本仓库包含 5 个基于 π0.5 的洗碗机餐盘操作 checkpoint。它们均使用 16 维直接动作表示（actiondim=32，包含双臂），动作预测 horizon 为 50；训练产物采用 JAX/Orbax checkpoint 格式。 circleLupload、circleMupload、squareupload 和 mixupload 是视觉-触觉策略。它们使用冻结的 facebook/sparsh-vjepa-base 作为触觉编码器，输入为相对于每个 episode 第 0 帧生成的 4 帧有序背景差分触觉序列： mixunload 不使用触觉输入或触觉编码器；它使用常规视觉/状态输入，并同样使用最近 8 步动作历史进行条件化。 - 五个顶层模型目录采用一致的结构：目录本身就是可加载的 Orbax checkpoint 根目录，下面直接包含 CHECKPOINTMETADATA、params/ 和 assets/。 - 每个 checkpoint 中的 assets//normstats.json 保存对应训练数据的归一化统计量；加载时应与同一 checkpoint 配套使用。 - circleLupload, circleMupload, squareupload, and mixupload are tactile π0.5 policies for loading large round, medium round, square, and mixed plates into a dishwasher rack, respectively. They…
Independent publisher
Zihao Wang
stumpferWinkel
Models in Library1
Datasets in Library0
Models on Hugging Face2
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Published tasks: Robotics.
Reported licenses: other. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.