B-Spline Policy Speeds Up Robots
chris_j_paxton · x · 2026-07-16
This repost introduces B-spline Policy: a method that represents a robot's future actions as continuous B-spline curves.
The main ideas are:
- Instead of predicting fixed-frequency discrete action chunks, it predicts continuous parameter curves.
- Actions can be executed faster by altering the time steps sampled from the curve.
- Combined with system design, it significantly accelerates operational policies on low-cost robotic arms.
The author also noted that in their videos, the robot's movements were faster and smoother than baseline methods, with all demonstrations performed in real-time.
Related event: B-spline Policy proposes faster, smoother robot manipulation(5 posts)→
More from Embodied
- RealSense D585 Pro AI-Powered 3D Stereo Depth Camera Unboxed for Physical AI — chrismatthieu · 2026-10-26
- 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