent, and role-based platform that connects the citizens, NGOs, and administrators in real-time. The proposed architecture bridges this gap by adopting layered service-oriented design, incident reporting using GPS, role-based access control, push notifications through Firebase, and a hotspot analytics component. All computational tasks involved in the operation of the platform are shown to be polynomial-time tractable or polynomial-time approximable under appropriate optimality guarantees. However, some important limitations – availability without internet connection, triaging using artificial intelligence, multilingualism, and nationwide federation – have been outlined as a structured research agenda in themselves, where solving each limitation is a concrete engineering or research problem which, if solved, can help extend the impact of the platform. Apart from stray animal welfare, the architectural principles and the transparency-first design philosophy described above are generalizable to other humanitarian coordination problems as well, such as community health worker assignment or food bank logistics.

1. Banerjee, L. & Rao, N. (2023). AI for Social Good: Animal Rescue and Welfare Applications. Elsevier AI Review, 14(2), 88–104. 2. Bhattacharya, S., Verma, R., & Singh, P. (2019). Crowdsourced Rescue Systems Using Mobile Platforms. Proc. ACM SmartCity Symposium, 45–53. 3. Gupta, A. & Mehta, S. (2022). Geospatial Data Analytics for Emergency Resource Allocation. Springer Nature. 4. Li, J. & Raj, K. (2020). Complexity and Heuristic Approaches in Vehicle Routing Problems. Journal of Computational Optimization, 27(3), 201–218. 5.  Mellor, D. J., Cave, N. E., & Beausoleil, N. J. (2020). Ward's Ten Commandments of Animal Welfare Revisited under the Five Domains Model. Veterinary Sciences, 7(1), 13. 6. Okolloh, O. (2009). Ushahidi: Web 2.0 Tools for Crowdsourcing Crisis Information. Participatory Learning and Action, 59(1), 65–70 7. Sharma, R., Nair, P., & Bhatia, M. (2021). AI-Driven Animal Welfare and Image Recognition in Smart Cities. IEEE Access, 9, 135421–135432. 8. Singh, A. & Kumar, R. (2021). Smart Computing and Sensing Technologies for Animal Welfare Operations. Intl. J. Animal Welfare Technology, 6(1), 33–49. 9. Government of India, DAHD. (2023). Annual Report on Stray Animal Population Management. New Delhi. 10. Howard, J. & Gugger, S. (2020). Fastai: A Layered API for Deep Learning. Information, 11(2), 108.