cs.RONov 2, 2026

A Practical Causal Framework for Autonomous Mobile Robots: From Simulation to Real-World Human Environments

Authors: Luca Castri, Gloria Beraldo, Nicola Bellotto

Organizations: University of Padua, Italy · National Research Council of Italy

Abstract

Causal inference has emerged as a powerful paradigm enabling robots to make safe, efficient decisions by reasoning about the ``why'' behind events. However, its real-world application is hindered by the difficulty of collecting causal data, especially in human-populated environments where training takes time, while users expect immediate operation. To this end, we tackle the challenge of transferring simulation-learnt causal relations to the real world with minimal effort. While retaining the invariant high-level causal structure, we empirically demonstrate the system adapts efficiently to real-world situations by updating only the causal model parameters with a limited set of new observations. Our results show that the parameter update enables rapid sim-to-real transfer. The framework runs efficiently onboard of a mobile robot and significantly outperforms a non-causal baselines navigating successfully and safely in complex human-shared scenarios.

Figures & tables

Explore similar work

CardsList
  1. Can Causal Models Enhance Robot Navigation? Online Causal Adaptation for Real-Robot Navigation

    Jun 14, 2026Zhitao Liang, Alex Mitrevski, Emmanuel Dean +1Robot Navigation

  2. Estimating the Causal Impact of Social Navigation Signals in Corridor Scenarios

    Oct 12, 2026Francesco Baldo, Luca Castri, Gloria Beraldo +1Social Robot NavigationSocial Navigation

  3. Zeva: In-Context Causal Learning for Generalizable Embodied Manipulation

    Aug 31, 2026Fu Chen, Xin Ding, Bingjia Huang +8Robot Policy LearningICL for Robotics