roto 2.0 推出四类机器人触觉强化学习新基准，支持盲操作
roto 2.0: The Robot Tactile Olympiad
- 构建可并行的触觉强化学习基准，支持16-24自由度机器人
- 盲操下10秒完成13次宝珠旋转，速度超当前最佳一个数量级
- 开源环境与调优基线，降低算法研究门槛
基于触觉的强化学习（RL）目前受限于研究碎片化及对过饱和方向任务的过度关注。我们推出机器人触觉奥林匹克（ exttt{roto 2.0}）v2版本，一个基于GPU并行化的基准测试，旨在统一四种不同机器人形态（16-DOF至24-DOF）的触觉强化学习评估。与以往基准不同，roto聚焦端到端‘盲操’任务，仅依赖本体感觉与触觉感知，不使用状态信息或蒸馏技术。我们展示显著性能提升：盲操作代理在10秒内完成13次宝珠旋转，速度比当前最先进水平快一个数量级。通过开源环境与稳健调优的基线，我们降低了研究门槛，使研究人员能专注于基础算法挑战而非繁琐的强化学习调参。
原文摘要 · Abstract (English)
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/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。