Training Autonomous Vehicles in Carla model using Augmented Random Search Algorithm

Riyanto Riyanto, Abdul Azis, Tarwoto Tarwoto, Wei Li Deng

Abstract


CARLA is an open source simulator for autonomous driving research. CARLA has been developed from scratch to support the development, training and validation of autonomous driving systems. In addition to open source code and protocols, CARLA provides open digital assets (urban layouts, buildings, vehicles) that are created for this purpose and can be used freely. We use CARLA to study the performance of Augmented Random Search (ARS) to autonomous driving: a classic modular pipeline, an end-to-end model trained via imitation learning, and an end-to-end model trained via reinforcement learning. Test the ability of the Augmented Random Search (ARS) algorithm to train driverless cars on data collected from the front cameras per car. In this study, a framework that can be used to train driverless car policy using ARS in Carla will be built. Although effective policies were not achieved after the first round of training, many insights on how to improve these outcomes in the future have been obtained.

Article Metrics

Abstract: 64 Viewers PDF: 29 Viewers

Keywords


CARLA; ARS; Data Mining; Autonomous driving;

Full Text:

PDF


References


A. R. Conn, N. I. M. Gould, and P. L. Toint, “Globally convergent augmented Lagrangian algorithm for optimization with general constraints and simple bounds,” SIAM J. Numer. Anal., vol. 28, no. 2, pp. 545–572, 1991, doi: 10.1137/0728030.

M. Geng, K. Xu, B. Ding, H. Wang, and L. Zhang, “Learning data augmentation policies using augmented random search,” arXiv, 2018.

A. K. Tiwari and S. V. Nadimpalli, “Augmented Random Search for Quadcopter Control: An alternative to Reinforcement Learning,” arXiv, 2019, doi: 10.5815/ijitcs.2019.11.03.

S. Tirumala et al., “Gait library synthesis for quadruped robots via augmented random search,” arXiv, 2019.

V. Kurenkov, H. Hamed, and S. Savin, “Learning Stabilizing Control Policies for a Tensegrity Hopper with Augmented Random Search,” arXiv, no. 19, 2020.

R. B. Gramacy et al., “Modeling an augmented lagrangian for blackbox constrained optimization,” Technometrics, vol. 58, no. 1, pp. 1–11, 2016, doi: 10.1080/00401706.2015.1014065.

H. Teimourzadeh, F. Jabari, and B. Mohammadi-Ivatloo, “An augmented group search optimization algorithm for optimal cooling-load dispatch in multi-chiller plants,” Comput. Electr. Eng., vol. 85, no. xxxx, p. 106434, 2020, doi: 10.1016/j.compeleceng.2019.07.020.

Y. Shang et al., “Stochastic dispatch of energy storage in microgrids: A reinforcement learning approach incorporated with MCTS,” arXiv, pp. 1–11, 2019.

Maiti and Bidinger, “COMBINING RESULTS FROM AUGMENTED DESIGNS OVER SITES,” J. Chem. Inf. Model., vol. 53, no. 9, pp. 1689–1699, 1981.

X. Chen, P. Wei, W. Ke, Q. Ye, and J. J. B, “Forecasting Events Using an Augmented Hidden Conditional Random Field,” vol. 9006, no. November, pp. 354–365, 2015, doi: 10.1007/978-3-319-16817-3.

B. I. Kim, H. Li, and A. L. Johnson, “An augmented large neighborhood search method for solving the team orienteering problem,” Expert Syst. Appl., vol. 40, no. 8, pp. 3065–3072, 2013, doi: 10.1016/j.eswa.2012.12.022.

H. Li, K. M. Lam, and M. Wang, “Image super-resolution via feature-augmented random forest,” Signal Process. Image Commun., vol. 72, no. 2, pp. 25–34, 2019, doi: 10.1016/j.image.2018.12.001.

Z. Liu et al., “Subgraph-augmented path embedding for semantic user search on heterogeneous social network,” Web Conf. 2018 - Proc. World Wide Web Conf. WWW 2018, pp. 1613–1622, 2018, doi: 10.1145/3178876.3186073.

I. V. Tetko, P. Karpov, R. Van Deursen, and G. Godin, “State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis,” Nat. Commun., vol. 11, no. 1, pp. 1–24, 2020, doi: 10.1038/s41467-020-19266-y.

H. Akeb, M. Hifi, and S. Negre, “An augmented beam search-based algorithm for the circular open dimension problem,” Comput. Ind. Eng., vol. 61, no. 2, pp. 373–381, 2011, doi: 10.1016/j.cie.2011.02.009.

Y. Zhang, A. Albarghouthi, and L. D’Antoni, “Robustness to Programmable String Transformations via Augmented Abstract Training,” arXiv, 2020.

L. Costa, I. A. C. P. Espírito Santo, and E. M. G. P. Fernandes, “A hybrid genetic pattern search augmented Lagrangian method for constrained global optimization,” Appl. Math. Comput., vol. 218, no. 18, pp. 9415–9426, 2012, doi: 10.1016/j.amc.2012.03.025.

Henderi and T. Wahyuningsih, “Comparison of Min-Max normalization and Z-Score Normalization in the K-nearest neighbor (kNN) Algorithm to Test the Accuracy of Types of Breast Cancer,” IJIIS Int. J. Informatics Inf. Syst., vol. 4, no. 1, pp. 13–20, 2021, doi: 10.47738/ijiis.v4i1.73.

C. J. M. Liang et al., “AutoSys: The design and operation of learning-augmented systems,” Proc. 2020 USENIX Annu. Tech. Conf. ATC 2020, pp. 323–336, 2020.


Refbacks

  • There are currently no refbacks.



Barcode

Journal of Applied Data Science

2723-6471 (Online)
Published by Bright Publisher
Puri Mersi Baru, Jl.Martadireja II, Gang Sitihingil 3 Blok A No 2, Purwokerto Timur, Jawa Tengah
Website : bright-journal.org/JADS
Email : info@bright-journal.org

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0