arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.14570cs.CVcs.RO
收藏

DICE:用于轨迹预测的带评分的多样化扩散模型

DICE: Diverse Diffusion Model with Scoring for Trajectory Prediction

University of Toronto(多伦多大学);Huawei(华为);Noah’s Ark Laboratory, Huawei(华为诺亚方舟实验室)

Younwoo Choi, Ray Coden Mercurius, Soheil Mohamad Alizadeh Shabestary, Amir Rasouli

AI总结:

提出一种基于扩散模型的高效轨迹预测框架DICE,通过高效采样机制最大化采样轨迹数量以提升精度并保持实时推理,同时引入评分机制选择最合理轨迹,在UCY/ETH和nuScenes基准上达到SOTA性能。

摘要:

动态环境中的道路使用者轨迹预测对于自动驾驶等各种应用来说是一项具有挑战性但至关重要的任务。该领域的主要挑战之一是,由于智能体未知且多样的意图,导致未来轨迹具有多模态性质。扩散模型在捕捉预测任务中的这种随机性方面已被证明非常有效。然而,这些模型涉及许多计算成本高昂的去噪步骤和采样操作,使其不太适合实时安全关键型应用。为此,我们提出了一种新颖的框架,该框架以计算高效的方式利用扩散模型来预测未来轨迹。为了最小化迭代采样中的计算瓶颈,我们采用了一种高效的采样机制,该机制允许我们最大化采样轨迹的数量以提高准确性,同时将推理时间保持在实时范围内。此外,我们提出了一种评分机制,通过分配相对排名来选择最合理的轨迹。我们通过在常见的行人(UCY/ETH)和自动驾驶(nuScenes)基准数据集上进行实证评估,展示了我们方法的有效性,我们的模型在多个子集和指标上达到了最先进的性能。

英文摘要:

Road user trajectory prediction in dynamic environments is a challenging but crucial task for various applications, such as autonomous driving. One of the main challenges in this domain is the multimodal nature of future trajectories stemming from the unknown yet diverse intentions of the agents. Diffusion models have shown to be very effective in capturing such stochasticity in prediction tasks. However, these models involve many computationally expensive denoising steps and sampling operations that make them a less desirable option for real-time safety-critical applications. To this end, we present a novel framework that leverages diffusion models for predicting future trajectories in a computationally efficient manner. To minimize the computational bottlenecks in iterative sampling, we employ an efficient sampling mechanism that allows us to maximize the number of sampled trajectories for improved accuracy while maintaining inference time in real time. Moreover, we propose a scoring mechanism to select the most plausible trajectories by assigning relative ranks. We show the effectiveness of our approach by conducting empirical evaluations on common pedestrian (UCY/ETH) and autonomous driving (nuScenes) benchmark datasets on which our model achieves state-of-the-art performance on several subsets and metrics.

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。

↑