论文/arXiv 2610.17208·16 天前

DexNinja：用 Real-to-Sim-to-Real 数据引擎学习鲁棒灵巧切割策略

DexNinja针对灵巧切割数据昂贵与仿真鸿沟，用real2sim2real生成训练分布，并在食物切片任务上验证。

AI 整理

• 仿真与训练
• 数据与采集

原文链接：DexNinja: Learning Robust Dexterous Cutting Policy with a Real-to-Sim-to-Real Data Engine（arXiv 2610.17208 · 发布日期：2026-10-12）

DexNinja: Learning Robust Dexterous Cutting Policy with a Real-to-Sim-to-Real Data Engine

DexNinja针对灵巧切割数据昂贵与仿真鸿沟，用real2sim2real生成训练分布，并在食物切片任务上验证。

核心要点

• 灵巧切割涉及高接触、可变形和拓扑变化物体，真实采集昂贵且易污染或损坏食物。
• 方法从少量真实演示重建物体实例，按类别约束随机化物理参数，生成增强操作片段。
• 自定义可微仿真器耦合机器人动力学、触觉接触与可变形切割，支持数据增强。
• 在食物切片任务中，数十个真实演示加数百仿真数据成功率超过60%，并提升超20%。

验证范围与局限：验证范围为灵巧食物切片任务，包含真实演示与仿真增强数据，并测试不同形状和尺寸的分布外物体。

英文摘要 (Abstract)

Cutting a piece of food looks effortless in human hands. For a robot, however, every cut is a high-contact interaction with a deformable, elasto-plastic object whose behavior changes with pose, contact mode, and cutting stage. Collecting real-world data is expensive and wasteful: each trial typically contaminates or damages the food, so obtaining scalable real world data for dexterous cutting is expensive and difficult. Simulation is an appealing alternative, but a large sim-to-real gap exists in both physics and perception. This gap is especially severe for topology-changing interactions like cutting, where small errors in contact, friction, or material and elasticity responses quickly compound. We propose \textsc{DexNinja}, a real2sim2real framework that turns a handful of real demonstrations into a dense and realistic training distribution. \textsc{DexNinja} (i) reconstructs object instances from real captures, (ii) randomizes physically meaningful parameters under category-level constraints, and (iii) produces augmented dexterous manipulation episodes using a custom differentiable simulator that couples robot dynamics, tactile contact, and deformable cutting. We evaluate \textsc{DexNinja} on a dexterous food-slicing task and show that (1) with tens of real demonstrations and hundreds of augmented simulator data, the success rate could reach more than 60%. (2) the augmented data consistently improves success rates when only using real data with more than 20% via sim-to-real, and (3) the resulting policies generalize to out-of-distribution objects with varying shapes and sizes.

作者：Haozhe Lou, Runyi Yang, Wanqi Zhong, Caiyun Liu, Yicheng Liu, Wenhao Liu, Wenlong Ma, Jiawei Xia, Kanzhi Wu, Danda Pani Paudel

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.17208：DexNinja: Learning Robust Dexterous Cutting Policy with a Real-to-Sim-to-Real Data Engine访问 2026-10-21