Embodied reasoning becomes task orchestration
ER 2 adds video understanding, multi-step planning, progress checking and higher-level orchestration above lower-level robot control.
ER 2 adds video understanding, multi-step planning, progress checking and higher-level orchestration above lower-level robot control.
The updated model family supports multiple robots coordinating in shared spaces rather than treating each machine as an isolated agent.
Google separated higher-level planning from physical control while broadening multi-step task execution.
Action-conditioned predictive models are used to improve generalizable embodied decision-making.
Google broadened dexterity, multi-step execution and the separation of higher-level planning from physical control.
Researchers map attacks across sensing, world modelling, planning, execution, feedback and long-term adaptation.
The World Action Planner uses action-conditioned world models to improve generalizable robot decision-making.