Autonomous vehicle navigation in shared pedestrian environments requires the ability to predict future crowd motion both accurately and with minimal delay. Understanding the uncertainty of the prediction is also crucial. Most existing approaches however can only estimate uncertainty through repeated sampling of generative models. Additionally, most current predictive models are trained on datasets that assume complete observability of the crowd using an aerial view. These are generally not representative of real-world usage from a vehicle perspective, and can lead to the underestimation of uncertainty bounds when the on-board sensors are occluded. Inspired by prior work in motion prediction using spatio-temporal graphs, we propose a novel Graph Convolutional Neural Network (GCNN)-based approach, Attentional-GCNN, which aggregates information of implicit interaction between pedestrians in a crowd by assigning attention weight in edges of the graph. Our model can be trained to either output a probabilistic distribution or faster deterministic prediction, demonstrating applicability to autonomous vehicle use cases where either speed or accuracy with uncertainty bounds are required. To further improve the training of predictive models, we propose an automatically labelled pedestrian dataset collected from an intelligent vehicle platform representative of real-world use. Through experiments on a number of datasets, we show our proposed method achieves an improvement over the state of art by 10% Average Displacement Error (ADE) and 12% Final Displacement Error (FDE) with fast inference speeds.

中文翻译：

---

Attentional-GCNN：针对通用自动车辆使用案例的自适应行人轨迹预测

在共享的行人环境中进行自动驾驶导航需要能够准确且以最小的延迟来预测未来人群的运动。理解预测的不确定性也至关重要。但是，大多数现有方法只能通过对生成模型进行重复采样来估计不确定性。另外，大多数当前的预测模型都在假设使用鸟瞰图可完全观察人群的数据集上进行训练。从车辆的角度来看，这些通常不能代表实际使用情况，当封闭车载传感器时，可能会导致不确定性范围的低估。受先前使用时空图进行运动预测的工作启发，我们提出了一种基于图卷积神经网络（GCNN）的新颖方法Attentional-GCNN，通过在图表边缘分配注意力权重来汇总人群中行人之间的隐式交互信息。我们的模型可以进行训练，以输出概率分布或更快的确定性预测，从而证明了其在需要速度或精度以及不确定性范围的自动驾驶汽车使用案例中的适用性。为了进一步改善预测模型的训练，我们提出了一个自动标记的行人数据集，该数据集是从代表实际用途的智能车辆平台收集的。通过在多个数据集上进行的实验，我们证明了我们提出的方法以最快的推理速度实现了10％的平均位移误差（ADE）和12％的最终位移误差（FDE）的改进。