Reward AI's OM-1 Model Achieves Stable Grip on Humanoid Stairs

1 reports archived1 independent sourcesupdated 10/28/2026, 03:36:18

Synthesis & Latest Updates

1 Sources Cross-Validated

Reward AI demonstrates its OM-1 model's capability to maintain grip stability during humanoid locomotion. The model learns from human data via sensorized gloves without teleoperation or robot demos, enabling robust last-mile delivery tasks in complex environments like stairs.

LATEST/Reward AI demonstrates its OM-1 model's capability to maintain grip stability during humanoid locomotion. The model learns from human data via sensorized gloves without teleoperation or robot demos, enabling robust last-mile delivery tasks in complex environments like stairs.

Hourly heat curve

2 fully observed hours

Fewer than 3 fully observed hours; trend not plotted yet.

Coverage timeline

Total 1 reports · Latest first

Rohan Paul (@rohanpaul_ai)T2Oct 28, 03:36·68 pts
Reward AI's OM-1 Model Achieves Stable Grip on Humanoid Stairs
- The OM-1 model solves the challenge of maintaining grip stability amidst locomotion vibrations
- Utilizes human demonstration data via sensorized gloves, eliminating traditional teleoperation
- Staircases are emerging as a critical benchmark for validating general manipulation capabilities in humanoids
View Related Reports & Analysis Original Source