BaTCAVe: Trustworthy Explanations for Robot Behaviors

Som Sagar, Aditya Taparia, Harsh Mankodiya, Pranav Bidare, Yifan Zhou, Ransalu Senanayake

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2025

* Equal contribution by Som Sagar and Aditya Taparia.

picture_as_pdf PDFplay_circle Videocode Code
Overview figure for BaTCAVe, showing Bayesian concept activation vectors producing explanations of robot decisions with uncertainty estimates.

Summary

We introduce BaTCAVe, a Bayesian extension of concept activation vectors that attaches calibrated uncertainty estimates to concept-based explanations of robot decisions, making post-hoc interpretation of neural network policies trustworthy across both simulation platforms and real-world robotic systems.

BibTeX

@inproceedings{sagar2025batcave,
    title={BaTCAVe: Trustworthy Explanations for Robot Behaviors},
    author={Sagar, Som and Taparia, Aditya and Mankodiya, Harsh and Bidare, Pranav and Zhou, Yifan and Senanayake, Ransalu},
    booktitle={2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
    pages={13867--13874},
    year={2025}
}