Designing AI for Explainability and Verifiability: A Value Sensitive Design Approach to Avoid Artificial Stupidity in Autonomous Vehicles
Open accessThe DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
One of the primary, if not most critical, difficulties in the design and implementation of autonomous systems is the black-boxed nature of the decision-making structures and logical pathways. How human values are embodied and actualised in situ may ultimately prove to be harmful if not outright recalcitrant. For this reason, the values of stakeholders become of particular significance given the risks posed by opaque structures of intelligent agents. This paper explores how decision matrix algorithms, via the belief-desire-intention model for autonomous vehicles, can be designed to minimize the risks of opaque architectures. Primarily through an explicit orientation towards designing for the values of explainability and verifiability. In doing so, this research adopts the Value Sensitive Design (VSD) approach as a principled framework for the incorporation of such values within design. VSD is recognized as a potential starting point that offers a systematic way for engineering teams to formally incorporate existing technical solutions within ethical design, while simultaneously remaining pliable to emerging issues and needs. It is concluded that the VSD methodology offers at least a strong enough foundation from which designers can begin to anticipate design needs and formulate salient design flows that can be adapted to the changing ethical landscapes required for utilisation in autonomous vehicles.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
European Union Regulations on Algorithmic Decision Making and a “Right to Explanation”
Goodman, B., & Flaxman, S. (2017) · AI Magazine · doi:10.1609/aimag.v38i3.2741 · Cited by 2,131
Network Dissection: Quantifying Interpretability of Deep Visual Representations
Bau, D., Zhou, B., Khosla, A., Oliva, A., & Torralba, A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.354 · Cited by 1,389
Value Sensitive Design and Information Systems
Friedman, B., Kahn, P. H., Borning, A., & Huldtgren, A. (2013) · Philosophy of Engineering and Technology · doi:10.1007/978-94-007-7844-3_4 · Cited by 678 · cited 2×
“1), referred to commonly as a ‘tripartite methodology’ consisting of conceptual investigations, empirical investigations, and technical investigations [7, 26].”
BackgroundMethodMeaningful Human Control over Autonomous Systems: A Philosophical Account
Santoni de Sio, F., & van den Hoven, J. (2018) · Frontiers in Robotics and AI · doi:10.3389/frobt.2018.00015 · Cited by 566 · cited 3×
“In doing so, we propose a VSD approach as a principled framework for incorporating human values in design and thus retaining meaningful human control over them [1].”
BackgroundMethodEmergence of grounded compositional language in multi-agent populations
Mordatch, I., & Abbeel, P. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11492 · Cited by 440
A Survey of Value Sensitive Design Methods
Friedman, B., Hendry, D. G., & Borning, A. (2017) · Foundations and Trends® in Human–Computer Interaction · doi:10.1561/1100000015 · Cited by 389 · cited 2×
“Prior literature on VSD has focused on its methodological foundations [6–8], its applicability to existing technologies, such as energy systems and care robotics [9–11], as well as its applicability to AI in general and other advanced technologies for instance, molecular manufacturing [12–15].”
BackgroundMethodTranslating Values into Design Requirements
van de Poel, I. (2013) · Philosophy of Engineering and Technology · doi:10.1007/978-94-007-7762-0_20 · Cited by 273
Human-Data Interaction: The Human Face of the Data-Driven Society
Mortier, R., Haddadi, H., Henderson, T., McAuley, D., & Crowcroft, J. (2014) · doi:10.2139/ssrn.2508051 · Cited by 247
Engineering and the Problem of Moral Overload
Van den Hoven, J., Lokhorst, G.-J., & Van de Poel, I. (2012) · Science and Engineering Ethics · doi:10.1007/s11948-011-9277-z · Cited by 194 · cited 2×
“This occurs when similar values are equally prized by enrolled stakeholders but are often at odds with each other when translated into technical design requirements [27, 32].”
BackgroundMethodA Rawlsian algorithm for autonomous vehicles
Leben, D. (2017) · Ethics and Information Technology · doi:10.1007/s10676-017-9419-3 · Cited by 141 · cited 1×
“DMAs are one of the primary algorithms used to form the machine learning set for AVs [20–22].”
Method
Cited by
Mapping value sensitive design onto AI for social good principles
Umbrello, S., & van de Poel, I. (2021) · AI and Ethics · doi:10.1007/s43681-021-00038-3 · Cited by 251
Self-citationHuman-centered evaluation of explainable AI applications: a systematic review
Kim, J., Maathuis, H., & Sent, D. (2024) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2024.1456486 · Cited by 130
Constructing Ethical AI Based on the “Human-in-the-Loop” System
Chen, X., Wang, X., & Qu, Y. (2023) · Systems · doi:10.3390/systems11110548 · Cited by 45
Reframing deception for human-centered AI
Umbrello, S., & Natale, S. (2024) · International Journal of Social Robotics · doi:10.1007/s12369-024-01184-4 · Cited by 23
Self-citation
Metadata
- Authors
- Umbrello, S., & Yampolskiy, R. V.
- Venue
- International Journal of Social Robotics
- Published
- 2021-05-15
- Volume
- 14
- Issue
- 2
- Pages
- 313-322
- ISSN
- 1875-4791 (ISSN-L)
- 1875-4805
- OpenAlex
- W3163027429
- Cited by
- 61
- References
- 12
- FWCI
- 3.71
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Designing AI for Explainability and Verifiability: A Value Sensitive Design Approach to Avoid Artificial Stupidity in Autonomous Vehicles. https://app.cochat.ai/papers/10.1007/s12369-021-00790-w
- The paper
- Umbrello, S., & Yampolskiy, R. V. (2022). Designing AI for Explainability and Verifiability: A Value Sensitive Design Approach to Avoid Artificial Stupidity in Autonomous Vehicles. International Journal of Social Robotics. https://doi.org/10.1007/s12369-021-00790-w
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.