ActOR: Ambient AI-Based Agentic Orchestration for Humanoid Autonomy in Operating Rooms
ActOR: Ambient AI-Based Agentic Orchestration for Humanoid Autonomy in Operating Rooms
This research introduces ActOR, a system that couples ambient AI with humanoid robots to enable autonomy in operating rooms. By fusing wall-mounted and head-mounted camera feeds into a shared digital twin, the system uses a large language model agent to plan locomotion and manipulation without task-specific training. Evaluation in simulated environments shows significant reductions in exploration calls and increases in task success rates, while physical tests in a mock OR demonstrate replanning capabilities after scene changes.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
's view. Closed-loop feedback increased success from 46.7% to 83.3% under nominal execution and from 8.3% to 51.7% under injected navigation, object-relocation, and grasp perturbations. In a physical mock OR with a humanoid, ActOR completed 14 of 20 single-object disposal trials and demonstrated replanning after scene changes. Ambient AI-based observations provide scene state that improves robot action planning, incr
Open source S5
arXiv:2611.04255v1 Announce Type: new Abstract: Operating rooms (ORs) increasingly contain ambient sensing infrastructure to enable AI-based optimization of workflows and utilization. We pursue an alternative path: using ambient AI to guide robot action and optimize utilization. Deploying humanoids in the OR without ambient AI is severely limited by cumbersome de novo orientation and planning due to partial onboard o
Open source S2
bservations. We posit that this can be achieved by coupling an ambient AI-based agentic orchestrator with the humanoid robotic actor, providing shared perception and execution feedback for humanoid autonomy in the OR. ActOR fuses a wall-mounted ambient camera and the robot's head-mounted camera into a shared object-level digital twin (DT). A large language model agent plans over the DT using pre-programmed locomotion
Open source S3
and manipulation skills without task-specific training. During execution, DT updates and execution outcomes inform retries, alternative approaches, or replanning. We evaluated ActOR in simulated and physical environments. Across three tasks in two simulated ORs reconstructed from real rooms, ambient perception reduced exploration from 1.05 to 0.12 Explore calls per trial when targets were initially outside the robot
Open source S4
Source：arXiv Robotics — research abstracts · arxiv.org