AI Pulse
📄 论文解读

让AI摸到力:不训练也能学会拧瓶盖

现在的机器人AI是“睁眼瞎”:它看得见物体,却感觉不到力。拧瓶盖、插插头这些事,关键不在“看”而在“手感”,而手感是图像给不了的。这篇研究给冻结的模型装了个“力觉手套”:底层用自终止的力原语快速闭环,不让慢半拍的AI直接碰力;上层把力信号翻译成带不确定性的物理量,让AI能像读数字一样读力。结果很猛:在真实机械臂上,GPT-6 Astra的零样本成功率从3.3%飙到90%。它不是你明天能用的产品,但它指了个方向——下一代机器人AI可能不是更聪明的模型,而是更聪明的“传感器翻译官”。

📄 原文摘要(英文)

Frontier multimodal models can now control robots zero-shot from images, yet many manipulation tasks depend on contact forces that images cannot show. Bringing force to an API-only frozen model raises two challenges. First, contact evolves much faster than an API model can decide, so the system must close the loop on force beneath the model. Second, a frozen model cannot interpret raw force streams, so force must be returned in a form the model can reason about. Therefore, we present ForceHarness, a harness that lets frozen models use force without demonstrations or finetuning. After calibrating hand force from a wrist sensor or joint torques alone, ForceHarness addresses the first challenge with self-terminating force primitives that regulate force on their own and return at a contact event. To address the second challenge, a physics translation layer turns each force trace into physical quantities with uncertainty as the tool result. To evaluate ForceHarness against expert force controllers and learned policies under identical conditions, we also build HiddenPhys, a seven-task MuJoCo benchmark with hidden physical variables. On a real arm without a wrist force sensor, ForceHarness raises the zero-shot success rate of GPT-6 Astra from 3.3% to 90.0%. In simulation, it adds 17.5 percentage points on the public ForceBench suite and 34.3 percentage points on HiddenPhys, surpassing force-aware policies trained on demonstrations on both benchmarks and matching hand-written expert controllers on HiddenPhys. Ablations further show that smaller models make significantly better decisions when given physical quantities rather than raw force values.

arXiv 原文

订阅 AI Pulse

每天 08:00 · 12:30 · 18:30 · 23:50 更新