As humanoid robots move from controlled industrial environments into everyday human life, their safe integration is essential for societal acceptance and effective human–robot interaction (HRI). This scoping review examines engineering safety frameworks for humanoid robots across four core domains: (1) physical safety in HRI, (2) cybersecurity and software robustness, (3) safety standards and regulatory frameworks, and (4) ethical and societal implications. In the area of physical safety, recent research trends emphasize proactive, multimodal perception-based collision avoidance, the use of compliance mechanisms, and fault-tolerant control to handle hardware failures and falls. In cybersecurity and software robustness, studies increasingly address the full threat landscape, secure real-time communication, and reliability of artificial intelligence (AI)-based control. The analysis of standards and regulations reveals a lag between technological advances and the adaptation of key safety standards in current research. Ethical and societal studies show that safety is also shaped by user trust, perceived safety, and data protection. Within the corpus of 121 peer-reviewed studies published between 2021 and 2025 and included in this review, most work concentrates on physical safety, while cybersecurity, standardization, and socio-ethical aspects are addressed less frequently. These gaps point to the need for more integrated, cross-domain approaches to safety engineering for humanoid robots.
József Sárosi (Mon,) studied this question.