AI-Enabled IoT Framework for Smart Cargo Bike Monitoring and Sustainable Urban Last-Mile Delivery

View at publisher Summarise with VIRAT
Authors: S. K. Mydhili, Niranjani M., Subash S., Merlin Christy J., R Nithyasri
Cited by: 0
References: 11

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Urban last-mile delivery operations increasingly demand cost-efficient and environmentally sustainable transportation solutions. While electric cargo bikes present a viable alternative to conventional fuel-based vehicles, their large-scale adoption is often constrained by limited real-time monitoring, energy-aware routing, and performance validation. This paper proposes an AI-enabled IoT framework for intelligent cargo bike monitoring and sustainable urban logistics. The system integrates on-bike sensors with cloudbased analytics to continuously acquire battery voltage and current, payload weight, environmental parameters, and GPS data. A modified$A^{*}$search-based energy-aware routing algorithm is employed to minimize battery consumption by incorporating payload and terrain characteristics, while a regression-based battery state-of-charge model enables accurate range prediction. Experimental evaluation conducted on representative urban routes in Coimbatore demonstrates that the proposed electric cargo bike consumes approximately$11.67 ~\text{Wh} / \text{km}$, resulting in an operating cost of ₹ 0.17 per kilometer, which is nearly 20 times lower than the ₹3.44 per kilometer cost of conventional petrol-based delivery vehicles. For a 9 km trip, the electric energy cost remains at ₹1.5, whereas the petrol cost rises to ₹31.0, highlighting a substantial economic advantage. In terms of environmental impact, the system achieves an average$\mathbf{C O}_{\mathbf{2}}$displacement of$\mathbf{1 0 2. 2 ~ g}$per kilometer, with total savings increasing from 370 g at 4 km to 920 g at 9 km. Real-time visualization through a smart dashboard validates these results under dynamic operating conditions, confirming the framework's suitability for fleet-level deployment. Overall, the proposed solution delivers a datadriven, economically viable, and environmentally sustainable approach to intelligent last-mile urban logistics.

Fields of Study & Subjects

Urban and Freight Transport Logistics Vehicle Routing Optimization Methods Electric Vehicles and Infrastructure

Publication details

Journal / source
International Conference on Intelligent Systems for Communication, IoT and Security (ICISCoIS)
Pages
1–8
Publication date
8 January 2026
Language
EN