机器人学会两只手配合干活了
以前教机器人用手，基本只教一只手，另一只手要么闲着要么只会简单扶着。这篇让机器人学会像人一样两只手分工配合：一只手稳住物体，另一只手做精细操作，而且不是针对某个特定动作练出来的，是跨任务、跨数据源一起学的。研究者自己建了一个 1575 段、覆盖 229 个物体的双手交互数据集，再用强化学习加行为克隆的循环，把成功的执行结果回收成新训练数据，让一个模型在没见过的物体上也能有 57% 的成功率，比之前的双手追踪方法高出 45 个百分点以上。它不是你明天能用上的东西，但这是机器人从「单手玩具」走向「双手帮手」的一个实在台阶。
📄 原文摘要(英文)
Despite recent progress in dexterous reference tracking, existing models focus primarily on single-hand manipulation and a limited range of interactions, leaving the bimanual dexterous behaviors common in real life unaddressed. The scarcity of contact-rich bimanual manipulation data and the increased complexity of coordinating contacts make developing a generalist bimanual tracker particularly challenging. Therefore, we present 1) DONIC, the first generalist bimanual tracker jointly trained across operation categories and human-motion sources, together with 2) BiHOI, a multi-view dataset of 1,575 sequences spanning 229 objects and emphasizing sustained bimanual interaction, where reconstructed interactions are retargeted into robot references. DONIC combines proximal policy optimization with behavioral cloning in a feedback loop that recycles verified successful executions into training demonstrations. An object-centered per-hand reward maintains object-motion feedback while supervising each hand according to its reference contact role. Clip-Centered Advantages remove reference-dependent advantage offsets while preserving within-trajectory differences. Together, these designs enable one single policy to learn coordinated manipulation across heterogeneous references. Without finetuning, a single checkpoint achieves 86.79% success on unseen trajectories of training objects and 57.32% on held-out objects, surpassing the state-of-the-art bimanual tracking baselines by 77.36 and 45.73 percentage points.