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

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.

Robot móvil autónomo con reconocimiento y navegación hacia botellas de plástico

“…En (Kulshreshtha et al, 2021) presentan el diseño de un robot recolector de basura. Los sensores que incluyen son una cámara, un sensor ultrasónico y un módulo GPS.…”

“…Diferente de otras propuestas recientes con objetivos similares (Kulshreshtha, 2021), (De La Torre et al, 2020), (Ramírez et al, 2020), (Bai, 2018), donde el reconocimiento se realiza al nivel de áreas rectangulares que encierran a los objetos, en este proyecto se aplica Segmentación Semántica (Ronneberger et al, 2015), para reconocer los objetos al nivel de pixeles. Esto permite delimitar el contorno de las botellas, y estimar su área y centroide de forma más precisa.…”

Automatic recognition of parasitic products in stool examination using object detection approach

“…Due to the lower accuracy of YOLOv3, larger weight of YOLOv4, and complex network structure of YOLOv5, a more simplified version of YOLOv4 (YOLOv4-Tiny) was designed to maximize detection speed and improve computational efficiency ( Wang, Bochkovskiy & Liao, 2021 ). In particular, it has been applied to the pine wilt disease detection ( Li et al, 2021 ), trash detection ( Kulshreshtha et al, 2021 ), multi-object tracking ( Wu et al, 2021 ), electronic component detection ( Guo et al, 2021 ), construction machinery and material identification ( Yao et al, 2022 ), and fruit flies gender classification ( Genaev et al, 2022 ). Based on the literatures, our research also focused on the fourth tiny model of YOLO, namely the YOLOv4-Tiny because it produces faster detection results and uses less memory with the support of low-end GPU devices.…”

Real-Time Fire Detection Method for Electric Vehicle Charging Stations Based on Machine Vision

“…In [15][16][17][18][19][20][21], the YOLOv4 network was applied to target detection tasks such as agricultural product inspection, industrial safety, and robot vision and achieved good detection results. In [22], a method to detect fires and PPEs to assist in monitoring and evacuation tasks was presented, using deep learning-based YOLOv4 and YOLOv4 tiny algorithms to perform the detection task, using a homemade fire dataset to train the model with a maximum average accuracy (mAP) of 76.86%.…”