In the last article, we introduced the current dilemmas and challenges faced by Advanced Driver Assistance Systems (ADAS) and proposed a solution of ARRK. In the following, we will tell you how ARRK realizes that operation with concrete examples.
上期文章中我们介绍了高级驾驶辅助系统(ADAS)当前所面临的困境与挑战,并提出了ARRK的解决方案。下面我们将以具体实例为大家讲述ARRK是如何实现该操作的。
Example Sharing
案例分享
Example ACC(Adaptive Cruise Control ): Analyzing the data sets with regard to trajectory planning ACC(自适应巡航系统)案例:分析轨迹规划相关的数据集
The ADAS function ACC was selected as a study example. It automatically controls the acceleration and breaking of a vehicle, always maintaining sufficient distance to other road users and obstacles. To do this, the system calculates the so-called time-to-collision (TTC) for each detected object. If it drops below a defined threshold value, the vehicle reacts accordingly with deceleration. Thereby applies: The greater the speed difference between the vehicle itself and an object in front of it, the shorter the TTC and the earlier the ACC must react.
ADAS中的ACC功能被选为一个研究案例。它能自动控制车辆的加速和制动,始终与其他道路使用者和障碍物保持足够的距离。为了做到这一点,该系统为每个检测到的物体计算所谓的碰撞时间(TTC)。如果它低于一个定义的阈值,车辆就会做出相应的减速反应。适用情况为车辆本身和前面的物体之间的速度差越大,TTC越短,ACC必须越早做出反应。
Due to this correlation, on motorways, for example, the system needs to reliably detect objects at a significantly greater distance, whereas in urban environments, potential obstacles may be located at a much wider close range. But are the ADAS of the different manufacturers even capable of doing this?
由于这种关联性,例如在高速公路上,系统需要可靠地检测到距离远得多的物体,而在城市环境中,潜在的障碍物可能位于范围更宽、但距离更近的位置。但是,不同制造商的ADAS是否有能力做到这一点?
To find out, the researchers focused on trajectory planning. For the deployment location Germany, they defined three driving scenarios with different speed limits and correspondingly varying requirements for the ACC: motorway (130 km/h recommended speed), country road (max. 100 km/h) and urban traffic (max. 50 km/h).
为了找出答案,研究人员把重点放在轨迹规划上。对于德国的部署地点,他们定义了三种具有不同速度限制的驾驶场景,并相应地对ACC提出了不同的要求:高速公路(建议速度130公里/小时)、乡村公路(最高100公里/小时)和城市交通(最高50公里/小时)。
For their analysis, the researchers drew on a total of six data sets, including large models that have been used by well-known OEMs for years: ONCE, nuScenes, A2D2, LyftLevel5, Waymo and Kitti.
为了进行分析,研究人员总共借鉴了六个数据集,包括知名OEM厂商多年来一直使用的大型模型:ONCE、nuScenes、A2D2、LyftLevel5、Waymo和Kitti。
The first objective of the study was to determine the statistical distribution of the annotated objects that the system is able to identify. This involved assessing the size of the bounding boxes used for annotation, the relationship between their size and distance from each other, the distance between the vehicle and other objects as well as their relative position distribution on the sensor and the optical flow of the image sequences.
该研究的第一个目标是确定系统能够识别的标注对象的统计分布。这涉及到评估用于标注的边界框的大小,它们的大小和彼此之间的距离的关系,车辆和其他物体之间的距离,以及它们在传感器上的相对位置分布和图像序列的光流。
With these parameters, the researchers determined how precisely the objects were annotated and accordingly tagged with bounding boxes in the first place. In addition, they investigated how well the camera sensors of the vehicles were adjusted to their operational areas of use and what proportion, for example, was accounted for by standing phases, during which (almost) static images were captured over a longer period of time.
通过这些参数,研究人员确定了物体被标注的精确程度,并在一开始相应标记了边界框。此外,他们还研究了摄像头传感器对操作域内动作的调整程度,以及例如车辆静止状态所占的比例,在此期间,(几乎)在较长时间内被捕获的都是静态图像。
Optimizing the examined data sets 优化受检数据集
The results of the analyses and the quality of the data sets came as a surprise to the machine learning specialists at ARRK Engineering – and in a negative way. For example, they discovered an unexpectedly large number of static images from traffic congestion and standing phases, which were not marked as such and could therefore negatively influence the detectors’ accuracy.
