用轻量Transformer生成高精度驾驶轨迹，支持复杂路线规划。
Efficient Virtuoso: A Latent Diffusion Transformer Model for Goal-Conditioned Trajectory Planning
- 两阶段归一化+低维潜空间，提升生成效率与稳定性。
- 在Waymo数据集上达0.25最小平均位移误差，性能领先。
- 多步稀疏路线比单点目标更能还原人类驾驶细节。
自主车辆规划系统需要生成多样且合理的未来轨迹分布。尽管生成模型已展现潜力，但实现高保真度、计算高效与精确控制仍是挑战。本文提出Efficient Virtuoso，一种面向目标条件的潜在扩散模型。方法引入新颖的两阶段归一化流程：先保持轨迹几何比例，再对PCA潜空间进行归一化，确保训练稳定。去噪过程在低维潜空间中通过简单MLP完成，由基于Transformer的StateEncoder融合丰富场景上下文进行条件控制。实验表明，该方法在Waymo Open Motion Dataset上取得最优表现，最小平均位移误差（minADE）为0.25。通过严谨消融实验发现：单点终点目标可解决战略模糊性，而更丰富的多步稀疏路线对实现高保真战术执行至关重要，能更贴近人类驾驶的细微行为。
原文摘要 · Abstract (English)
The ability to generate a diverse and plausible distribution of future trajectories is a critical capability for autonomous vehicle planning systems. While recent generative models have shown promise, achieving high fidelity, computational efficiency, and precise control remains a significant challenge. In this paper, we present the Efficient Virtuoso, a conditional latent diffusion model for goal-conditioned trajectory planning. Our approach introduces a novel two-stage normalization pipeline that first scales trajectories to preserve their geometric aspect ratio and then normalizes the resulting PCA latent space to ensure a stable training target. The denoising process is performed efficiently in this low-dimensional latent space by a simple MLP denoiser, which is conditioned on a rich scene context fused by a powerful Transformer-based StateEncoder. We demonstrate that our method achieves state-of-the-art performance on the Waymo Open Motion Dataset, achieving a minimum Average Displacement Error (minADE) of 0.25. Furthermore, through a rigorous ablation study on goal representation, we provide a key insight: while a single endpoint goal can resolve strategic ambiguity, a richer, multi-step sparse route is essential for enabling the precise, high-fidelity tactical execution that mirrors nuanced human driving behavior.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。