Robot Control Viable with 32×32 Depth Input
yacineMTB · x · 2026-07-17
In the context of robot control, the discussant suggests that depth sensors are sufficient. Input can be downscaled to 32×32 pixels and then used to train a control model, which is already enough to support RL control.
The conversation also touches on robot "blindness" as a prominent issue, necessitating more reliable external inputs for perception. However, a counterpoint is raised that depth cameras have a limited effective range, which might be insufficient if mounted directly on a robot.
Related event: T800 Robot Combat Exposes Perception Flaws(3 posts)→
More from Embodied
- Physical world agent swarm demo shared on X — pduan · 2026-10-26
- Looking for a wearable mic with best battery life that feeds recordings to personal agents via MCP — altryne · 2026-10-26
- 'Lamp Swarm': a desk of lamp-shaped robots shows what physical AI work looks like — dee_hw · 2026-10-26
- Tencent's HiSTEVE 1.0: hierarchical VLA agent plays Minecraft with native keyboard and mouse, hits 85% SOTA — _akhaliq · 2026-10-26
- SJTU's VaM lets robots learn online from mistakes, 95%+ success over 4-hour autonomous runs — chris_j_paxton · 2026-10-26
- DIY humanoid PhoneGirl day 4: collision tests, servo rework, 160° knee bend — _Stocko_ · 2026-10-26