Resolution criteria

This market will resolve to the date of publication of the first study, test report, or review from a reputable, independent consumer testing organization, scientific journal, or major technology news outlet (such as Consumer Reports, IEEE Spectrum, Wired, CNET, Nature, or Science) demonstrating that a commercially available, fully autonomous home robot or integrated home robotic system has successfully automated household cleaning with a 99% or higher success rate.

To satisfy the resolution criteria, the published report must verify that the technology meets the following standards:

• Fully Autonomous: The robot(s) must execute tasks entirely through onboard AI and sensor suites without requiring active physical human assistance, on-site human cleaning labor, or remote teleoperation (passive remote monitoring is permitted).

• Housekeeping Tasks: The system must successfully perform at least three of the following standard tasks:

  1. Floor care (vacuuming and mopping floors).

  2. Tidying and object rearrangement (identifying misplaced items, clearing clutter, and putting them away).

  3. Surface cleaning (wiping down countertops, tables, or dusting furniture).

  4. Dish management (loading, running, and unloading a dishwasher).

  5. Laundry (washing, drying, and folding clothes).

• 99% Success Rate: The reported success rate must be 99% or higher, defined as completing the initiated tasks without critical errors (e.g., damaging property, getting permanently stuck, or failing to clean the area) across a testing sample of at least 50 unique household rooms or environments.

• Commercial Availability: The robotic system or robot-as-a-service program must be commercially available for purchase or hire by the general public at the time of the publication.

If no such verified report is published by December 31, 2060, the market will resolve to by December 31, 2060,.

Background

While autonomous floor cleaning (via advanced LiDAR and AI-enhanced robot vacuums) has become highly commoditized, full household automation remains a significant challenge. Private residences represent highly unstructured, highly varied physical environments.

To bridge this gap, modern physical AI startups are actively gathering massive human-demonstration datasets to train general-purpose humanoid robots for home chores. Companies like Shift and Tau Robotics are deploying teleoperated and semi-autonomous systems to train models on real-world cleaning workflows. However, achieving a 99% success rate across arbitrary household layouts, fragile items, and dynamic obstacles remains a major milestone for robotics researchers.