Two Papers Show B-Spline Action Parameterization Improves Manipulation Learning
ChongZzZhang · x · 2026-07-30
The post shares two papers related to robot policies (Spline policy and B-Spline policy). The author notes that both studies demonstrate that using spline action parameterization aids in manipulation learning, with the first paper containing more mathematical equations.
Related event: B-Spline Action Parameterization Enhances Robot Learning(2 posts)→
More from Embodied
- Musk Declares 'Money Won't Matter by 2036' as Humanoid Robots Create Infinite Economy — r0ck3t23 · 2026-07-30
- Shenzhen's LIGHTBOT-0 Navigates Complex Terrain with Single Policy and Depth Only — CyberRobooo · 2026-07-30
- Advantech Edge Device Powered by Nvidia Thor Runs RealSense GMSL Cameras — chrismatthieu · 2026-07-30
- Stanford's Open-Source Pupper Robot Dog Powered by Gemini Robotics Model — DynamicWebPaige · 2026-07-30
- Robotics Leaders on How World Models Drive Real-World Deployment — Scobleizer · 2026-07-30
- The Humanoid Dilemma: Servitude, Co-existence, or Human Obsolescence? — wavefnx · 2026-07-30