Agriculture Rover For Soil and Crop Data Collection

The prototype demonstrates the feasibility of developing a low-cost ESP32-based agricultural rover for basic field monitoring. During testing, the rover successfully avoided obstacles in 28 out of 30 attempts, corresponding to a success rate of approximately 93.3%. The soil moisture sensor also distinguished between dry and wet soil conditions, while the system monitored surrounding air conditions. The reported operating time of 2.5–3.5 hours and estimated prototype cost of ₹2,100–₹3,800 indicate its potential for affordable agricultural applications. Future improvements will focus on integrating an ESP32-CAM with a lightweight convolutional neural network (CNN), such as Tiny-YOLO, for leaf disease classification; a GPS module for location-based soil data collection; and a solar panel for supplementary battery charging. A linear actuator could enable rootzone soil probing, while LoRaWAN could support long-range data transmission. Multi-sensor ranging and row-following control could further improve navigation accuracy and operational reliability. It is important to distinguish the tested system from the proposed enhancements. Although the camera, GPS module, and solar panel are visible in the prototype photograph, they were not included in the reported experimental configuration. Therefore, their performance and contribution to the system have not yet been validated. Further testing under different soil, lighting, and field conditions will be necessary to evaluate the reliability and practical suitability of the proposed system.

1]        A. Sharma, A. Jain, P. Gupta, and V. Chowdary, “Machine learning applications for precision agriculture: A review,” IEEE Access, vol. 9, pp. 4843–4876, 2021. [2]            J. Hemming and T. Rath, “Computer-visionbased weed identification under field conditions using controlled lighting,” J. Agric. Eng. Res., vol. 78, no. 3, pp. 233–243, 2001. [3]            C. Zhang and J. M. Kovacs, “The application of small unmanned aerial systems for precision agriculture: A review,” Precision Agric., vol. 13, no. 6, pp. 693–712, 2012. [4]            S. Wolfert, L. Ge, C. Verdouw, and M.-J. Bogaardt, “Big data in smart farming – A review,” Agric. Syst., vol. 153, pp. 69–80, 2017. [5]       P. Radoglou-Grammatikis, P. Sarigiannidis, T. Lagkas, and I. Moscholios, “A compilation of UAV applications for precision agriculture,” Comput. Netw., vol. 172, Art. no. 107148, 2020. [6]            M. S. Farooq, S. Riaz, A. Abid, K. Abid, and M. A. Naeem, “A survey on the role of IoT in agriculture for the implementation of smart farming,” IEEE Access, vol. 7, pp. 156237– 156271, 2019. [7]            F. Rovira-Más, “Sensor architecture and task classification for agricultural vehicles and environments,” Sensors, vol. 10, no. 12, pp. 11226–11247, 2010. [8]            A. Bechar and C. Vigneault, “Agricultural robots for field operations: Concepts and components,” Biosyst. Eng., vol. 149, pp. 94–111, 2016. [9]            R. K. Kodali and S. Sahu, “IoT based smart agricultural system using ESP32,” in Proc. IEEE ic-ETITE, 2020, pp. 1–5. [10]          K. R. Aravind, P. Raja, and M. PérezRuiz, “Task-based agricultural mobile robots in arable farming: A review,” Span. J. Agric.    Res., vol. 15, no. 1, Art. no. e02R01, 2017.