OATCR: Outdoor Autonomous Trash-Collecting Robot Design Using YOLOv4-Tiny

Medhasvi Kulshreshtha,Princy Randhawa,Adil Khadidos,Sushma S Chandra,Alaa O Khadidos,Georgios Tsaramirsis

doi:10.3390/electronics10182292

Medhasvi Kulshreshtha, Princy Randhawa + Show 4 more

Open Access

https://doi.org/10.3390/electronics10182292

Copy DOI

Abstract

This paper proposed an innovative mechanical design using the Rocker-bogie mechanism for resilient Trash-Collecting Robots. Mask-RCNN, YOLOV4, and YOLOv4-tiny were experimented on and analyzed for trash detection. The Trash-Collecting Robot was developed to be completely autonomous as it was able to detect trash, move towards it, and pick it up while avoiding any obstacles along the way. Sensors including a camera, ultrasonic sensor, and GPS module played an imperative role in automation. The brain of the Robot, namely, Raspberry Pi and Arduino, processed the data from the sensors and performed path-planning and consequent motion of the robot through actuation of motors. Three models for object detection were tested for potential use in the robot: Mask-RCNN, YOLOv4, and YOLOv4-tiny. Mask-RCNN achieved an average precision (mAP) of over 83% and detection time (DT) of 3973.29 ms, YOLOv4 achieved 97.1% (mAP) and 32.76 DT, and YOLOv4-tiny achieved 95.2% and 5.21 ms DT. The YOLOv4-tiny was selected as it offered a very similar mAP to YOLOv4, but with a much lower DT. The design was simulated on different terrains and behaved as expected.

Highlights

Robots have been aiding humans in many areas as they are more capable and often better equipped to deal with tasks that include high repeatability
Similar to the function of brain and spine in humans, the Raspberry Pi had the function of running the heavier computational tasks such as image processing and robot tracking, while the Arduino UNO performed intermediary tasks such as obstacle avoidance and path planning, which lifted some load from the Raspberry Pi
A unique robot was built from scratch to autonomously collect trash from public areas

Summary

Introduction

Robots have been aiding humans in many areas as they are more capable and often better equipped to deal with tasks that include high repeatability. The advancements in the areas of batteries, sensors, artificial intelligence (AI), and machine learning (ML) open new horizons and application domains as they allow robots and, more precisely, mobile robots to perform more complex tasks [1]. These can be anything from driving and delivering packages to cleaning jobs [2]. There are many mobile robots designed for indoorcleaning operation, there are less low-cost robots designed for outdoor-cleaning operations with the ability to remove medium-size objects [3] This is very important when the cleaning must be done under difficult environmental conditions, such as heat or cold or when cleaning materials that are hazardous for humans or the environment [4]. A completely autonomous robot was capable of performing activities like trash detection, obstacle avoidance, robotic path-planning, and robotic motion control automatically

Methods

Results

Conclusion