arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2302.00735cs.ROcs.AIcs.LG
收藏

MTP-GO:基于图的神经 ODE 概率多智能体轨迹预测

MTP-GO: Graph-Based Probabilistic Multi-Agent Trajectory Prediction with Neural ODEs

Linköping University(林雪平大学);Lund University(隆德大学)

Theodor Westny, Joel Oskarsson, Björn Olofsson, Erik Frisk

AI总结:

提出 MTP-GO,结合时间图神经网络、神经 ODE、混合密度网络与 Kalman 滤波实现多智能体多模态概率轨迹预测,并在多数据集指标上超越现有方法。

摘要:

实现具有弹性的自主运动规划,需要对周围道路使用者的未来行为作出鲁棒预测。针对这一需求及相关挑战,我们提出了名为 MTP-GO 的模型。该模型利用时间图神经网络对场景进行编码,为底层运动模型生成输入。运动模型采用神经常微分方程实现,其中状态转移函数与模型其余部分共同学习。通过结合混合密度网络与 Kalman 滤波的概念,模型获得多模态概率预测。结果展示了所提模型在多个数据集上的预测能力,并在多项指标上优于若干最先进方法。

英文摘要:

Enabling resilient autonomous motion planning requires robust predictions of surrounding road users' future behavior. In response to this need and the associated challenges, we introduce our model titled MTP-GO. The model encodes the scene using temporal graph neural networks to produce the inputs to an underlying motion model. The motion model is implemented using neural ordinary differential equations where the state-transition functions are learned with the rest of the model. Multimodal probabilistic predictions are obtained by combining the concept of mixture density networks and Kalman filtering. The results illustrate the predictive capabilities of the proposed model across various data sets, outperforming several state-of-the-art methods on a number of 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。

↑