iPad: Iterative Proposal-centric End-to-End Autonomous Driving

TL;DR

iPad introduces an iterative, proposal-centric framework for end-to-end autonomous driving that enhances planning accuracy and efficiency by focusing on candidate future plans and multi-view data fusion.

Contribution

The paper presents ProFormer, a novel BEV encoder that iteratively refines proposals, and auxiliary tasks that improve planning with minimal overhead, advancing E2E driving methods.

Findings

Achieves state-of-the-art performance on NAVSIM and CARLA Bench2Drive.

Significantly improves planning efficiency over prior methods.

Demonstrates robustness and accuracy in complex driving scenarios.

Abstract

End-to-end (E2E) autonomous driving systems offer a promising alternative to traditional modular pipelines by reducing information loss and error accumulation, with significant potential to enhance both mobility and safety. However, most existing E2E approaches directly generate plans based on dense bird's-eye view (BEV) grid features, leading to inefficiency and limited planning awareness. To address these limitations, we propose iterative Proposal-centric autonomous driving (iPad), a novel framework that places proposals - a set of candidate future plans - at the center of feature extraction and auxiliary tasks. Central to iPad is ProFormer, a BEV encoder that iteratively refines proposals and their associated features through proposal-anchored attention, effectively fusing multi-view image data. Additionally, we introduce two lightweight, proposal-centric auxiliary tasks - mapping and prediction - that improve planning quality with minimal computational overhead. Extensive experiments on the NAVSIM and CARLA Bench2Drive benchmarks demonstrate that iPad achieves state-of-the-art performance while being significantly more efficient than prior leading methods.