Analysis of a Modular Autonomous Driving Architecture: The Top Submission to CARLA Leaderboard 2.0 Challenge
This work addresses autonomous driving challenges for researchers and practitioners, but it is incremental as it builds on existing modular approaches with specific enhancements.
The paper tackled autonomous driving by presenting a modular architecture that won first place in the CARLA Leaderboard 2.0 challenge, using language-assisted perception and inverse reinforcement learning to improve reliability in traffic scenarios.
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.