Explainable Autonomous Robots: Taxonomy, State, and Trends — An Implementation-driven Mapping Study

Abstract As autonomous robots increasingly operate in dynamic environments shared with humans, explaining their decisions and behaviors isessential for trust, transparency, and effective human-robot interaction. Although eXplainable Artificial Intelligence (XAI) has receivedsubstantial attention in recent years, challenges specific to eXplainable Autonomous Robot (XAR) remain underexplored. We reporta systematic mapping study of 94 papers (922 screened) published between 2021 and February 2026, providing empirical evidenceon how XAR research is implemented. Based on the analyzed papers, we derive a taxonomy spanning target platforms, softwarecharacteristics, explanation structures, stakeholders, and evaluation practices. With this, we categorize the reviewed literature andderive insights, trends and challenges for XAR research.The field demonstrates technical feasibility across diverse contexts. However, we identify clear opportunities: reversing the currenttrend from real-world validation to simulations (especially in Machine Learning (ML)-based systems), more explicit specification ofthe intended context of use, deeper investigation of human involvement, exploration of multi-agent/multi-stakeholder scenarios,and closer alignment between researchers’ focus on “Why” explanations and users’ broader question needs. Furthermore, currentevaluation practices are inconsistent in their initial motivation and measured results. Finally, XAR research forgoes comparativeanalysis and reproducibility due to a severe lack of open-source code. Instructions A README is supplied with the zip files to replcicate our data anlaysis.