分析结果和数据集的质量令ARRK Engineering|埃尔科工程 的机器学习专家们大吃一惊,情况不容乐观。例如,他们发现了大量来自交通拥堵和静止状态的静态图像,这些图像没有被标记,因此可能对检测器的准确性产生负面影响。
On the other hand, all the data sets examined completely lacked annotated objects at greater distances of around 100 m and more. However, due to the short TTC at speeds of about 130 km/h, it is imperative that ADAS detect such distant obstacles in order to ensure safe use on German motorways. In addition, the annotation of the objects can often be inaccurate because many people are working on the data sets with different approaches.
另一方面,所有被检查的数据集完全缺失了在大约100米或更远距离的标注物体。然而,由于时速约为130公里的TTC(碰撞时间)较短,为了确保在德国高速公路上的安全使用,ADAS必须检测到如此远的障碍。此外,由于许多人都在用不同的方法处理数据集,所以对物体的标注往往可能不准确。
To compensate for this, the bounding boxes are set more amply than necessary and often overlap. This in turn makes it harder for the systems to detect obstacles and prolongs the training processes. In addition, heat maps visualizing the distribution of the annotated objects over the entire sensor field of view reveal that 99.9 percent of the objects were detected in the lower half only.
为了弥补这一点,边界框的设置需要十分充足,且重叠安置。这反过来又使系统更难检测到障碍物,延长了训练过程。此外,根据整个传感器视野中标注物体分布的热图显示,99.9%的物体仅被检测到下半部分。
The researchers now aim to improve the poor quality of the data sets with regard to the development of level 2 and 3 ADAS. Therefore, they developed an approach to validate the models considering the operational domains of the systems and to correct their deficiencies accordingly. For example, the precision and generalization of the detector trainings can be increased by eliminating images with significantly overlapping bounding boxes as well as static images.
研究人员现在的目标是改善L2和L3 ADAS开发数据集的不良质量。因此,他们开发了一种方法,可以考虑到系统的操作域来验证模型,并相应地纠正其不足之处。例如,通过消除具有明显重叠边界框的图像以及静态图像,可以提高检测器训练的精度和通用性。
In addition, the study results allow determining to which extent a data set is applicable to a specific operational scenario, and amending it accordingly during training. In the case of ACC, this includes driving in urban areas, in the countryside or on motorways. By better aligning the camera sensors to the actual traffic situation, the efficiency of the calculations and thus also the reaction time of the ACC can be improved.
此外,研究结果可以确定一个数据集在多大程度上适用于特定的操作场景,并在训练中对其进行相应的修正。就ACC而言,这包括在城区、乡村或高速公路上的驾驶。通过根据实际道路更高地调整摄像头传感器,可以提高计算效率,从而也可以提高ACC的反应速度。
Increasing safety on the roads thanks to validated data sets 通过验证数据集 提高道路安全性
Validating data sets with ARRK Engineering’s newly developed approaches allows reducing the required iteration loops in the training process and thus the overall development time of the ADAS significantly. More efficient training can therefore save valuable time already in the development phase.
用ARRK Engineering|埃尔科工程 创新开发的方法验证数据集,可以减少训练过程中所需要的迭代循环量,从而大大减少ADAS的整体开发时间。因此,更有效的训练可以节省开发阶段的宝贵时间。
In addition, systems that have been precisely trained for their operational domain also feature higher functional safety. In practical use, for example, ACC can detect moving objects and stationary obstacles more reliably and initiate appropriate decelerating in time. Given that more and more highly functional ADAS will be on our roads in the future on the path to autonomous driving, this will increase general safety in daily road traffic.
此外,针对操作域进行过精准训练的系统,也具有更高的功能安全性。例如,在实际使用中,ACC可以更可靠地检测移动物体和静止障碍物,并及时启动适当的减速。鉴于未来在自动驾驶的道路上会出现越来越多的高功能ADAS,这将提高日常道路交通的总体安全性。
本文在AAAI人工智能大会 SafetyAI 2023分论坛宣读,扫描下方二维码,填写相关信息,稍后我们会将完整报告以邮件的形式发到您的邮箱中。
关于ARRK Engineering|埃尔科工程
ARRK Engineering GmbH 原名 P+Z Engineering GmbH,成立于1967年,总部位于德国慕尼黑,在英国、罗马尼亚、日本和中国均设有分公司或办公室,是汽车及航空航天等行业内众多国际一线品牌的长期合作伙伴,为客户提供高端的工程开发咨询服务。
埃尔科工程技术开发(上海)有限公司 是德国 ARRK Engineering GmbH 在中国设立的全资子公司,成立于2019年9月,志为中国汽车领域提供世界一流的工程技术服务。