内容来源：https://www.wired.com/story/this-ai-powered-robot-keeps-going-even-if-you-attack-it-with-a-chainsaw/

内容总结：

初创公司Skild AI研发“全能机器人大脑”，机器人断腿后仍能爬行引关注

想象一下，一台四足机器人即使被电锯切断所有腿，仍能继续爬行——这场景对大多数人而言如同噩梦，但对初创公司Skild AI的联合创始人兼首席执行官迪帕克·帕塔克来说，这却代表了机器人适应性的一大突破，是迈向通用机器人智能的鼓舞人心的信号。

帕塔克将这一技术称为“全能身体大脑”。其核心目标是解决机器人技术发展的一个关键瓶颈：用“一个大脑”控制“任何机器人”完成“任何任务”。与许多研究者的观点一致，Skild AI团队认为，如果能收集足够多的训练数据，机器人AI模型有望迎来类似ChatGPT等大语言模型的飞跃式进步。

与传统方法（如通过远程操作或模拟训练算法控制特定机器人）不同，Skild的策略是让单一算法学习控制大量不同形态的物理机器人，执行多种任务。通过这种方式训练出的模型——“Skild大脑”——获得了更强的通用性，甚至能适应从未见过的机器人形态。该模型还具备快速适应新状况的能力，例如腿部缺失或复杂地形，其原理类似于大语言模型通过“情境学习”分解难题、迭代思考的过程。

尽管丰田研究院等机构及竞争对手也在开发通用机器人AI，但Skild的独特之处在于其模型能泛化至如此多不同类型的硬件。在实验中，团队训练的算法成功让未参与训练的真实两足、四足机器人实现行走。更令人惊讶的是，当一台四足机器人被扶起仅用后腿站立时，算法能感知地面并像控制人形机器人一样让其用后腿“散步”。即使面对腿部被绑、截断或加长等极端形态变化，甚至部分电机被禁用，机器人也能迅速调整策略，例如像不稳的自行车一样用两个轮子保持平衡。

除了移动能力，Skild也将该技术应用于机械臂操控。测试表明，经过训练的模型能控制陌生型号的机械臂，并适应环境突变（如光线骤暗）。帕塔克透露，公司已与一些使用机械臂的企业展开合作，并于2024年完成3亿美元融资，估值达15亿美元。

帕塔克承认这些成果可能令一些人感到不安，但他本人则视之为机器人“物理超级智能”的萌芽，并对此充满热情。这一技术的未来发展及其伦理影响，正引发业界广泛关注。

中文翻译：

一个四足机器人即使四条腿都被电锯锯断后仍能继续爬行，这对大多数人来说简直是噩梦般的场景。但对于初创公司Skild AI的联合创始人兼首席执行官迪帕克·帕塔克而言，这种反乌托邦式的适应能力恰恰预示着一种全新、更通用的机器人智能正在崛起。

"我们称之为'全能躯体大脑'"，帕塔克向我解释道。他的团队开发这款通用人工智能算法，旨在攻克机器人技术发展的核心难题："任何机器人，任何任务，只需一个大脑。这达到了荒谬的通用程度。"

许多研究者认为，只要能收集足够多的训练数据，用于控制机器人的AI模型将迎来类似语言模型和聊天机器人的飞跃性进展。帕塔克指出，现有训练方法如远程操作或模拟训练难以产生足量数据。

Skild的解决方案是让单一算法学习控制各类物理机器人执行多样化任务。经长期训练，这套被命名为"Skild大脑"的模型获得了适应不同物理形态的通用能力——包括从未见过的全新形态。为配合学术论文发表，团队还开发了精简版模型LocoFormer。

该模型专为快速适应新情境设计，无论是肢体缺损还是险峻地形，都能运用既有经验应对困境。帕塔克将其类比于大语言模型处理复杂问题时的"情境学习"机制：将问题分解后纳入上下文窗口进行推演。

尽管丰田研究院及竞品公司Physical Intelligence也在研发通用机器人AI模型，但Skild的独特之处在于其模型能跨越多类硬件平台实现泛化。在一项实验中，团队训练算法控制多种异形步行机器人。当算法部署于训练数据未包含的双足/四足实体机器人时，竟能自如控制其移动。

