Evaluating 30+ Embodied AI Models Reveals Lack of Robustness
ZeYanjie · x · 2026-07-09
The authors evaluated over 30 frontier embodied AI models, concluding that current general robot policies are still far from achieving robust manipulation in the real world.
To address this, the team built RoboDojo to further research and evaluate the performance of embodied agents in real-world manipulation tasks.
Related event: RoboDojo Benchmarks 30+ Embodied AI Models: General Robotics Still Unstable(2 posts)→
More from Embodied
- Sunday Robotics says ACT-2 folds laundry with 99.1% zero-shot success, and Walden Robotics emerges at $1.1B — lukas_m_ziegler · 2026-07-22
- Walden Robotics launches at a $1.1B valuation with $300M from Toyota — lukas_m_ziegler · 2026-07-22
- Mimic Robotics unveils a 15-DOF hand and wearable exoskeleton — lukas_m_ziegler · 2026-07-22
- Anime meme turns 1X’s 25-DOF humanoid hand demo into a robotics joke — prajdabre · 2026-07-22
- Langy adds a Claude Code-style AI engineer for domain experts — _rchaves_ · 2026-07-22
- Sim2real and evaluation are becoming central to robotics simulation work — m_wulfmeier · 2026-07-22