人形/四足变形金刚像行李搬运工一样扔箱子
ANYmal外形小巧,四足行走,看起来就像一只带轮子的机器狗 Swiss Mile
Swiss Mile's ANYmal robot is a remarkable beast, capable of getting around as a wheeled quadruped, or standing up on its hind legs and using its front wheels as hands. Now, it's learning to do useful tasks – in about the funniest way possible.
Swiss Mile公司的ANYmal机器人是一种非凡的动物,它可以像带轮子的四足动物一样四处走动,或者用后腿站立,用前轮当手。现在,它是学习做有用的任务——以一种可能的最有趣的方式。
The architecture here is pretty phenomenal in its own right; ANYmal is a great name for this thing. It looks like a robot dog in quadruped mode – albeit one with rather fiddly looking legs, as well as the odd inclusion of wheels. But that makes for super-efficient locomotion across a range of even and uneven surfaces, including stairs. Why walk when you can roll – and indeed, why waste energy on bipedal balancing when you can get around on four legs much more easily?
这里的架构本身就非常惊人;ANYmal是一个很好的名字。它看起来就像一只四足机器狗——尽管它的腿看起来相当灵巧,还奇怪地装了轮子。但这使得机器人在一系列平坦和不平坦的表面(包括楼梯)上都能超高效地移动。当你能滚的时候,为什么要走呢?事实上,当你可以更容易地用四条腿走动时,为什么要浪费精力用两条腿来保持平衡呢?
But, as the humanoid-focused companies point out, a lot of the tasks we want robots to take over are currently designed for the human form. And when it needs to act more like a human, ANYmal simply squats back and stands up, using its motorized wheels to self-balance. Here, look at this video from a year ago:
但是,正如专注于类人型机器人的公司所指出的那样,我们希望机器人接管的许多任务目前都是为人类设计的。当它需要表现得更像人类时,ANYmal只需向后蹲下,然后站起来,用它的电动轮来实现自我平衡。来,请看一年前的这段视频:
Advanced Skills through Multiple Adversarial Motion Priors in Reinforcement Learning
强化学习中通过多个对抗性运动先验的高级技能
Standing up leaves its front legs free to act as arms. And while it would be totally possible to have a set of hands tucked away that could fold out for dextrous manipulation in humanoid mode, the team at Swiss Mile – an ETH Zurich spinout company – has decided to see just how much this bot can get done using nothing but its powered wheels as hands.
站起来后,它的前腿就可以充当手臂了。虽然在人形模式下完全有可能有一双折叠起来的手,可以灵活地进行操作,但苏黎世联邦理工学院的子公司Swiss Mile的团队已经决定看看这个机器人只用它的动力轮作为手能完成多少工作。
One of the earliest such tasks, as shown in the video above, was pressing elevator buttons – fairly remarkable in itself when you consider the precision that requires as opposed to the rather blunt instrument of an 8-10-inch (20-25-cm) diameter wheel.
最早的此类任务之一,如上面的视频所示,是按电梯按钮-本身相当了不起,当你考虑到需要的精度,而不是一个8-10英寸(20-25厘米)直径的轮子相当钝的工具。
While the above video had the ANYmal approaching tasks from reinforcement learning and imitation learning perspectives, and attempting to reverse certain motions in order to achieve the opposite task, the team has more recently been experimenting with a new technique it's calling "curiosity-driven learning."
在上面的视频中,ANYmal从强化学习和模仿学习的角度来处理任务,并试图扭转某些动作以完成相反的任务,而团队最近一直在尝试一种新的技术,它被称为“好奇心驱动的学习”。
The ANYmal robot has taught itself to throw boxes into bins in a way that would make airport baggage handlers proud Swiss Mile
ANYmal机器人已经学会了将箱子扔进垃圾箱的方法,这种方法会让机场的行李搬运工感到骄傲。
In the new approach, the robot is given a task, rewarded only when it completes the task, and encouraged to explore and play with goal-related items in its environment, effectively being told to just get in there and figure things out for itself.
在新的方法中,机器人被赋予一个任务,只有当它完成任务时才能得到奖励,并鼓励机器人在其环境中探索和玩与目标相关的物品,有效地被告知只要进入那里,自己弄清楚事情。
So nobody needs to go in there and do the tedious work of designing complex reward schemes to guide the robot toward its goal. And nobody needs to sit there and demonstrate the task a hundred times over so the robot can watch and learn. You just need to set some key variables, point out objects that could be significant to the task, and give the robot its final goal.
因此,没有人需要去那里,做繁琐的工作,设计复杂的奖励计划,以引导机器人向它的目标。而且没有人需要坐在那里把任务演示一百遍,这样机器人就可以观察和学习。你只需要设置一些关键变量,指出可能对任务有重要意义的对象,并给出机器人的最终目标。
A remarkably capable robot when it comes to efficient locomotion across a broad range of surfaces
In testing, this technique is already delivering impressive results – the ANYmal learned to open doors well enough to nail the task 15 times in a row, for example, and also figured out how to pick up a box and put it in a bin – which is going to be one of the key early jobs needed from general-purpose robots as they start entering the workforce.
在测试中,这项技术已经取得了令人印象深刻的结果——ANYmal学会了足够好的开门能力,可以连续15次完成任务。例如,它还弄清楚了如何拿起一个盒子并把它放进一个箱子里——这将是通用机器人进入劳动力市场所需要的关键早期工作之一。、
But the fun here is in how the ANYmal gets the job done – given the simple goal of "get box into bin," it's learned to pick them up and fling them at the bin in a way that would make airport baggage handlers proud. There's something wonderfully... relatable, perhaps, about the way it chucks those boxes. Enjoy the video below.
但有趣的是ANYmal是如何完成工作的——考虑到“把箱子放进垃圾箱”这个简单的目标,它学会了把箱子捡起来并扔向垃圾箱,其方式会让机场的行李处理员感到骄傲。有一种奇妙的...也许,它扔箱子的方式让人产生共鸣。请欣赏下面的视频。
Curiosity-Driven Learning of Joint Locomotion and Manipulation Tasks
好奇心驱动的联合运动和操作任务的学习
At this stage, ANYmal is more of a research project than anything else. But Swiss Mile could move to commercialize it, and this bot's remarkable transforming capability could be a real game changer, combining the advantages of a humanoid form with the compact, efficient locomotion of a wheeled quadruped. Very neat work!
在这个阶段,ANYmal更多的是一个研究项目,而不是别的。但Swiss Mile可以将其商业化,而这个机器人非凡的变形能力可能会成为一个真正的游戏规则改变者,它将人形机器人的优点与轮式四足机器人紧凑、高效的移动结合在一起。非常整洁的工作!
Source: Swiss Mile via IEEE Spectrum
资料来源: Swiss Mile通过IEEE频谱
智能佳机器人
400 099 1872
www.bjrobot.com