Robot Model Demonstrates Impressive Climbing Generalization
ChongZzZhang · x · 2026-07-11
A developer showcased the impressive generalization capabilities of their robotics model (AME-2). The model was trained for just 10 hours (3,000 iterations) on 4 GPUs, using only climbing data for a height of 48cm. In actual testing, however, it successfully generalized and completed a 70cm climbing task. The author attributes this success to the model's ability to understand and plan sensory-to-motor mappings.
More from Embodied
- DONIC hits 86.79% on bimanual dexterous tracking, crushing prior SOTA's 9.43% — liuziwei7 · 2026-10-27
- Bedrock Robotics raises $600M as its fully autonomous excavators do paid work on live job sites — Sethwinterroth · 2026-10-27
- AW-0 hits 80.8% on RoboTwin tasks, beating strongest baseline by 16 points — trevordarrell · 2026-10-27
- AW-0's code stream fixes world model prediction: picks mango where baseline grabs apple — trevordarrell · 2026-10-27
- AW-0 runs at 230ms on a single RTX 5090, 2.4x faster than autoregressive code planning — trevordarrell · 2026-10-27
- AW-0 debuts: one generative world action model plans in code, predicts, and controls robots — trevordarrell · 2026-10-27