Safety Evaluation Enters the Foundation-Model Stack
Google paired its robotics release with layered safeguards and an agentic-robot safety benchmark.
Market Driver: safety
Airlines Tighten the Battery Gate
Major US airlines expanded restrictions on transporting humanoid and animal-like robots because of battery-safety concerns.
Safe Agent Execution Gets Localized Obligations
HALO proposes localized obligations for admitting and supervising heterogeneous agent actions safely.
World Models Receive a Security Threat Model
Researchers map attacks across sensing, world modelling, planning, execution, feedback and long-term adaptation.
