← 研踪 PaperTrailarXiv:2611.20185 · v1
RoboKit: Accelerating Parallel Differentiable Optimization for Robot Learning
首次提交 2026-11-16 02:40
版本更新 2026-11-16 02:40
雷达观测 2026-11-17 12:06
摘要
We present RoboKit, a high-performance, general-purpose toolkit for parallel differentiable optimization in robotics, built on three principles: (i) Performance and flexibility: GPU-parallel multi-seed solvers pair sampling with versatile optimizers, running 2-60 faster than task-specific baselines across seven tasks; (ii) Geometry, rendering and physics: hybrid and coarse-to-fine representations accelerate collision, differentiable rendering and simulation, optimizing 4096 grasps in 2.97 s; (iii) Integration with learning: costs are differentiable and simulation is parallel, so RoboKit both distills optimization into policies and trains RL; distilled policies run 9-240 faster at comparable accuracy, and RL reaches a GPU baseline's scores up to 2.1 sooner on the same simulator.
作者备注:Accepted to CoRL 2026. Project page: https://openrobokit.com/robokit
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-16 02:40 · 最新观测版本
RoboKit: Accelerating Parallel Differentiable Optimization for Robot Learning
We present RoboKit, a high-performance, general-purpose toolkit for parallel differentiable optimization in robotics, built on three principles: (i) Performance and flexibility: GPU-parallel multi-seed solvers pair sampling with versatile optimizers, running 2-60 faster than task-specific baselines across seven tasks; (ii) Geometry, rendering and physics: hybrid and coarse-to-fine representations accelerate collision, differentiable rendering and simulation, optimizing 4096 grasps in 2.97 s; (iii) Integration with learning: costs are differentiable and simulation is parallel, so RoboKit both distills optimization into policies and trains RL; distilled policies run 9-240 faster at comparable accuracy, and RL reaches a GPU baseline's scores up to 2.1 sooner on the same simulator.
查看此版本解读 →查看此版本原文 ↗