当前位置: X-MOL 学术IEEE Robot. Automation Lett. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Forecasting Trajectory and Behavior of Road-Agents Using Spectral Clustering in Graph-LSTMs
IEEE Robotics and Automation Letters ( IF 5.2 ) Pub Date : 2020-07-01 , DOI: 10.1109/lra.2020.3004794
Rohan Chandra , Tianrui Guan , Srujan Panuganti , Trisha Mittal , Uttaran Bhattacharya , Aniket Bera , Dinesh Manocha

We present a novel approach for traffic forecasting in urban traffic scenarios using a combination of spectral graph analysis and deep learning. We predict both the low-level information (future trajectories) as well as the high-level information (road-agent behavior) from the extracted trajectory of each road-agent. Our formulation represents the proximity between the road agents using a weighted dynamic geometric graph (DGG). We use a two-stream graph-LSTM network to perform traffic forecasting using these weighted DGGs. The first stream predicts the spatial coordinates of road-agents, while the second stream predicts whether a road-agent is going to exhibit overspeeding, underspeeding, or neutral behavior by modeling spatial interactions between road-agents. Additionally, we propose a new regularization algorithm based on spectral clustering to reduce the error margin in long-term prediction (3-5 seconds) and improve the accuracy of the predicted trajectories. Moreover, we prove a theoretical upper bound on the regularized prediction error. We evaluate our approach on the Argoverse, Lyft, Apolloscape, and NGSIM datasets and highlight the benefits over prior trajectory prediction methods. In practice, our approach reduces the average prediction error by approximately 75% over prior algorithms and achieves a weighted average accuracy of 91.2% for behavior prediction. Additionally, our spectral regularization improves long-term prediction by up to $\text{70}\%$.

中文翻译:

使用 Graph-LSTM 中的谱聚类预测道路代理的轨迹和行为

我们提出了一种结合频谱图分析和深度学习的城市交通场景交通预测新方法。我们从每个道路代理的提取轨迹中预测低级信息(未来轨迹)以及高级信息(道路代理行为)。我们的公式使用加权动态几何图 (DGG) 表示道路代理之间的接近度。我们使用双流图-LSTM 网络使用这些加权 DGG 执行流量预测。第一个流预测道路代理的空间坐标,而第二个流通过建模道路代理之间的空间交互来预测道路代理是否会表现出超速、低速或中性行为。此外,我们提出了一种基于谱聚类的新正则化算法,以减少长期预测(3-5 秒)中的误差幅度并提高预测轨迹的准确性。此外,我们证明了正则化预测误差的理论上限。我们在 Argoverse、Lyft、Apolloscape 和 NGSIM 数据集上评估了我们的方法,并强调了与先前轨迹预测方法相比的优势。在实践中,我们的方法比之前的算法减少了大约 75% 的平均预测误差,并实现了 91.2% 的行为预测加权平均准确率。此外,我们的频谱正则化将长期预测提高了 $\text{70}\%$。我们证明了正则化预测误差的理论上限。我们在 Argoverse、Lyft、Apolloscape 和 NGSIM 数据集上评估了我们的方法,并强调了与先前轨迹预测方法相比的优势。在实践中,我们的方法比之前的算法减少了大约 75% 的平均预测误差,并实现了 91.2% 的行为预测加权平均准确率。此外,我们的频谱正则化将长期预测提高了 $\text{70}\%$。我们证明了正则化预测误差的理论上限。我们在 Argoverse、Lyft、Apolloscape 和 NGSIM 数据集上评估了我们的方法,并强调了与先前轨迹预测方法相比的优势。在实践中,我们的方法比之前的算法减少了大约 75% 的平均预测误差,并实现了 91.2% 的行为预测加权平均准确率。此外,我们的频谱正则化将长期预测提高了 $\text{70}\%$。2% 用于行为预测。此外,我们的频谱正则化将长期预测提高了 $\text{70}\%$。2% 用于行为预测。此外,我们的频谱正则化将长期预测提高了 $\text{70}\%$。
更新日期:2020-07-01
down
wechat
bug