Setting AI in context: A case study on defining the context and operational design domain for automated driving

• URL: http://arxiv.org/abs/2201.11451v1
• Date: Thu, 27 Jan 2022 11:26:32 GMT
• Title: Setting AI in context: A case study on defining the context and operational design domain for automated driving
• Authors: Hans-Martin Heyn and Padmini Subbiash and Jennifer Linder and Eric Knauss and Olof Eriksson
• Abstract summary: The case study investigates the challenges with context definitions for the development of perception functions that use machine learning for automated driving. The results outline challenges experienced by an automotive supplier company when defining the operational context for systems using machine learning.
• Score: 5.083561746476347
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: [Context and motivation] For automated driving systems, the operational context needs to be known in order to state guarantees on performance and safety. The operational design domain (ODD) is an abstraction of the operational context, and its definition is an integral part of the system development process. [Question / problem] There are still major uncertainties in how to clearly define and document the operational context in a diverse and distributed development environment such as the automotive industry. This case study investigates the challenges with context definitions for the development of perception functions that use machine learning for automated driving. [Principal ideas/results] Based on qualitative analysis of data from semi-structured interviews, the case study shows that there is a lack of standardisation for context definitions across the industry, ambiguities in the processes that lead to deriving the ODD, missing documentation of assumptions about the operational context, and a lack of involvement of function developers in the context definition. [Contribution] The results outline challenges experienced by an automotive supplier company when defining the operational context for systems using machine learning. Furthermore, the study collected ideas for potential solutions from the perspective of practitioners.

Related papers

• Interactive Agents to Overcome Ambiguity in Software Engineering [61.40183840499932]
  AI agents are increasingly being deployed to automate tasks, often based on ambiguous and underspecified user instructions. Making unwarranted assumptions and failing to ask clarifying questions can lead to suboptimal outcomes. We study the ability of LLM agents to handle ambiguous instructions in interactive code generation settings by evaluating proprietary and open-weight models on their performance.
  arXiv  Detail & Related papers  (2025-02-18T17:12:26Z)
• Learning Task Representations from In-Context Learning [73.72066284711462]
  Large language models (LLMs) have demonstrated remarkable proficiency in in-context learning. We introduce an automated formulation for encoding task information in ICL prompts as a function of attention heads. We show that our method's effectiveness stems from aligning the distribution of the last hidden state with that of an optimally performing in-context-learned model.
  arXiv  Detail & Related papers  (2025-02-08T00:16:44Z)
• On STPA for Distributed Development of Safe Autonomous Driving: An Interview Study [0.7851536646859475]
  System-Theoretic Process Analysis (STPA) is a novel method applied in safety-related fields like defense and aerospace. STPA assumes prerequisites that are not fully valid in the automotive system engineering with distributed system development and multi-abstraction design levels. This can be seen as a maintainability challenge in continuous development and deployment.
  arXiv  Detail & Related papers  (2024-03-14T15:56:02Z)
• AutoGuide: Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents [74.17623527375241]
  We introduce a novel framework, called AutoGuide, which automatically generates context-aware guidelines from offline experiences. As a result, our guidelines facilitate the provision of relevant knowledge for the agent's current decision-making process. Our evaluation demonstrates that AutoGuide significantly outperforms competitive baselines in complex benchmark domains.
  arXiv  Detail & Related papers  (2024-03-13T22:06:03Z)
• Auto-ICL: In-Context Learning without Human Supervision [93.05202223767463]
  We propose Automatic In-Context Learning framework that enables the model to autonomously generate examples and instructions for problem-solving. With experiments across various models and datasets, results show that model-generated contexts outperform human-annotated contexts.
  arXiv  Detail & Related papers  (2023-11-15T07:37:28Z)
• Towards Scenario-based Safety Validation for Autonomous Trains with Deep Generative Models [0.0]
  We report our practical experiences regarding the utility of data simulation with deep generative models for scenario-based validation. We demonstrate the capabilities of semantically editing railway scenes with deep generative models to make a limited amount of test data more representative.
  arXiv  Detail & Related papers  (2023-10-16T17:55:14Z)
• Using Ontologies for the Formalization and Recognition of Criticality for Automated Driving [0.0]
  Recent advances suggest the ability to leverage relevant knowledge in handling the inherently open and complex context of the traffic world. This paper demonstrates to be a powerful tool for modeling and formalization of factors associated with criticality in the environment of automated vehicles. We elaborate on the modular approach, present a publicly available implementation, and evaluate the method by means of a large-scale drone data set of urban traffic scenarios.
  arXiv  Detail & Related papers  (2022-05-03T14:32:11Z)
• Finding Critical Scenarios for Automated Driving Systems: A Systematic Literature Review [20.926088145784604]
  We present the results of a systematic literature review in the context of autonomous driving. We introduce a comprehensive taxonomy for critical scenario identification methods. We also give an overview of the state-of-the-art research based on the taxonomy encompassing 86 papers between 2017 and 2020.
  arXiv  Detail & Related papers  (2021-10-16T21:24:19Z)
• CausalCity: Complex Simulations with Agency for Causal Discovery and Reasoning [68.74447489372037]
  We present a high-fidelity simulation environment that is designed for developing algorithms for causal discovery and counterfactual reasoning. A core component of our work is to introduce textitagency, such that it is simple to define and create complex scenarios. We perform experiments with three state-of-the-art methods to create baselines and highlight the affordances of this environment.
  arXiv  Detail & Related papers  (2021-06-25T00:21:41Z)
• Out of Context: A New Clue for Context Modeling of Aspect-based Sentiment Analysis [54.735400754548635]
  ABSA aims to predict the sentiment expressed in a review with respect to a given aspect. The given aspect should be considered as a new clue out of context in the context modeling process. We design several aspect-aware context encoders based on different backbones.
  arXiv  Detail & Related papers  (2021-06-21T02:26:03Z)
• Towards an Ontology for Scenario Definition for the Assessment of Automated Vehicles: An Object-Oriented Framework [0.0]
  We develop a comprehensive and operable definition of the notion of scenario. We propose an object-oriented framework in which scenarios and their building blocks are defined as classes of objects. We provide definitions and justifications of each of the terms.
  arXiv  Detail & Related papers  (2020-01-30T08:14:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.