What and When to Explain? On-road Evaluation of Explanations in Highly Automated Vehicles
Explanations in automated vehicles help passengers understand the vehicle’s state and capabilities, leading to increased trust in the technology. Specifically, for passengers of SAE Level 4 and 5 vehicles who are not engaged in the driving process, the enhanced sense of control provided by...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | English |
| Published: |
ACM
2023
|
| Online Access: | https://hdl.handle.net/1721.1/152332 |
| _version_ | 1826204858738278400 |
|---|---|
| author | Kim, Gwangbin Yeo, Dohyeon Jo, Taewoo Rus, Daniela Kim, SeungJun |
| author2 | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science |
| author_facet | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Kim, Gwangbin Yeo, Dohyeon Jo, Taewoo Rus, Daniela Kim, SeungJun |
| author_sort | Kim, Gwangbin |
| collection | MIT |
| description | Explanations in automated vehicles help passengers understand the vehicle’s state and capabilities, leading to increased trust in the technology. Specifically, for passengers of SAE Level 4 and 5 vehicles who are not engaged in the driving process, the enhanced sense of control provided by explanations reduces potential anxieties, enabling them to fully leverage the benefits of automation. To construct explanations that enhance trust and situational awareness without disturbing passengers, we suggest testing with people who ultimately employ such explanations, ideally under real-world driving conditions. In this study, we examined the impact of various visual explanation types (perception, attention, perception+attention) and timing mechanisms (constantly provided or only under risky scenarios) on passenger experience under naturalistic driving scenarios using actual vehicles with mixed-reality support. Our findings indicate that visualizing the vehicle’s perception state improves the perceived usability, trust, safety, and situational awareness without adding cognitive burden, even without explaining the underlying causes. We also demonstrate that the traffic risk probability could be used to control the timing of an explanation delivery, particularly when passengers are overwhelmed with information. Our study’s on-road evaluation method offers a safe and reliable testing environment and can be easily customized for other AI models and explanation modalities. |
| first_indexed | 2024-09-23T13:02:13Z |
| format | Article |
| id | mit-1721.1/152332 |
| institution | Massachusetts Institute of Technology |
| language | English |
| last_indexed | 2024-09-23T13:02:13Z |
| publishDate | 2023 |
| publisher | ACM |
| record_format | dspace |
| spelling | mit-1721.1/1523322024-01-23T18:23:42Z What and When to Explain? On-road Evaluation of Explanations in Highly Automated Vehicles Kim, Gwangbin Yeo, Dohyeon Jo, Taewoo Rus, Daniela Kim, SeungJun Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Explanations in automated vehicles help passengers understand the vehicle’s state and capabilities, leading to increased trust in the technology. Specifically, for passengers of SAE Level 4 and 5 vehicles who are not engaged in the driving process, the enhanced sense of control provided by explanations reduces potential anxieties, enabling them to fully leverage the benefits of automation. To construct explanations that enhance trust and situational awareness without disturbing passengers, we suggest testing with people who ultimately employ such explanations, ideally under real-world driving conditions. In this study, we examined the impact of various visual explanation types (perception, attention, perception+attention) and timing mechanisms (constantly provided or only under risky scenarios) on passenger experience under naturalistic driving scenarios using actual vehicles with mixed-reality support. Our findings indicate that visualizing the vehicle’s perception state improves the perceived usability, trust, safety, and situational awareness without adding cognitive burden, even without explaining the underlying causes. We also demonstrate that the traffic risk probability could be used to control the timing of an explanation delivery, particularly when passengers are overwhelmed with information. Our study’s on-road evaluation method offers a safe and reliable testing environment and can be easily customized for other AI models and explanation modalities. 2023-10-03T15:05:42Z 2023-10-03T15:05:42Z 2023-09-27 2023-10-01T07:49:17Z Article http://purl.org/eprint/type/JournalArticle 2474-9567 https://hdl.handle.net/1721.1/152332 Kim, Gwangbin, Yeo, Dohyeon, Jo, Taewoo, Rus, Daniela and Kim, SeungJun. 2023. "What and When to Explain? On-road Evaluation of Explanations in Highly Automated Vehicles." Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 7 (3). PUBLISHER_CC en https://doi.org/10.1145/3610886 Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use. The author(s) application/pdf ACM Association for Computing Machinery |
| spellingShingle | Kim, Gwangbin Yeo, Dohyeon Jo, Taewoo Rus, Daniela Kim, SeungJun What and When to Explain? On-road Evaluation of Explanations in Highly Automated Vehicles |
| title | What and When to Explain? On-road Evaluation of Explanations in Highly Automated Vehicles |
| title_full | What and When to Explain? On-road Evaluation of Explanations in Highly Automated Vehicles |
| title_fullStr | What and When to Explain? On-road Evaluation of Explanations in Highly Automated Vehicles |
| title_full_unstemmed | What and When to Explain? On-road Evaluation of Explanations in Highly Automated Vehicles |
| title_short | What and When to Explain? On-road Evaluation of Explanations in Highly Automated Vehicles |
| title_sort | what and when to explain on road evaluation of explanations in highly automated vehicles |
| url | https://hdl.handle.net/1721.1/152332 |
| work_keys_str_mv | AT kimgwangbin whatandwhentoexplainonroadevaluationofexplanationsinhighlyautomatedvehicles AT yeodohyeon whatandwhentoexplainonroadevaluationofexplanationsinhighlyautomatedvehicles AT jotaewoo whatandwhentoexplainonroadevaluationofexplanationsinhighlyautomatedvehicles AT rusdaniela whatandwhentoexplainonroadevaluationofexplanationsinhighlyautomatedvehicles AT kimseungjun whatandwhentoexplainonroadevaluationofexplanationsinhighlyautomatedvehicles |