Autonomous Vehicle Routing and Navigation, Computer Vision Algorithms, and Transportation Analytics in Network Connectivity Systems

Obstacle detection and target tracking are two major issues for intelligent autonomous vehicles. This paper proposes a new scheme to achieve target tracking and real-time obstacle detection of obstacles based on computer vision. ResNet-18 deep learning neural network is utilized for obstacle detection and Yolo-v3 deep learning neural network is employed for real-time target tracking. These two trained models can be deployed on an autonomous vehicle equipped with an NVIDIA Jetson Nano motherboard. The autonomous vehicle moves to avoid obstacles and follow tracked targets by camera. Adjusting the steering and movement of the autonomous vehicle according to the PID algorithm during the movement, therefore, will help the proposed vehicle achieve stable and precise tracking.

Download Full-text

Numerical route reservation method in the geoinformatic task of autonomous vehicle routing

Computer Optics ◽

10.18287/2412-6179-2018-42-5-912-920 ◽

2018 ◽

Vol 42 (5) ◽

pp. 912-920 ◽

Cited By ~ 10

Author(s):

A.A. Agafonov ◽

◽

V.V. Myasnikov ◽

◽

Keyword(s):

Vehicle Routing ◽

Autonomous Vehicle

Download Full-text

Development of a Data Acquisition System for Autonomous Vehicle Systems

International Journal of Vehicle Structures and Systems ◽

10.4273/ijvss.10.4.04 ◽

2018 ◽

Vol 10 (4) ◽

Cited By ~ 1

Author(s):

Yucheng Liu ◽

Andrew Le Clair ◽

Matthew Doude ◽

V. Reuben F. Burch

Keyword(s):

Data Acquisition ◽

Autonomous Vehicle ◽

Video Recording ◽

Network Connectivity ◽

Data Acquisition System ◽

Acquisition System ◽

Sensor Data ◽

Vehicle Speed ◽

Usage Patterns ◽

Sensor Package

A data acquisition system along with a sensor package was designed and installed on an existing mechanically-controlled system to gather more data on their usage patterns. The data collected through the developed system include GPS route, vehicle speed and acceleration, engine state, transmission state, seat occupancy, fuel level, and video recording. The sensor package was designed and integrated in a way that does not interfere with the driver’s operation of the system. Cellular network connectivity was employed to retrieve sensor data so as to minimize human effort and maintain typical usage patterns of the outfitted systems. Testing and validation results showed that the developed system can correctly and effectively record data necessary for further analysis and optimization. The collected data will significantly promote system activity simulations in order to facilitate optimizing work flow at large industrial facilities and improving energy efficiency.

Download Full-text

SEMI-OTOMATIS SISTEM PENGEREMAN AUTONOMOUS VEHICLE MENGGUNAKAN PNEUMATIK SILINDER BERBASIS MIKROKOTROLLER

E-Link : Jurnal Teknik Elektro dan Informatika ◽

10.30587/e-link.v16i2.3055 ◽

2021 ◽

Vol 16 (2) ◽

pp. 1

Author(s):

Teguh Arifianto ◽

Royyan Ghozali ◽

Akhwan Akhwan ◽

Sunardi Sunardi ◽

Willy Artha Wirawan

Keyword(s):

Computer Vision ◽

Autonomous Vehicle

Autonomous vehicle merupakan moda transportasi masa depan yang menerapkan imageprocessing dan computer vision untuk pengenalan objek maupun kendali pada motor. Transportasiini dapat beroperasi sendiri sehingga kendaraan ini mengutamakan keamanan dalam berkendara.Jika pada kendaraan konvensional, sistem pengereman dikendalikan oleh pengendara. Namun, padakendaraan autonomous, sistem pengereman akan bekerja pada keadaan tertentu. Penelitian inimemodifikasi pengereman mekanik yang ada pada kendaraan autonomous agar dapat bekerja secarasemi otomatis dengan menggunakan aktuator pneumatik silinder berukuran 50x50mm. Selain itu,penelitian ini juga menggunakan sensor warna pixycam dan micro lidar vl53l0x sebagai input padamikrokontroller arduino. Input pada mikrokontroller arduino ini menjadi parameter perintah untukmengaktifkan selenoid valve agar udara bertekenan dapat menggerakkan pneumatik silinder. Hasildari penelitian ini adalah pemakaian silinder pneumatik berukuran 50x50mm dapat menarik pedalrem pada sarana autonomous dengan tangki udara bervolume 0,16m3 dan tekanan sebesar 6 bar.

Download Full-text