AI Learns How to Act Like a Dog

An interesting collaboration between the University of Washington and the Allen Institute for AI results in a project that aims to get AI to simulate a dog.  People, of course, wonder why dogs? It has to be more than the fact that they are cute, furry, and man’s best friend. Indeed it is! Dogs were chosen because they are smart.  They are smart and complex yet we don’t know what they are really thinking about. We may think we do (“My dog loves to play ball.” Does he really? Or is he just pleasing you?), but we really don’t.

As an initial foray into this line of research, the team wanted to see if by monitoring the dog closely and mapping its movements and actions to the environment it sees, they could create a system that accurately predicted those movements.

In order to do so, they loaded up a Malamute named Kelp M. Redmon with a basic suite of sensors. There’s a GoPro camera on Kelp’s head, six inertial measurement units (on the legs, tail and trunk) to tell where everything is, a microphone, and an Arduino that tied the data together.

They recorded many hours of activities — walking in various environments, fetching things, playing at a dog park, eating — syncing the dog’s movements to what it saw. The result is the Dataset of Ego-Centric Actions in a Dog Environment, or DECADE, which they used to train a new AI agent.

Read the complete article on Tech Crunch

关于此作者

Image of Jenn Toso

Jenn Toso 是一个社交媒体营销专家,擅长一切社交活动!作为 DigiKey 社交媒体团队的忠实成员,您可以在 DigiKey 的社交媒体渠道上看到她的博客、分享、推特和帖子。Jenn 酷爱创客和 STEM 社区,她相信今天的年轻人手中握着一把为我们每个人创造更美好明天的钥匙。Jenn 拥有科学学士学位、互联网营销硕士学位和曲棍球妈妈博士学位。业余时间,Jenn 喜欢探索她最近发现的可穿戴技术的亲和力,也喜欢让自己痴迷于所有与曲棍球相关的东西。您会常常发现 Jenn 活跃在一些社交媒体或曲棍球球场上——或有时候同时乐在其中。

More posts by Jenn Toso
 TechForum

Have questions or comments? Continue the conversation on TechForum, Digi-Key's online community and technical resource.

Visit TechForum