The missing link: Developing a safety case for perception components in automated driving

Salay, Rick; Czarnecki, Krzysztof; Kuwajima, Hiroshi; Yasuoka, Hirotoshi; Nakae, Toshihiro; Abdelzad, Vahdat; Huang, Chengjie; Kahn, Maximilian; Nguyen, Van Hoang

doi:10.48550/arxiv.2108.13294

Cited by 4 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ISO 21448 [147] focuses on processes and measures to ensure the absence of unreasonable risk due to a hazard caused by functional insufficiencies, where the performance limitation of sensors is also explicitly mentioned as one of the sources of functional insufficiencies. The basic safety specification considers the occurrence of an error pattern [148] within the ODD being sufficiently low, commonly reflected as a probability term. While the appendix of the ISO 21448 covers some high-level aspects and some of the processoriented results aim at offering a general argumentation framework [148], [149], [150], [151], [152], we consider the key technical challenge to be the "implementation aspects" of such a process.…”

Section: A Safety Standards and Guidelines For Perceptionmentioning

confidence: 99%

“…The basic safety specification considers the occurrence of an error pattern [148] within the ODD being sufficiently low, commonly reflected as a probability term. While the appendix of the ISO 21448 covers some high-level aspects and some of the processoriented results aim at offering a general argumentation framework [148], [149], [150], [151], [152], we consider the key technical challenge to be the "implementation aspects" of such a process. ANSI/UL 4600 [153] is a standard to promote a proper consideration of safety issues for generic autonomous systems and specifically adopt autonomous vehicles as a concrete case.…”

Section: A Safety Standards and Guidelines For Perceptionmentioning

confidence: 99%

See 1 more Smart Citation

Sensing and Machine Learning for Automotive Perception: A Review

et al. 2023

View full text Add to dashboard Cite

Automotive perception involves understanding the external driving environment and the internal state of the vehicle cabin and occupants using sensor data. It is critical to achieving high levels of safety and autonomy in driving. This article provides an overview of different sensor modalities, such as cameras, radars, and light detection and ranging (LiDAR) used commonly for perception, along with the associated data processing techniques. Critical aspects of perception are considered, such as architectures for processing data from single or multiple sensor modalities, sensor data processing algorithms and the role of machine learning techniques, methodologies for validating the performance of perception systems, and safety. The technical challenges for each aspect are analyzed, emphasizing machine learning approaches, given their potential impact on improving perception. Finally, future research opportunities in automotive perception for their wider deployment are outlined.

show abstract

Section: A Safety Standards and Guidelines For Perceptionmentioning

confidence: 99%

Section: A Safety Standards and Guidelines For Perceptionmentioning

confidence: 99%

Sensing and Machine Learning for Automotive Perception: A Review

et al. 2023

View full text Add to dashboard Cite

show abstract

“…There has been some work that proposes how safety approaches may be developed for the use of ML in specific domains such as automotive [18] or healthcare [19] and on assurance of the learning lifecycle more generally [20]. There has also been a limited amount of work on safety case structures for ML components [21,22]. There has been no other work however that describes a detailed safety assurance process for ML components and describes how that process can be used to create an explicit safety case for ML.…”

Section: Safety Assurance Cases For Machine Learningmentioning

confidence: 99%

Creating a Safety Assurance Case for a Machine Learned Satellite-Based Wildfire Detection and Alert System

Hawkins

Picardi

Donnell³

et al. 2023

J Intell Robot Syst

View full text Add to dashboard Cite

Wildfires are a common problem in many areas of the world with often catastrophic consequences. A number of systems have been created to provide early warnings of wildfires, including those that use satellite data to detect fires. The increased availability of small satellites, such as CubeSats, allows the wildfire detection response time to be reduced by deploying constellations of multiple satellites over regions of interest. By using machine learned components on-board the satellites, constraints which limit the amount of data that can be processed and sent back to ground stations can be overcome. There are hazards associated with wildfire alert systems, such as failing to detect the presence of a wildfire, or detecting a wildfire in the incorrect location. It is therefore necessary to be able to create a safety assurance case for the wildfire alert ML component that demonstrates it is sufficiently safe for use. This paper describes in detail how a safety assurance case for an ML wildfire alert system is created. This represents the first fully developed safety case for an ML component containing explicit argument and evidence as to the safety of the machine learning.

show abstract

“…The safety of DNNs is currently researched from different angles; we recommend readers to a current survey [5] conducted by the German national project KI-Absicherung for an overview. On the methodology side, many results on safety argumentation use semi-formal/structural notations with variations on argumentation strategies (to list a few [2,17,8,14]). The value of these results is the offering of a generic argumentation structure, where the purpose of this paper is to demonstrate its implementation aspects for one type of performance insufficiencies.…”

Section: Related Workmentioning

confidence: 99%

Unaligned but Safe -- Formally Compensating Performance Limitations for Imprecise 2D Object Detection

Schuster¹,

Seferis²,

Burton³

et al. 2022

Preprint

View full text Add to dashboard Cite

In this paper, we consider the imperfection within machine learning-based 2D object detection and its impact on safety. We address a special sub-type of performance limitations: the prediction bounding box cannot be perfectly aligned with the ground truth, but the computed Intersection-over-Union metric is always larger than a given threshold. Under such type of performance limitation, we formally prove the minimum required bounding box enlargement factor to cover the ground truth. We then demonstrate that the factor can be mathematically adjusted to a smaller value, provided that the motion planner takes a fixed-length buffer in making its decisions. Finally, observing the difference between an empirically measured enlargement factor and our formally derived worst-case enlargement factor offers an interesting connection between the quantitative evidence (demonstrated by statistics) and the qualitative evidence (demonstrated by worst-case analysis).

show abstract

The missing link: Developing a safety case for perception components in automated driving

Cited by 4 publications

References 0 publications

Sensing and Machine Learning for Automotive Perception: A Review

Sensing and Machine Learning for Automotive Perception: A Review

Creating a Safety Assurance Case for a Machine Learned Satellite-Based Wildfire Detection and Alert System

Unaligned but Safe -- Formally Compensating Performance Limitations for Imprecise 2D Object Detection

Contact Info

Product

Resources

About