Follow the Soldiers with Optimized Single-Shot Multibox Detection and Reinforcement Learning

TL;DR

This paper presents an autonomous system for following a soldier using an optimized SSD Lite model and reinforcement learning, demonstrating improved speed and accuracy over other SSD variants.

Contribution

The paper introduces the use of SSD Lite combined with reinforcement learning for real-time object following in autonomous systems, with comparative performance analysis.

Findings

SSD Lite outperforms SSD and SSD with NCS in speed and accuracy

SSD Lite achieves 2-3 times faster inference speed

The integrated system successfully follows a moving soldier in real-world scenarios

Abstract

Nowadays, autonomous cars are gaining traction due to their numerous potential applications on battlefields and in resolving a variety of other real-world challenges. The main goal of our project is to build an autonomous system using DeepRacer which will follow a specific person (for our project, a soldier) when they will be moving in any direction. Two main components to accomplish this project is an optimized Single-Shot Multibox Detection (SSD) object detection model and a Reinforcement Learning (RL) model. We accomplished the task using SSD Lite instead of SSD and at the end, compared the results among SSD, SSD with Neural Computing Stick (NCS), and SSD Lite. Experimental results show that SSD Lite gives better performance among these three techniques and exhibits a considerable boost in inference speed (~2-3 times) without compromising accuracy.