AlignDrive: Aligned Lateral-Longitudinal Planning for End-to-End Autonomous Driving

TL;DR

AlignDrive addresses the coordination gap between lateral and longitudinal planning in end-to-end autonomous driving by conditioning longitudinal planning on a predicted drive path and predicting longitudinal displacements along that path. The method introduces a cascaded framework with a Drive Path Predictor, Planning-oriented Data Augmentation, and a Longitudinal Planning Module, leveraging cross-attention and path-aware anchor regression to enforce spatial consistency and collision awareness. A planning-oriented augmentation strategy simulates safety-critical events by inserting agents and relabeling longitudinal targets, improving robustness in interactive scenarios. Evaluations on Bench2Drive show state-of-the-art driving score and low collision rates, with ablations validating the contribution of path conditioning, displacement-based planning, and augmentation.

Abstract

End-to-end autonomous driving has rapidly progressed, enabling joint perception and planning in complex environments. In the planning stage, state-of-the-art (SOTA) end-to-end autonomous driving models decouple planning into parallel lateral and longitudinal predictions. While effective, this parallel design can lead to i) coordination failures between the planned path and speed, and ii) underutilization of the drive path as a prior for longitudinal planning, thus redundantly encoding static information. To address this, we propose a novel cascaded framework that explicitly conditions longitudinal planning on the drive path, enabling coordinated and collision-aware lateral and longitudinal planning. Specifically, we introduce a path-conditioned formulation that explicitly incorporates the drive path into longitudinal planning. Building on this, the model predicts longitudinal displacements along the drive path rather than full 2D trajectory waypoints. This design simplifies longitudinal reasoning and more tightly couples it with lateral planning. Additionally, we introduce a planning-oriented data augmentation strategy that simulates rare safety-critical events, such as vehicle cut-ins, by adding agents and relabeling longitudinal targets to avoid collision. Evaluated on the challenging Bench2Drive benchmark, our method sets a new SOTA, achieving a driving score of 89.07 and a success rate of 73.18%, demonstrating significantly improved coordination and safety

Figures (7)

• Figure 1: (a) Drive path (black), trajectory (blue), and longitudinal displacement (red). Path waypoints are sampled spatially, trajectory waypoints temporally, and displacements represent traveled distance along the path at fixed time intervals. (b) Comparison of E2E paradigms. Parallel planning predicts the drive path and longitudinal trajectory independently, which can lead to potential coordination inconsistencies. In the example on the right, the independently predicted longitudinal trajectory is collision-free by itself, but applying its speed along a separately predicted lateral path could cause a collision. In contrast, our cascaded paradigm first predicts the drive path and then regresses path-conditioned longitudinal displacements. With the path prior, the model identifies the potential conflict and outputs shorter displacements, yielding to avoid collision. Perception inputs are omitted for clarity.
• Figure 2: Overview of the proposed AlignDrive system, which consists of three components. The Drive Path Predictor refines queries through cross-attention with image features to encode the drive path, maps, and agents. The Planning-oriented Data Augmentation enriches scenarios by inserting additional agents and relabeling longitudinal displacements. Finally, the Longitudinal Planning Module predicts forward displacements along the drive path; combined with the path, these displacements yield the final trajectory that is both collision-aware and spatially consistent. On the right side of the figure, the black numbers denote the scores of predicted drive paths, while the red numbers represent the scores of the corresponding longitudinal planning for each drive path.
• Figure 3: (a) Planning-oriented augmentation. Non-threatening agents are inserted at a distance with unchanged GT displacements, while threatening agents are placed nearby and cause adaptive shortening of GT displacements. (b) Representation encoding. Inserted agents are projected into future positions, transformed to corner representations, and encoded via a Fourier encoder (top). Reference points are sampled by displacement anchors and encoded with MLPs. For clarity, although multiple drive paths are predicted in practice, only one representative path is illustrated here. (bottom)
• Figure 4: Effect of planning-oriented data augmentation on planning performance. All augmented variants ($p=0.1,0.2,0.3,0.4$) outperform the no-augmentation baseline.
• Figure 5: Red points are predicted drive paths, while blue points show longitudinal planning outputs (trajectory waypoints for the baseline, displacement squences for ours). Relevant vehicles are highlighted in green. The baseline collides with cross-traffic, while our method avoids it.