Autonomous Human-Vehicle Leader-Follower Control Using Deep-Learning-Driven Gesture Recognition

Leader-follower autonomy (LFA) systems have so far only focused on vehicles following other vehicles. Though there been several decades of research into this topic, has not yet any work human-vehicle leader-follower in the known literature. We present a system which an autonomous vehicle—our ACTor 1 platform—can follow human leader who controls vehicle through hand-and-body gestures. successfully developed modular pipeline that uses artificial intelligence/deep learning to recognize gestures from user view vehicle’s camera and translate those physical action by vehicle. demonstrate our using platform, modified Polaris Gem 2. Results show design reliably recognizes body language translates LFA commands real time. This numerous applications such as material transport industrial contexts.