B-spline Makes Robot Arms Faster and Smoother
Haoyu_Xiong_ · x · 2026-07-15
This post introduces a new robotic manipulation method: B-spline Policy (BSP).
The author notes that while past manipulation evaluations often focused on success rate, speed is equally important. Instead of predicting discrete, fixed-frequency action chunks like traditional methods, BSP parameterizes actions as continuous B-spline curves.
They claim that this representation, combined with the system design, enables low-cost robotic arms to achieve faster and smoother manipulation. The post also emphasizes:
- The project is co-led by multiple researchers;
- The included video shows the robot moving significantly faster than the baseline;
- The video footage is recorded in real-time.
Related event: B-spline Policy proposes faster, smoother robot manipulation(5 posts)→
More from Embodied
- NVIDIA open-sources FLORA, a robotics data engine ~125x cheaper than GPT-6 Astra — nvidia · 2026-10-27
- Embodied AI startups need a different operational discipline, investor says — ___Mufasaa · 2026-10-27
- π0.5 study: raising demos from 10 to 438 lifts Place Ball in Bowl success from 7% to 83% — stingning · 2026-10-27
- GPT-6 Astra controls dexterous hands zero-shot at just 5.2% success in 500 trials — stingning · 2026-10-27
- HandsOn benchmark: 66 verified tasks and 18,000 human demos for dexterous manipulation — stingning · 2026-10-27
- DexPort: a handheld interface with a real robot hand for dexterous-hand data collection — pabbeel · 2026-10-27