Gesture Controlled Rover with Visual Processing Using ESP32-CAM and Edge AI

Gesture Controlled Rover with Visual Processing Using ESP32-CAM and Edge AI

Vijay Mahali1, Sunil Kumar1, Vishal Kumar1 , Mrs. Anamika Kumari2 , Mr.Hare krishna2

Department of Electronics and Communication Engineering

1 B.Tech Scholar , RTCIT Ormanjhi  Ranchi, Jharkhand, India

2 Assistant Professor, RTCIT Ormanjhi  Ranchi,Jharkhand India

Abstract - This research introduces a novel, budget-friendly robotic system that integrates gesture-based control and real-time object detection on a mobile rover. The system uses a smartphone’s gestures for directional control and the ESP32-CAM module for capturing visual data, processed locally using a compact machine learning model trained via Edge Impulse. This hybrid configuration allows seamless human-machine interaction and intelligent behavior in various environments. The rover is well-suited for surveillance, rescue operations, and intelligent automation, combining affordability with innovation.

Keywords
Gesture-Controlled Rover, ESP32-CAM, Edge AI, Real-Time Object Detection, Embedded Machine Learning, Edge Impulse, Bluetooth Navigation, Visual Processing Robot, Arduino Robotics, Smart Surveillance, Low-Power AI, DIY Robotics, On-Device Inference.