C$^{2}$INet：利用先验感知的持续因果干预实现增量轨迹预测
C$^{2}$INet: Realizing Incremental Trajectory Prediction with Prior-Aware Continual Causal Intervention
AI总结：
本文提出C$^{2}$INet方法，在持续学习框架下通过变分推断对齐环境先验与混杂因子后验、结合记忆队列持续去偏和剪枝策略，实现可泛化的多智能体轨迹预测并缓解灾难性遗忘。
摘要：
复杂场景中多智能体的轨迹预测对于自动驾驶等应用至关重要。然而，现有方法往往忽视环境偏差，导致泛化能力较差。此外，硬件限制制约了跨环境大规模数据的使用，而持续学习设置进一步加剧了灾难性遗忘的挑战。为解决这些问题，我们提出了持续因果干预（C$^{2}$INet）方法，用于在持续学习框架内实现可泛化的多智能体轨迹预测。利用变分推断，我们在潜在空间中将环境相关先验与混杂因子的后验估计器对齐，从而干预影响轨迹表示的因果关联。此外，我们利用记忆队列存储各种场景下的最优变分先验，确保在增量任务训练过程中持续去偏。所提出的C$^{2}$INet增强了对多样化任务的适应性，同时保留先前任务信息以防止灾难性遗忘。该方法还引入了剪枝策略以缓解过拟合。在三个真实和合成复杂数据集上与最先进方法的对比评估表明，我们提出的方法持续取得可靠的预测性能，有效缓解了不同场景特有的混杂因素。这凸显了我们的方法在实际应用中的实用价值。
英文摘要：
Trajectory prediction for multi-agents in complex scenarios is crucial for applications like autonomous driving. However, existing methods often overlook environmental biases, which leads to poor generalization. Additionally, hardware constraints limit the use of large-scale data across environments, and continual learning settings exacerbate the challenge of catastrophic forgetting. To address these issues, we propose the Continual Causal Intervention (C$^{2}$INet) method for generalizable multi-agent trajectory prediction within a continual learning framework. Using variational inference, we align environment-related prior with posterior estimator of confounding factors in the latent space, thereby intervening in causal correlations that affect trajectory representation. Furthermore, we store optimal variational priors across various scenarios using a memory queue, ensuring continuous debiasing during incremental task training. The proposed C$^{2}$INet enhances adaptability to diverse tasks while preserving previous task information to prevent catastrophic forgetting. It also incorporates pruning strategies to mitigate overfitting. Comparative evaluations on three real and synthetic complex datasets against state-of-the-art methods demonstrate that our proposed method consistently achieves reliable prediction performance, effectively mitigating confounding factors unique to different scenarios. This highlights the practical value of our method for real-world applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
