Autoregressive Meta-Actions for Unified Controllable Trajectory Generation

TL;DR

This paper introduces Autoregressive Meta-Actions, a novel framework for controllable trajectory generation in autonomous driving that aligns meta-actions with trajectory segments at a frame level, improving task coherence and adaptability.

Contribution

It proposes a unified, frame-level meta-action approach integrated into autoregressive models, along with a staged pre-training process for better motion and decision control.

Findings

Enhanced trajectory adaptivity and responsiveness.

Reduced complexity through frame-level meta-actions.

Validated effectiveness on experimental datasets.

Abstract

Controllable trajectory generation guided by high-level semantic decisions, termed meta-actions, is crucial for autonomous driving systems. A significant limitation of existing frameworks is their reliance on invariant meta-actions assigned over fixed future time intervals, causing temporal misalignment with the actual behavior trajectories. This misalignment leads to irrelevant associations between the prescribed meta-actions and the resulting trajectories, disrupting task coherence and limiting model performance. To address this challenge, we introduce Autoregressive Meta-Actions, an approach integrated into autoregressive trajectory generation frameworks that provides a unified and precise definition for meta-action-conditioned trajectory prediction. Specifically, We decompose traditional long-interval meta-actions into frame-level meta-actions, enabling a sequential interplay between autoregressive meta-action prediction and meta-action-conditioned trajectory generation. This decomposition ensures strict alignment between each trajectory segment and its corresponding meta-action, achieving a consistent and unified task formulation across the entire trajectory span and significantly reducing complexity. Moreover, we propose a staged pre-training process to decouple the learning of basic motion dynamics from the integration of high-level decision control, which offers flexibility, stability, and modularity. Experimental results validate our framework's effectiveness, demonstrating improved trajectory adaptivity and responsiveness to dynamic decision-making scenarios. We provide the video document and dataset, which are available at https://arma-traj.github.io/.