Starset Society 中文镜像站

谷歌研究人员使用AI来教机器像真正的狗一样移动

Google Researchers Use AI to Teach Robots to Move like Real Dogs

Google researchers have used artificial intelligence (AI) to teach robots how to move with the agility of real animals (in this case, dogs). They describe their experiment in a blog released this week.

谷歌的研究人员已经使用人工智能(AI)来教机器人(注:所指的是图中的机器人)如何像真正的动物那样敏捷地移动,他们在本周发布的博客中描述了他们的实验。

“First, we describe how robots can learn agile behaviors by imitating motions from real animals, producing fast and fluent movements like trotting and hopping. Then, we discuss a system for automating the training of locomotion skills in the real world, which allows robots to learn to walk on their own, with minimal human assistance,” shared in the blog Xue Bin (Jason) Peng, Student Researcher and Sehoon Ha, Research Scientist, Robotics at Google.

谷歌的学生研究员薛斌(杰森)彭和研究科学家Sehoon Ha在博客中分享道:“首先,我们描述了机器人如何通过模仿真实动物的动作来学习的、如何做出快速流畅的动作的,就比如小跑和跳跃;那么接下来,我们讨论一个在现实世界中自动化运动技能训练的系统,它允许机器人在最少的人为帮助下学会自己走路。”

They achieved this impressive feat by using something called reinforcement learning (RL). They began by taking a reference motion clip recorded from an animal and using RL to get the robot to imitate those motions.

他们通过使用所谓的强化学习(RL)实现了这一令人印象深刻的壮举;从一个动物的参考动作剪辑开始,然后用RL让机器人模仿这些动作。

Read more at Interesting Engineering

翻译:SGCS翻译组

STARSET_Mirror

评论