Abstract
Automated parking is a challenging operational domain for advanced driver assistance systems, requiring robust scene understanding and interaction reasoning. The key challenge is twofold: (i) predict multiple plausible ego intentions according to context and (ii) for each intention, predict the joint responses of surrounding agents, enabling effective what-if decision-making. However, existing methods often fall short, typically treating these interdependent problems in isolation. We propose ParkDiffusion++, which jointly learns a multi-modal ego intention predictor and an ego-conditioned multi-agent joint trajectory predictor for automated parking. Our approach makes several key contributions. First, we introduce an ego intention tokenizer that predicts a small set of discrete endpoint intentions from agent histories and vectorized map polylines. Second, we perform ego-intention-conditioned joint prediction, yielding socially consistent predictions of the surrounding agents for each possible ego intention. Third, we employ a lightweight safety-guided denoiser with different constraints to refine joint scenes during training, thus improving accuracy and safety. Fourth, we propose counterfactual knowledge distillation, where an EMA teacher refined by a frozen safety-guided denoiser provides pseudo-targets that capture how agents react to alternative ego intentions. Extensive evaluations demonstrate that ParkDiffusion++ achieves state-of-the-art performance on the Dragon Lake Parking (DLP) dataset and the Intersections Drone (inD) dataset. Importantly, qualitative what-if visualizations show that other agents react appropriately to different ego intentions.
Abstract (translated)
自动泊车是高级驾驶辅助系统的一个具有挑战性的操作领域,需要强大的场景理解和交互推理能力。主要的挑战在于两个方面:(i)根据上下文预测多个合理的自身意图;(ii)对于每个意图,预测周围代理的联合响应,从而实现有效的假设情景决策制定。然而,现有的方法往往难以满足这些相互依赖的问题需求,在处理这些问题时通常将其孤立对待。 我们提出了ParkDiffusion++,这是一种同时学习多模态自身意图预测器和基于自身条件的多代理联合轨迹预测器的方法,用于自动化泊车系统。我们的方法做出了几个关键贡献: 1. 我们引入了一个自身意图编码器(ego intention tokenizer),它可以从代理历史记录和向量化的地图折线图中预测一组离散的终端意图。 2. 我们进行了基于自身意图条件下的联合预测,为每一种可能的自身意图生成周围代理的社会一致性预测结果。 3. 在训练期间,我们采用了一种轻量级的安全导向去噪器,并根据不同约束对联合场景进行细化处理,从而提高准确性和安全性。 4. 我们提出了反事实知识蒸馏技术,在这种方法中,经过冻结安全导向去噪器优化的EMA教师模型提供伪目标,捕捉代理对替代自身意图的反应方式。 广泛的评估表明,ParkDiffusion++在Dragon Lake Parking (DLP) 数据集和Intersections Drone (inD) 数据集上实现了最先进的性能。值得注意的是,从定性的假设情景可视化结果中可以看出,其他代理能够适当响应不同的自身意图变化。
URL
https://arxiv.org/abs/2602.20923