Multi-Modal Gesture-Based Robotic Vehicle Control Using Embedded Systems with Adaptive Signal Processing and Cross-Platform Validation

Advanced robotic vehicle control systems are becoming increasingly important in modern intelligent transportation and automation environments due to the growing demand for adaptive, contactless, and real-time human–machine interaction. Despite significant advancements in embedded robotics, achieving reliable and stable vehicle operation under dynamic real-world conditions remains a major challenge because of sensor noise, inconsistent signal patterns, environmental disturbances, and latency constraints during real-time execution. This work presents a unified intelligent robotic vehicle framework integrating multi-modal operational capabilities including gesture-driven navigation, autonomous vehicle movement, manual control operation, and traffic light signal response within a single embedded architecture. The proposed framework combines motion sensing, adaptive signal interpretation, real-time decision processing, and embedded actuation mechanisms to achieve accurate and stable robotic navigation across varying operational scenarios. A structured processing pipeline involving sensor calibration, signal stabilization, dynamic mapping, and adaptive control strategies is employed to enhance robustness, responsiveness, and operational consistency. The gesture interaction module enables intuitive contactless navigation through motion-based command interpretation, while the autonomous navigation module supports self-directed movement and environmental adaptability. Manual control functionality ensures direct operational intervention for precision movement, whereas the traffic signal response mechanism enables intelligent vehicle behavior based on real-time signal conditions. The complete system is implemented using integrated hardware components including motion sensing units, microcontroller-based processing modules, motor driver interfaces, traffic signal detection mechanisms, and robotic chassis assemblies, ensuring efficient coordination between perception, processing, and physical actuation. Experimental analysis demonstrates stable real-time performance with low operational latency, accurate command execution, reliable autonomous behavior, and consistent signal-based decision response under diverse environmental conditions. Furthermore, the incorporation of real-time feedback mechanisms improves interpretability and operational awareness during system execution. The proposed framework offers enhanced adaptability, scalability, and functional reliability compared to conventional robotic control approaches, making it a suitable solution for next-generation intelligent robotics, smart mobility platforms, automation systems, and assistive embedded technologies.