🏎️ tldr 🤖

Robots are not in as nearly as many places as they should be. It’s difficult to get them to do all the complicated tasks we want them to do and they lack the ability to interact with us. To remedy these issues, yondu is creating more readily accessible robot intelligence and we’re targeting mobile robotics first.

‎

⚠️ problem… 😔

Robots are widely underutilized in multiple industries.

Why?

They have limited ability to interact with humans and it’s difficult to use them.

What’s being done about it?

As it is, we need either developers to create custom software or skilled operators to control robots in order to carry out specific tasks.

‎

✅ solution? 🧠

But what if we could just tell a robot what to do and it actually listened?

With this level of control, we introduce and enable new robotic applications in a variety of industries.

• drones for firefighters and photographers
• robot dogs for construction and companionship
• hospitality bots in hospitals and homes

To be honest, robots should really just be about everywhere!

Here’s a demo of us using a voice controlled agent we made to pilot DJI drones.

‎

🏹 yondu! ◀️

What’s yondu?

yondu is creating models for command-directed navigation in mobile robots!

We provide on-demand intelligence for any robotics manufacturer or service provider.

We are also deploying these models on off-the-shelf hardware to fill the various gaps coming from a lack of existing smart robot services.

‎

💻 our approach 🧠

We are beginning with foundation models for navigation and we have good reasons to.

• There are already tons of mobile robotics applications that benefit from improved autonomy and human-robot interaction.
• There’s also lot of untapped footage all over the internet for learning autonomous navigation.
• Mobile robots are a lot cheaper compared to dextrous ones.

We are using a code generation agent to create some annotated training data for our end-to-end models.

‎

👨 the team 👨

The founders met while studying at MIT and have been involved in various escapades throughout the years. From hacking hijinks to grueling late night projects, the two have done it all!

Michael (left) was studying Robotics at MIT and has worked on building an open source bipedal robot and an autonomous train track cleaner!

Tahmid (right) studied Computer Science and AeroAstro at MIT and was a graduate student researching uncertainty quantification for deep learning.

P.S. can someone start a same day furniture delivery company?

‎

🥺 some asks 👉 👈

• all feedback is appreciated 😀 feel free to email us at founders[at]yonduai[dot]com
• 💼 connections to businesses that could use our models for their robots
• 🚧 connections to organizations (law enforcement, search-and-rescue, construction, inspection, security, etc) that could use smart robots