Yasin Sonmez and Hanna Krasowski and Murat Arcak

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2025-14

April 29, 2025

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2025/EECS-2025-14.pdf

Imitation learning is a promising approach for training autonomous vehicles (AV) to navigate complex traffic environments by mimicking expert driver behaviors. While existing imitation learning frameworks focus on leveraging expert demonstrations, they often overlook the potential of additional complex driving data from surrounding traffic participants. In this paper, we propose a data augmentation strategy that enhances imitation learning by leveraging the observed trajectories of nearby vehicles, captured by the AV’s sensors, as additional expert demonstrations. We introduce a vehicle selection sampling strategy that prioritizes informative and diverse driving behaviors, contributing to a richer and more diverse dataset for training. We evaluate our approach using the state-of-the-art learning-based planning method PLUTO on the nuPlan dataset and demonstrate that our augmentation method leads to improved performance in complex driving scenarios. Specifically, our method reduces collision rates and improves safety metrics compared to the baseline. Notably, even when using only 10% of the original dataset, our method matches or exceeds the performance of the full dataset, with improved collision rates. Our findings highlight the importance of leveraging diverse real-world trajectory data in imitation learning and provide insights into data augmentation strategies for autonomous driving.

Advisors: Murat Arcak

---

BibTeX citation:

@mastersthesis{Sonmez:EECS-2025-14,
    Author= {Sonmez, Yasin and Krasowski, Hanna and Arcak, Murat},
    Title= {Learning to Drive by Imitating Surrounding Vehicles},
    School= {EECS Department, University of California, Berkeley},
    Year= {2025},
    Month= {Apr},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2025/EECS-2025-14.html},
    Number= {UCB/EECS-2025-14},
    Abstract= {Imitation learning is a promising approach for training autonomous vehicles (AV) to navigate complex traffic environments by mimicking expert driver behaviors. While existing imitation learning frameworks focus on leveraging expert demonstrations, they often overlook the potential of additional complex driving data from surrounding traffic participants. In this paper, we propose a data augmentation strategy that enhances imitation learning by leveraging the observed trajectories of nearby vehicles, captured by the AV’s sensors, as additional expert demonstrations. We introduce a vehicle selection sampling strategy that prioritizes informative and diverse driving behaviors, contributing to a richer and more diverse dataset for training. We evaluate our approach using the state-of-the-art learning-based planning method PLUTO on the nuPlan dataset and demonstrate that our augmentation method leads to improved performance in complex driving scenarios. Specifically, our method reduces collision rates and improves safety metrics compared to the baseline. Notably, even when using only 10% of the original dataset, our method matches or exceeds the performance of the full dataset, with improved collision rates. Our findings highlight the importance of leveraging diverse real-world trajectory data in imitation learning and provide insights into data augmentation strategies for autonomous driving.},
}

EndNote citation:

%0 Thesis
%A Sonmez, Yasin 
%A Krasowski, Hanna 
%A Arcak, Murat 
%T Learning to Drive by Imitating Surrounding Vehicles
%I EECS Department, University of California, Berkeley
%D 2025
%8 April 29
%@ UCB/EECS-2025-14
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2025/EECS-2025-14.html
%F Sonmez:EECS-2025-14