令人惊叹的是，搭载"全能大脑"的四足机器人在被强制站立时，能通过后肢触感感知地面，立即以类人机器人模式用后腿行走。该算法甚至能应对机器人结构的极端改变——当腿部被捆绑、切除或加长时，机器人仍能调整行动模式。团队还尝试禁用四轮腿机器人的两个电机，机器人竟能像失衡自行车般用两轮保持平衡。

Skild将相同技术应用于机械臂操控领域。经多款模拟机械臂训练的Skild大脑不仅能操控陌生硬件，还能适应光照骤变等环境突变。帕塔克透露公司已与多家机械臂应用企业展开合作，并于2024年完成3亿美元融资，估值达15亿美元。

帕塔克承认这些成果可能令人不安，但他从中窥见了机器人物理超智能的曙光："老兄，这实在让我个人兴奋不已。"您如何看待Skild的多才多艺机器人大脑？欢迎发送邮件至ailab@wired.com分享见解。

本文节选自威尔·奈特《AI实验室》时事通讯，往期内容请点击此处查阅。

英文来源：

A four-legged robot that keeps crawling even after all four of its legs have been hacked off with a chainsaw is the stuff of nightmares for most people.
For Deepak Pathak, cofounder and CEO of the startup Skild AI, the dystopian feat of adaptation is an encouraging sign of a new, more general kind of robotic intelligence.
“This is something we call an omni-bodied brain,” Pathak tells me. His startup developed the generalist artificial intelligence algorithm to address a key challenge with advancing robotics: “Any robot, any task, one brain. It is absurdly general.”
Many researchers believe the AI models used to control robots could experience a profound leap forward, similar to the one that produced language models and chatbots, if enough training data can be gathered.
Existing methods for training robotic AI models, such as having algorithms learn to control a particular system through teleoperation or in simulation, do not generate enough data, Pathak says.
Skild’s approach is to instead have a single algorithm learn to control a large number of different physical robots across a wide range of tasks. Over time, this produces a model which the company calls Skild Brain, with a more general ability to adapt to different physical forms—including ones it has never seen before. The researchers created a smaller version of the model, called LocoFormer, for an academic paper outlining its approach.
The model is also designed to adapt quickly to a new situation, such as missing leg or treacherous new terrain, figuring out how to apply what it has learned to its new predicament. Pathak compares the approach to the way large language models can take on particularly challenging problems by breaking it down and feeding its deliberations back into its own context window—an approach known as in-context learning.
Other companies, including the Toyota Research Institute and a rival startup called Physical Intelligence, are also racing to develop more generally capable robot AI models. Skild is unusual, however, in how it is building models that generalize across so many different kinds of hardware.
In one experiment, the Skild team trained their algorithm to control a large number of walking robots of different shapes. When the algorithm was then run on real two- and four-legged robots—systems not included in the training data—it was able to control their movements and have them walk around.
At one point, the team found that a four-legged robot running the company’s omni-bodied brain will quickly adapt when it is placed on its hind legs. Because it senses the ground beneath its hind legs, the algorithm operates the robot dog as if it were a humanoid, having it stroll around on its hind legs.
The generalist algorithm could also adapt extreme changes to a robot’s shape—when, for example, its legs were tied together, cut off, or modified to become longer. The team also tried deactivating two of the motors on a quadruped robot with wheels as well as legs. The robot was able to adapt by balancing on two wheels like an unsteady bicycle.
Skild is testing the same approach for robot manipulation. It trained Skild Brain on a range of simulated robot arms and found that the resulting model could control unfamiliar hardware and adapt to sudden changes in its environment like a reduction in lighting. The startup is already working with some companies that use robot arms, Pathak says. In 2024 the company raised $300 million in a round that valued the company at $1.5 billion.
Pathak says the results might seem creepy to some, but to him they show the sparks of a kind of physical superintelligence for robots. “It is so exciting to me personally, dude,” he says.
What do you think of Skild’s multitalented robot brain? Send an email to ailab@wired.com to let me know.
This is an edition of Will Knight’s AI Lab newsletter. Read previous newsletters here.