Eric Leong

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2022-79

May 12, 2022

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2022/EECS-2022-79.pdf

We aim to bridge the gap between end-to-end learning and traditional pipeline-based approaches for autonomous vehicles (AVs). In this work, we replace the traditional planning and control algorithms of modular approaches with an end-to-end learned policy, developing a hybrid of the two approaches. Our learned policy takes a bird's-eye-view representation of the world as input, and produces control actions such as braking, steering, and acceleration. To support the development of this learned policy, we introduce caRLot, a novel OpenAI gym environment that builds atop the open-source Pylot AV platform to provide configurable abstractions in addition to an interface with the CARLA simulator. We use caRLot to learn a model-free reinforcement learning policy that replaces planning and control, and compare its performance and runtime against several state-of-the-art approaches. We find that our hybrid approach has a notable improvement in runtime over a modular driving system, while having a significant advantage in interpretability over end-to-end systems.

Advisors: Joseph Gonzalez

---

BibTeX citation:

@mastersthesis{Leong:EECS-2022-79,
    Author= {Leong, Eric},
    Title= {Bridging the Gap Between Modular and End-to-end Autonomous Driving Systems},
    School= {EECS Department, University of California, Berkeley},
    Year= {2022},
    Month= {May},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2022/EECS-2022-79.html},
    Number= {UCB/EECS-2022-79},
    Abstract= {We aim to bridge the gap between end-to-end learning and traditional pipeline-based approaches for autonomous vehicles (AVs). In this work, we replace the traditional planning and control algorithms of modular approaches with an end-to-end learned policy, developing a hybrid  of the two approaches. Our learned policy takes a bird's-eye-view representation of the world as input, and produces control actions such as braking, steering, and acceleration. To support the development of this learned policy, we introduce caRLot, a novel OpenAI gym environment that builds atop the open-source Pylot AV platform to provide configurable abstractions in addition to an interface with the CARLA simulator. We use caRLot to learn a model-free reinforcement learning policy that replaces planning and control, and compare its performance and runtime against several state-of-the-art approaches. We find that our hybrid approach has a notable improvement in runtime over a modular driving system, while having a significant advantage in interpretability over end-to-end systems.},
}

EndNote citation:

%0 Thesis
%A Leong, Eric 
%T Bridging the Gap Between Modular and End-to-end Autonomous Driving Systems
%I EECS Department, University of California, Berkeley
%D 2022
%8 May 12
%@ UCB/EECS-2022-79
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2022/EECS-2022-79.html
%F Leong:EECS-2022-79