🤖 AI Summary
This work addresses two critical challenges in fully autonomous delivery robots deployed on resource-constrained embedded platforms: (1) insufficient real-time performance of AI perception algorithms, and (2) low-latency, reliable communication between ROS 2 and embedded motion controllers. To this end, we propose a heterogeneous computing framework that tightly couples AI-based perception with hard real-time motion control. We design a firmware-level emergency motor shutdown mechanism for fault tolerance and an AWS IoT–enabled remote reliability monitoring system. Furthermore, we implement a cross-platform, low-latency communication protocol between Raspberry Pi 5 and ESP32/FreeRTOS, integrated with PID-based closed-loop motor control. The complete system demonstrates end-to-end perception, path planning, and motion control in realistic outdoor environments, sustaining continuous, stable delivery operations. It achieves industrial-grade robustness, determinism, and deployability on cost-effective embedded hardware.
📝 Abstract
This paper presents the development of a fully autonomous delivery robot integrating mechanical engineering, embedded systems, and artificial intelligence. The platform employs a heterogeneous computing architecture, with RPi 5 and ROS 2 handling AI-based perception and path planning, while ESP32 running FreeRTOS ensures real-time motor control. The mechanical design was optimized for payload capacity and mobility through precise motor selection and material engineering. Key technical challenges addressed include optimizing computationally intensive AI algorithms on a resource-constrained platform and implementing a low-latency, reliable communication link between the ROS 2 host and embedded controller. Results demonstrate deterministic, PID-based motor control through rigorous memory and task management, and enhanced system reliability via AWS IoT monitoring and a firmware-level motor shutdown failsafe. This work highlights a unified, multi-disciplinary methodology, resulting in a robust and operational autonomous delivery system capable of real-world deployment.