BaTCAVe: Trustworthy Explanations for Robot Behaviors
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908582447939584 |
|---|---|
| author | Sagar, Som Taparia, Aditya Mankodiya, Harsh Bidare, Pranav Zhou, Yifan Senanayake, Ransalu |
| author_facet | Sagar, Som Taparia, Aditya Mankodiya, Harsh Bidare, Pranav Zhou, Yifan Senanayake, Ransalu |
| contents | Black box neural networks are an indispensable part of modern robots. Nevertheless, deploying such high-stakes systems in real-world scenarios poses significant challenges when the stakeholders, such as engineers and legislative bodies, lack insights into the neural networks' decision-making process. Presently, explainable AI is primarily tailored to natural language processing and computer vision, falling short in two critical aspects when applied in robots: grounding in decision-making tasks and the ability to assess trustworthiness of their explanations. In this paper, we introduce a trustworthy explainable robotics technique based on human-interpretable, high-level concepts that attribute to the decisions made by the neural network. Our proposed technique provides explanations with associated uncertainty scores for the explanation by matching neural network's activations with human-interpretable visualizations. To validate our approach, we conducted a series of experiments with various simulated and real-world robot decision-making models, demonstrating the effectiveness of the proposed approach as a post-hoc, human-friendly robot diagnostic tool. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_10733 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BaTCAVe: Trustworthy Explanations for Robot Behaviors Sagar, Som Taparia, Aditya Mankodiya, Harsh Bidare, Pranav Zhou, Yifan Senanayake, Ransalu Robotics Machine Learning Black box neural networks are an indispensable part of modern robots. Nevertheless, deploying such high-stakes systems in real-world scenarios poses significant challenges when the stakeholders, such as engineers and legislative bodies, lack insights into the neural networks' decision-making process. Presently, explainable AI is primarily tailored to natural language processing and computer vision, falling short in two critical aspects when applied in robots: grounding in decision-making tasks and the ability to assess trustworthiness of their explanations. In this paper, we introduce a trustworthy explainable robotics technique based on human-interpretable, high-level concepts that attribute to the decisions made by the neural network. Our proposed technique provides explanations with associated uncertainty scores for the explanation by matching neural network's activations with human-interpretable visualizations. To validate our approach, we conducted a series of experiments with various simulated and real-world robot decision-making models, demonstrating the effectiveness of the proposed approach as a post-hoc, human-friendly robot diagnostic tool. |
| title | BaTCAVe: Trustworthy Explanations for Robot Behaviors |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2409.10733 |