触觉 RL 终于有了标准化的 GPU 并行基准，做机器人操作和强化学习的团队可以直接用 roto 2.0 测试算法，不用再花时间调环境——盲操速度提升 10 倍的结果值得点开看看。
机器人触觉强化学习（RL）研究因碎片化和过度关注饱和的定向任务而受阻。roto 2.0 是一个 GPU 并行化的基准测试，覆盖四种不同机器人形态（16-24 自由度），专注于仅依赖本体感觉和触觉的“盲”操作，无需状态信息或知识蒸馏。其盲代理在 10 秒内完成 13 次 Baoding 球旋转，速度比当前最先进水平快一个数量级。通过开源环境和调优基线，该工作降低了入门门槛，让研究者能聚焦核心算法挑战。
roto 2.0: The Robot Tactile Olympiad
Tactile-based reinforcement learning (RL) is currently hindered by fragmented research and a focus on over-saturated orientation tasks. We introduce v2 of the Robot Tactile Olympiad (\texttt{roto 2.0}), a GPU-parallelised benchmark designed to standardise tactile-based RL across four distinct robotic morphologies (16-DOF to 24-DOF). Unlike prior benchmarks, roto focuses on end-to-end "blind" manipulation, utilising only proprioception and tactile sensing without state information or distillation. We demonstrate a significant performance leap, with our blind agents achieving 13 Baoding ball rotations in 10 seconds, an order of magnitude faster than current state-of-the-art speeds. By open-sourcing our environments and robustly tuned baselines, we reduce the barrier to entry and enable researchers to prioritise fundamental algorithmic challenges over tedious RL tuning. Website: https://elle-miller.github.io/roto/