Our paper on neuro-symbolic explainability was accepted to RA-L!

January 28, 2026

Our paper titled “Neuro-Symbolic Generation of Explanations for Robot Policies with Weighted Signal Temporal Logic” was accepted to IEEE Robotics and Automation Letters (RA-L)! We propose a method for inferring the weighted signal temporal logic specification that best explains a given robot policy, along with three explainability metrics. The work was led by Miki Yuasa.