Melola Discovery

← Melola Discovery

Jurnal SINTA 1

Key Factors that Negatively Affect Performance of Imitation Learning for Autonomous Driving

Journal of Robotics and Control (JRC) · Vol. 5 No. 1 (2024) · hlm. 239–252

DOI
10.18196/jrc.v5i1.20371
ISSN
2715-5072, 2715-5056
Terbit
2024-01-29
Penerbit
Universitas Muhammadiyah Yogyakarta
Bahasa
eng

Abstrak

Conditional imitation learning (CIL) has proven superior to other autonomous driving (AD) algorithms. However, its performance evaluation through physical implementations is still limited. This work contributes a systematic evaluation to identify key factors potentially improving its performance. It modified convolutional neural network parameter values, such as reducing the number of filter channels and neuron units, and implemented the model into a vision-based autonomous vehicle (AV). The AV has front-wheel steering with an Ackermann mechanism since it is commonly used by passenger cars. Using the Inertia Measurement Unit, we measured the vehicle’s location and yaw angle along the experimental route. The AV had to move autonomously through new road sectors in the morning, afternoon, and night. First, an overall performance evaluation was carried out. The results showed a 99% success rate from 648 evaluation experiments under different conditions in which the 1% failure rate happened at new intersections. Then, a turning performance evaluation was conducted to identify key factors leading to failure at new intersections. They include fast speed, dazzling light reflection, late navigation command change instant, and the untrained turning driving pattern. The AV never failed while driving on the trained routes. It had a 100% success rate when driving slower, even under various lighting conditions and at various driving patterns, including untrained intersections. Although this study is limited to identifying key factors at three constant speeds, the results become the foundation for future research to improve CIL performance for AD, including by incorporating multimodal fusion and multi-route networks.

Kata kunci

Jaringan kolaborasi para penulis

16 penulis · 36 tautan kepenulisan bersama · 26 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Universitas Airlangga
  • Institut Teknologi Sepuluh Nopember
  • Sanata Dharma University
  • National Research and Innovation Agency
  • The University of Tokyo
  • Indonesian Institute of Sciences
  • Bandung Institute of Technology
  • Organisasi lain
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Nalita RusliUniversitas Islam Negeri Ar-Raniry1
Muhammad Turhan YaniPoliteknik Pelayaran Malahayati1
Dita Maria VirginiaSanata Dharma University1
Agustina SetiawatiSanata Dharma University1
Prisma MegantoroUniversitas Airlangga1
Lilik Jamilatul AwalinUniversitas Airlangga1
I Nyoman SutantraInstitut Teknologi Sepuluh Nopember1
Yoga Uta NugrahaInstitut Teknologi Sepuluh Nopember1
Indra SidhartaInstitut Teknologi Sepuluh Nopember1
Agus MukhlisinUniversitas Airlangga1
Asep NugrohoAfiliasi tidak diketahui1
Latif RozaqiAfiliasi tidak diketahui1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) https://journal.umy.ac.id/index.php/jrc/oai, pertama di-harvest 9 Nov 2026, terakhir terlihat 9 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">Key Factors that Negatively Affect Performance of Imitation Learning for Autonomous Driving</dc:title>
	<dc:creator>Rijanto, Estiko</dc:creator>
	<dc:creator>Changgraini, Nelson</dc:creator>
	<dc:creator>Saputra, Roni Permana</dc:creator>
	<dc:creator>Abidin, Zainal</dc:creator>
	<dc:subject xml:lang="en-US">Autonomous Driving</dc:subject>
	<dc:subject xml:lang="en-US">Convolutional Neural Networks</dc:subject>
	<dc:subject xml:lang="en-US">Front-Wheel Steering</dc:subject>
	<dc:subject xml:lang="en-US">Imitation Learning.</dc:subject>
	<dc:description xml:lang="en-US">Conditional imitation learning (CIL) has proven superior to other autonomous driving (AD) algorithms. However, its performance evaluation through physical implementations is still limited. This work contributes a systematic evaluation to identify key factors potentially improving its performance. It modified convolutional neural network parameter values, such as reducing the number of filter channels and neuron units, and implemented the model into a vision-based autonomous vehicle (AV). The AV has front-wheel steering with an Ackermann mechanism since it is commonly used by passenger cars. Using the Inertia Measurement Unit, we measured the vehicle’s location and yaw angle along the experimental route. The AV had to move autonomously through new road sectors in the morning, afternoon, and night. First, an overall performance evaluation was carried out. The results showed a 99% success rate from 648 evaluation experiments under different conditions in which the 1% failure rate happened at new intersections. Then, a turning performance evaluation was conducted to identify key factors leading to failure at new intersections. They include fast speed, dazzling light reflection, late navigation command change instant, and the untrained turning driving pattern. The AV never failed while driving on the trained routes. It had a 100% success rate when driving slower, even under various lighting conditions and at various driving patterns, including untrained intersections. Although this study is limited to identifying key factors at three constant speeds, the results become the foundation for future research to improve CIL performance for AD, including by incorporating multimodal fusion and multi-route networks.</dc:description>
	<dc:publisher xml:lang="en-US">Universitas Muhammadiyah Yogyakarta</dc:publisher>
	<dc:date>2024-01-29</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.umy.ac.id/index.php/jrc/article/view/20371</dc:identifier>
	<dc:identifier>10.18196/jrc.v5i1.20371</dc:identifier>
	<dc:source xml:lang="en-US">Journal of Robotics and Control (JRC); Vol. 5 No. 1 (2024); 239-252</dc:source>
	<dc:source>2715-5072</dc:source>
	<dc:source>2715-5056</dc:source>
	<dc:source>10.18196/jrc.v5i1</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journal.umy.ac.id/index.php/jrc/article/view/20371/8943</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2024 Estiko Rijanto, Nelson Changgraini, Roni Permana Saputra, Zainal Abidin</dc:rights>
</oai_dc:dc>