Explaining Deep Learning-Based Driver Models
Different systems based on Artificial Intelligence (AI) techniques are currently used in relevant areas such as healthcare, cybersecurity, natural language processing, and self-driving cars. However, many of these systems are developed with “black box” AI, which makes it difficult to explain how the...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-04-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/11/8/3321 |
| _version_ | 1797538520187797504 |
|---|---|
| author | Maria Paz Sesmero Lorente Elena Magán Lopez Laura Alvarez Florez Agapito Ledezma Espino José Antonio Iglesias Martínez Araceli Sanchis de Miguel |
| author_facet | Maria Paz Sesmero Lorente Elena Magán Lopez Laura Alvarez Florez Agapito Ledezma Espino José Antonio Iglesias Martínez Araceli Sanchis de Miguel |
| author_sort | Maria Paz Sesmero Lorente |
| collection | DOAJ |
| description | Different systems based on Artificial Intelligence (AI) techniques are currently used in relevant areas such as healthcare, cybersecurity, natural language processing, and self-driving cars. However, many of these systems are developed with “black box” AI, which makes it difficult to explain how they work. For this reason, explainability and interpretability are key factors that need to be taken into consideration in the development of AI systems in critical areas. In addition, different contexts produce different explainability needs which must be met. Against this background, Explainable Artificial Intelligence (XAI) appears to be able to address and solve this situation. In the field of automated driving, XAI is particularly needed because the level of automation is constantly increasing according to the development of AI techniques. For this reason, the field of XAI in the context of automated driving is of particular interest. In this paper, we propose the use of an explainable intelligence technique in the understanding of some of the tasks involved in the development of advanced driver-assistance systems (ADAS). Since ADAS assist drivers in driving functions, it is essential to know the reason for the decisions taken. In addition, trusted AI is the cornerstone of the confidence needed in this research area. Thus, due to the complexity and the different variables that are part of the decision-making process, this paper focuses on two specific tasks in this area: the detection of emotions and the distractions of drivers. The results obtained are promising and show the capacity of the explainable artificial techniques in the different tasks of the proposed environments. |
| first_indexed | 2024-03-10T12:31:36Z |
| format | Article |
| id | doaj.art-1d8fc40d1510453db560af47b5a93b33 |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-03-10T12:31:36Z |
| publishDate | 2021-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-1d8fc40d1510453db560af47b5a93b332023-11-21T14:33:12ZengMDPI AGApplied Sciences2076-34172021-04-01118332110.3390/app11083321Explaining Deep Learning-Based Driver ModelsMaria Paz Sesmero Lorente0Elena Magán Lopez1Laura Alvarez Florez2Agapito Ledezma Espino3José Antonio Iglesias Martínez4Araceli Sanchis de Miguel5Computer Science Department, Universidad Carlos III de Madrid, 28911 Madrid, SpainComputer Science Department, Universidad Carlos III de Madrid, 28911 Madrid, SpainComputer Science Department, Universidad Carlos III de Madrid, 28911 Madrid, SpainComputer Science Department, Universidad Carlos III de Madrid, 28911 Madrid, SpainComputer Science Department, Universidad Carlos III de Madrid, 28911 Madrid, SpainComputer Science Department, Universidad Carlos III de Madrid, 28911 Madrid, SpainDifferent systems based on Artificial Intelligence (AI) techniques are currently used in relevant areas such as healthcare, cybersecurity, natural language processing, and self-driving cars. However, many of these systems are developed with “black box” AI, which makes it difficult to explain how they work. For this reason, explainability and interpretability are key factors that need to be taken into consideration in the development of AI systems in critical areas. In addition, different contexts produce different explainability needs which must be met. Against this background, Explainable Artificial Intelligence (XAI) appears to be able to address and solve this situation. In the field of automated driving, XAI is particularly needed because the level of automation is constantly increasing according to the development of AI techniques. For this reason, the field of XAI in the context of automated driving is of particular interest. In this paper, we propose the use of an explainable intelligence technique in the understanding of some of the tasks involved in the development of advanced driver-assistance systems (ADAS). Since ADAS assist drivers in driving functions, it is essential to know the reason for the decisions taken. In addition, trusted AI is the cornerstone of the confidence needed in this research area. Thus, due to the complexity and the different variables that are part of the decision-making process, this paper focuses on two specific tasks in this area: the detection of emotions and the distractions of drivers. The results obtained are promising and show the capacity of the explainable artificial techniques in the different tasks of the proposed environments.https://www.mdpi.com/2076-3417/11/8/3321Explainable Artificial Intelligence (XAI)advanced driver-assistance system (ADAS)automotive environmentbehavior driver recognitionemotions driver recognitionXRAI (Region-based saliency method) |
| spellingShingle | Maria Paz Sesmero Lorente Elena Magán Lopez Laura Alvarez Florez Agapito Ledezma Espino José Antonio Iglesias Martínez Araceli Sanchis de Miguel Explaining Deep Learning-Based Driver Models Applied Sciences Explainable Artificial Intelligence (XAI) advanced driver-assistance system (ADAS) automotive environment behavior driver recognition emotions driver recognition XRAI (Region-based saliency method) |
| title | Explaining Deep Learning-Based Driver Models |
| title_full | Explaining Deep Learning-Based Driver Models |
| title_fullStr | Explaining Deep Learning-Based Driver Models |
| title_full_unstemmed | Explaining Deep Learning-Based Driver Models |
| title_short | Explaining Deep Learning-Based Driver Models |
| title_sort | explaining deep learning based driver models |
| topic | Explainable Artificial Intelligence (XAI) advanced driver-assistance system (ADAS) automotive environment behavior driver recognition emotions driver recognition XRAI (Region-based saliency method) |
| url | https://www.mdpi.com/2076-3417/11/8/3321 |
| work_keys_str_mv | AT mariapazsesmerolorente explainingdeeplearningbaseddrivermodels AT elenamaganlopez explainingdeeplearningbaseddrivermodels AT lauraalvarezflorez explainingdeeplearningbaseddrivermodels AT agapitoledezmaespino explainingdeeplearningbaseddrivermodels AT joseantonioiglesiasmartinez explainingdeeplearningbaseddrivermodels AT aracelisanchisdemiguel explainingdeeplearningbaseddrivermodels |