Analysis of a Modular Autonomous Driving Architecture: The Top Submission to CARLA Leaderboard 2.0 Challenge

TL;DR

This paper details the Kyber-E2E modular autonomous driving system that achieved first place in the CARLA Leaderboard 2.0 challenge 2023, emphasizing a multi-component architecture and advanced perception models.

Contribution

Introduction of a modular architecture integrating language-assisted perception and IRL for improved autonomous driving performance in challenging scenarios.

Findings

Achieved first place in CARLA Leaderboard 2.0 challenge 2023.

Demonstrated the effectiveness of language-assisted perception models.

Showed the impact of component-wise resource allocation on overall performance.

Abstract

In this paper we present the architecture of the Kyber-E2E submission to the map track of CARLA Leaderboard 2.0 Autonomous Driving (AD) challenge 2023, which achieved first place. We employed a modular architecture for our solution consists of five main components: sensing, localization, perception, tracking/prediction, and planning/control. Our solution leverages state-of-the-art language-assisted perception models to help our planner perform more reliably in highly challenging traffic scenarios. We use open-source driving datasets in conjunction with Inverse Reinforcement Learning (IRL) to enhance the performance of our motion planner. We provide insight into our design choices and trade-offs made to achieve this solution. We also explore the impact of each component in the overall performance of our solution, with the intent of providing a guideline where allocation of resources can have the greatest impact.