11-20 更新 实时
首页/ 算力市场/ 正文

John Deere 5 吨滑移装载机经 AI 训练学会特技

算力市场 来源:Tom's Hardware 2026-11-20 18:00 0 阅读 机器翻译
John Deere 5 吨滑移装载机经 AI 训练学会特技

来自美国和瑞士的一组研究人员分享了一些视频,展示了一台身手极其灵活、敏捷而优雅的 John Deere 5 吨滑移装载机。一篇近期发表的论文《Heavy Metal Acrobatics》解释了这一令人瞠目的自主机器人壮举背后的原理。研究人员希望这项工作能对未来建筑、采矿和物料搬运等行业的重型机械自动化有所助益。它还表明,在仿真中进行的强化学习能够相当出色地迁移到现实世界。

研究人员利用强化学习,教会一台 5 吨重的 John Deere 滑移装载机自主完成复杂的特技动作。该系统在仿真中完成训练后迁移到真实机器上,能够用两个轮子保持平衡、在崎岖地形上行驶、旋转,并在安全落地前控制其铲斗。这项研究展示了 AI 驱动的自动化在重型建筑和工业机械领域的潜力。视频来源:@leggedrobotics / @ETH 论文:https://t.co/MT7fyZ54Hk#engineering #technology 2026年11月17日

如果你展开上方嵌入的视频,就能看到一台庞大的 332G 滑移装载机做出一些令人惊叹的特技动作。它用两个轮子来回跳跃、原地旋转,并在屈伸举升臂的同时保持平衡。而且,它在做这些动作时,看起来从不会有倾覆的危险。研究人员称,“只有少数顶尖的人类操作员”能够完成演示视频中那样的特技动作。

这台动作惊人的滑移装载机背后的技术主要是强化学习(RL),并结合了物理建模和神经网络模型。由于这类机械体量庞大、动力强劲且笨重,直接在硬件上进行强化学习被认为不切实际。于是,研究团队决定使用一套仿真系统进行训练,其中编程复现了 John Deere 332G 复杂的控制组合。随后,这些数据通过 sim-to-real 迁移应用到真实的滑移装载机上。仿真必须极其精确。

这台动作灵活的重型巨兽令人印象深刻,但 Heavy Metal Acrobatics 的研究背后当然有着一个根本目标。科学家们正在为“重型机械的动态自主控制”奠定基础。人们希望这能推动重工业设备领域实现更高程度的自动化。最终,自主控制应当比任何人类都更安全、更快速、更高效。

从这些展示重型机械灵活、高机动性的视频演示来看,AI 驱动的自动化空间显然比人们此前预想的更大。此外,看来成为一名熟练的重型机械操作员绝对不是一个不会被 AI 取代的职业。

译文由英文原文机器翻译,术语按行业惯例统一,可在文末展开原文核对。

查看英文原文(Autonomous 5-ton John Deere skid-steer loader trained to perform acrobatic maneuvers using AI)

Videos of an incredibly acrobatic, nimble, and graceful John Deere 5-ton skid-steer loader have been shared by a group of researchers from the U.S. and Switzerland. A recently published paper titled Heavy Metal Acrobatics provides the reasoning behind this eyebrow-raising autonomous robotics feat. It is hoped this research will be useful in the future automation of heavy machinery in industries like construction, mining, and material handling. It also demonstrates that reinforcement learning in a simulation can transfer remarkably well to the real world.

Researchers have used reinforcement learning to teach a 5-tonne John Deere skid-steer loader to perform complex acrobatic manoeuvres autonomously. Trained in simulation and transferred to a real machine, the system can balance on two wheels, navigate rough terrain, spin, and control its bucket before landing safely. The research demonstrates the potential of AI-driven automation for heavy construction and industrial machinery.Video Credit: @leggedrobotics / @ETH Paper: https://t.co/MT7fyZ54Hk#engineering #technologyNovember 17, 2026

If you unfurl the video embed above, you can see a hulking 332G skid-steer do some astonishing tricks. It hops back and forth on two wheels, pirouettes, and balances while flexing its lift arm. Moreover, it does these moves while never looking like it will teeter over. The researchers claim that “only a handful of elite human operators” have ever been able to pull off stunts as you see in the demo videos.

The technology behind the remarkable acrobatic skid-steer is mostly Reinforcement Learning (RL), with physics modeling and neural network models. As machinery like this is so big, powerful, and bulky, undertaking RL directly on the hardware wasn’t deemed practical. Instead, the research team decided to use a simulation programmed with the John Deere 332G’s complex array of controls for training. This data was subsequently applied to the actual skid-steer via a sim-to-real transfer. The simulations must be extremely accurate.

Heavy Metal Acrobatics
Heavy Metal Acrobatics
Heavy Metal Acrobatics
Heavy Metal Acrobatics

This acrobatic goliath is impressive, but of course there’s an underlying goal driving Heavy Metal Acrobatics’ research. The scientists are laying the foundations for the enabling of “dynamic autonomous control of heavy machinery.” It is hoped this will help promote greater automation in heavy equipment sectors of industry. Eventually, autonomous control should be safer, faster, and more efficient than any human.

With these video demonstrations of nimble and highly maneuverable heavy machinery, it is clear that there’s more scope for AI-driven automation than one may have previously expected. Furthermore, it looks like being a skilled heavy machinery operator is definitely not an AI-proof occupation.

正文保留英文原文,标题与摘要由机器翻译。

本文由采集器自动同步

原文发布于 Tom's Hardware(Autonomous 5-ton John Deere skid-steer loader trained to perform acrobatic maneuvers using AI),标题、摘要与正文由机器翻译,术语按行业惯例统一,未经人工逐句校订。

阅读原文 ↗