End-to-end autonomous driving is a fully differentiable machine learning
system that takes raw sensor input data and other metadata as prior information
and directly outputs the ego vehicle's control signals or planned trajectories.
This paper attempts to systematically review all recent Machine Learning-based
techniques to perform this end-to-end task, including, but not limited to,
object detection, semantic scene understanding, object tracking, trajectory
predictions, trajectory planning, vehicle control, social behavior, and
communications. This paper focuses on recent fully differentiable end-to-end
reinforcement learning and deep learning-based techniques. Our paper also
builds taxonomies of the significant approaches by sub-grouping them and
showcasing their research trends. Finally, this survey highlights the open
challenges and points out possible future directions to enlighten further
research on the topic.

综述了近期基于机器学习的技术，包括但不限于目标检测、轨迹预测与强化学习，以及对其进行分类和研究趋势，同时指出了该领域的挑战和未来研究方向。

基于深度学习的端到端自动驾驶：系统性综述

End-to-end Autonomous Driving using Deep Learning: A Systematic Review

Accurate and robust trajectory predictions of road users are needed to enable
safe automated driving. To do this, machine learning models are often used,
which can show erratic behavior when presented with previously unseen inputs.
In this work, two environment-aware models (MotionCNN and MultiPath++) and two
common baselines (Constant Velocity and an LSTM) are benchmarked for robustness
against various perturbations that simulate functional insufficiencies observed
during model deployment in a vehicle: unavailability of road information, late
detections, and noise. Results show significant performance degradation under
the presence of these perturbations, with errors increasing up to +1444.8\% in
commonly used trajectory prediction evaluation metrics. Training the models
with similar perturbations effectively reduces performance degradation, with
error increases of up to +87.5\%. We argue that despite being an effective
mitigation strategy, data augmentation through perturbations during training
does not guarantee robustness towards unforeseen perturbations, since
identification of all possible on-road complications is unfeasible.
Furthermore, degrading the inputs sometimes leads to more accurate predictions,
suggesting that the models are unable to learn the true relationships between
the different elements in the data.

本研究旨在评估几种常见基线以及两种环境感知模型在自动驾驶中进行准确且稳健的车道预测的表现，结果发现训练过程中加入与实际部署场景相似的扰动可以有效减少性能下降，但仍无法保证对未知的干扰具有鲁棒性，甚至有时降低输入噪声反而有助于提高预测准确性。

用于自动驾驶的道路用户轨迹预测模型的鲁棒性基准测试

Robustness Benchmark of Road User Trajectory Prediction Models for  Automated Driving

With the increasing availability and affordability of personal robots, they
will no longer be confined to large corporate warehouses or factories but will
instead be expected to operate in less controlled environments alongside larger
groups of people. In addition to ensuring safety and efficiency, it is crucial
to minimize any negative psychological impact robots may have on humans and
follow unwritten social norms in these situations. Our research aims to develop
a model that can predict the movements of pedestrians and perceptually-social
groups in crowded environments. We introduce a new Social Group Long Short-term
Memory (SG-LSTM) model that models human groups and interactions in dense
environments using a socially-aware LSTM to produce more accurate trajectory
predictions. Our approach enables navigation algorithms to calculate
collision-free paths faster and more accurately in crowded environments.
Additionally, we also release a large video dataset with labeled pedestrian
groups for the broader social navigation community. We show comparisons with
different metrics on different datasets (ETH, Hotel, MOT15) and different
prediction approaches (LIN, LSTM, O-LSTM, S-LSTM) as well as runtime
performance.

本研究开发了一个模型用于预测人群和人群之间的交互，在拥挤的环境下使用 SG-LSTM 模型以更准确地预测轨迹，同时提供一个标记了行人组的大型视频数据集。