TARS Robotics unveils embodied foundation model AWE: 15+ tasks, one model, zero retraining
heyshrutimishra · x · 2026-09-11
Robotics company TARS Robotics introduces its embodied-native foundation model, AI World Engine (AWE), built around physical intuition rather than canned trajectories: 15+ real-world tasks across domains, one foundation model, zero task-specific retraining, with adaptive force control and deformable manipulation. Skills reportedly remain useful even when objects, materials, or surroundings change — the poster highlights the per-moment decisions (when to pull, where to apply pressure, how to leverage gravity and tools) as the key to translating human instinct into robots.
More from Embodied
- Replit Agent in a robot builds and publishes websites autonomously via MCP — amasad · 2026-09-11
- Qualcomm's next-gen Hexagon NPU runs 30B MoE models with 32K context on-device — lee_stott · 2026-09-11
- Working with an ESP32 device using Copilot CLI and Astra — DanWahlin · 2026-09-11
- VATIX: open-source driving world model trained on 5,500 hours of real-world footage — abursuc · 2026-09-11
- Reachy Mini robot gains spotlight after joining NVIDIA's portfolio — RachelVT42 · 2026-09-11
- PhyFilter: physics-informed filter lets sim-trained robots traverse real terrain without extra data — 机器之心 · 2026-09-11