Causal Robot: Proactively Explaining & Preventing Robot Failures via Causal Reasoning

Research Project, 2025

Robots in dynamic environments struggle with unforeseen situations due to limited adaptability. We propose a novel, causal-based approach to empower robots with rapid prediction and prevention of both immediate and future failures. We focus on a) automatically learning the cause-effect relationships of tasks, and b) generating explanations for unsuccessful actions. This project will enable robots to understand “why” things happen, which will allow them to learn from their mistakes, thus improving their future performances. This research significantly advances robot autonomy, fostering the development of safer, more trustworthy robotic agents. We will contribute to WP5 by enabling robots to effectively learn and transfer knowledge across diverse tasks and environments. We will help with WP2 as robots need to adapt to various user needs and home settings. Our research lays the foundation for robots that can continuously learn and improve their assistive capabilities.