World Labs says simulation-trained robot policies ran for an hour across five platforms

World Labs, the AI startup founded by Fei-Fei Li, says its Real-to-Sim-to-Real (R2S2R) engine trained robot policies entirely in simulation that ran autonomously for one hour on RB-Y1, YAM, Flexiv, and xArm systems, with ALOHA used for separate demonstrations. The company evaluated policy ranking with 2,000 simulated and 100 real cube-handover trials per checkpoint but did not disclose success rates for the one-hour runs or provide independent replication.

World Labs says simulation-trained robot policies ran for an hour across five platforms - World Labs says its Real-to-Sim-to-Real engine converts one physical task into thousands of variations covering object configuration, clutter, lighting, physics, robot state and camera viewpoint. 1 https://www.worldlabs.ai/blog/real-to-sim-to-real - Policies trained entirely in simulation ran autonomously for one hour on RB-Y1, YAM, Flexiv and xArm systems; ALOHA was used for separate training and evaluation demonstrations. 1 https://www.worldlabs.ai/blog/real-to-sim-to-real 2 https://the-decoder.com/world-labs-turns-one-real-world-robot-task-into-thousands-of-simulated-variations-for-training/ - The company evaluated policy ranking with 2,000 simulated and 100 real cube-handover trials per checkpoint, but did not disclose success rates for the one-hour runs or provide an independent replication. 1 https://www.worldlabs.ai/blog/real-to-sim-to-real World Labs says it has built a robot-training system that turns one physical task into thousands of controllable simulations, then transfers policies trained without real-world data onto physical robots. In demonstrations published July 28, the policies ran autonomously for one hour on tasks involving cables, power cords, test tubes and thin objects in clutter. 1 https://www.worldlabs.ai/blog/real-to-sim-to-real The startup, founded by Fei-Fei Li, calls the system Real-to-Sim-to-Real, or R2S2R. It comes from SceniX, a robotics and simulation company that joined World Labs on July 21. 3 https://www.worldlabs.ai/blog/scenix From one task to thousands of variations R2S2R begins with a physical robot, its sensors, the surrounding environment, the objects involved and a task demonstration. World Labs says it reconstructs those elements as an interactive simulation that preserves task-relevant observations and physical interactions, then varies appearance, object configuration, clutter, friction, robot state and camera viewpoint. 1 https://www.worldlabs.ai/blog/real-to-sim-to-real The company showed examples involving rigid, articulated and deformable objects. They included cable sliding and plugging with a YAM robot, elastic-cable insertion with ALOHA, power-cord routing around a refrigerator with RB-Y1, and a bimanual cube handover with ALOHA. 1 https://www.worldlabs.ai/blog/real-to-sim-to-real This differs from World Labs’ earlier public robotics work with Marble, its generative 3D-world product. Marble’s published case study describes generating scenes and exporting Gaussian splats and collision meshes into tools including NVIDIA Isaac Sim, MuJoCo and RoboSuite. R2S2R instead focuses on reconstructing a particular physical task closely enough to train and evaluate robot policies. 4 https://www.worldlabs.ai/case-studies/1-robotics The hardware demonstrations World Labs says policies trained entirely in simulation transferred directly to physical systems and ran without human intervention for one hour. The hour-long demonstrations covered power-cord manipulation with RB-Y1, sustained cable manipulation with YAM, tight-tolerance test-tube transfer with Flexiv, and marker and pencil singulation with xArm. ALOHA was used for the bimanual box-packing and cube-handover demonstrations, but the release does not identify an ALOHA one-hour run. 1 https://www.worldlabs.ai/blog/real-to-sim-to-real 2 https://the-decoder.com/world-labs-turns-one-real-world-robot-task-into-thousands-of-simulated-variations-for-training/ The release gives task descriptions and run durations, but it does not provide success rates, cycle counts, interruption counts or failure distributions for those one-hour demonstrations. The evidence establishes extended autonomous runs under the company’s test conditions; it does not show how often the robots would complete the same tasks across repeated trials or in less controlled environments. 1 https://www.worldlabs.ai/blog/real-to-sim-to-real That distinction matters because simulation-trained policies can still degrade on real hardware when dynamics, sensor noise or environmental conditions differ. NVIDIA’s SPARR project, for example, describes the sim-to-real gap as a continuing problem and adds a real-world residual policy to correct discrepancies after simulation pretraining. 5 https://research.nvidia.com/labs/srl/projects/sparr/ A narrower evaluation claim World Labs separately tested whether its simulator could predict which policies would perform better on real hardware. The test used an ALOHA cube-handover task and compared policy architectures, training configurations and checkpoints in simulated and physical rollouts. Each checkpoint received 2,000 simulated trials—1,000 in-distribution and 1,000 out-of-distribution—and 100 real trials split evenly between the two settings. 1 https://www.worldlabs.ai/blog/real-to-sim-to-real The company says simulation preserved the relative ranking of policies, tracked improvements and plateaus during training, and identified similar spatial regions of success and failure. It also showed paired near-boundary successes and matching failures between simulation and reality. 1 https://www.worldlabs.ai/blog/real-to-sim-to-real Those results support a practical use for the system: screening weak checkpoints in simulation and reserving physical tests for the most promising candidates. They do not show that simulation reproduces real-world success rates exactly. World Labs explicitly frames the simulator’s value as supporting decisions such as ranking policies and locating failure regions. 1 https://www.worldlabs.ai/blog/real-to-sim-to-real The July 28 post does not link to a peer-reviewed paper, public benchmark code or an independent replication. Whether the approach transfers to longer-horizon tasks, unfamiliar objects, outdoor settings or everyday clutter remains unresolved. Companies mentioned Further sources 1 World Labs’ July 28, 2026 technical release describing the Real-to-Sim-to-Real … ↗ https://www.worldlabs.ai/blog/real-to-sim-to-real 2 The Decoder’s August 15, 2026 report clarifying that ALOHA was one test platfor… ↗ https://the-decoder.com/world-labs-turns-one-real-world-robot-task-into-thousands-of-simulated-variations-for-training/ 3 World Labs’ July 21, 2026 announcement that SceniX joined the company, and Worl… ↗ https://www.worldlabs.ai/blog/scenix 4 World Labs’ November 12, 2025 case study describing Marble’s generated environm… ↗ https://www.worldlabs.ai/case-studies/1-robotics 5 NVIDIA Research’s SPARR project page describing continuing sim-to-real degradat… ↗ https://research.nvidia.com/labs/srl/projects/sparr/ The stories that matter, in one email. Free — unsubscribe anytime.