🤖 What if building your own robot arm costs less than £220?
For years, robotics has been locked behind high prices and complex systems. So we decided to change that.
Today, we’re open-sourcing Ark-Bot — a fully 3D-printed, 6-DOF robot arm that works seamlessly with our Python robotics library, Ark.
And yes… It’s only £215.86 to build.
🧠ArkBot Specs 🧠
1️⃣ Reach: 1 meter 2️⃣ Weight: 2.6 kg 3️⃣ Payload: 1.8 kg 💪 4️⃣ DOF: 6 5️⃣ Input Voltage: DC 12V
🤟Fully 3D-printable & open-source 🤟Integrated with Ark — no ROS required
📹 We’ve also released a video showing the full assembly process — because robotics should be something everyone can learn, build, and improve on.
👩🎓 With Ark-Bot, anyone — from students to AI researchers — can experiment with embodied AI, robot learning, and control algorithms on real hardware, affordably.
If you could control a 1-meter robot arm from your laptop for under £220… 👉 What would you build first?
Hey, amazing, awesome people of the beautiful internet 😍🥰
Distillation has been (from my point of view) a main driving factor for the success of hashtag#LLMs - like distilling the knowledge of an amazing big model (say hashtag#DeepSeekv3, or hashtag#GeminiAI) into yours.
Probably, you have done it with minimising a KL divergence, and it somehow worked.
Well, not that well, right?
1️⃣ Your model tends to memorise! 2️⃣ Your model might get the right answer, but its reasoning might be flawed.
To fix those problems, we rethink distillation and process a new approach! A method that is based on constrained RL that comes with nice theoretical guarantees and excellent performance!
Hello, amazing robotics people 😍 😍 😍 We have FINALLY delivered on your major request! Ark just got a major upgrade:
We’ve now integrated Vision-Language-Action Models (VLAs) into Ark 🎉 VLAs = models that connect vision + language → robot actions (see image)
What does this mean?
🗣️ Give robots natural language instructions → they act 👀 Combine perception + language for real-world control 🦾 Powered by pi0 pretrained models for fast prototyping ⚡ Supports easy data collection and fine-tuning within Ark within a couple of lines of code
Next, we plan to go into the world of designing worlds 😉 Who knows, maybe those video models are actually zero-shot learners and reasoners?
We have written a fun little blog on how you can do robotics with Ark and in Python. We also give you some examples of how OpenAI Gym can become hardware-grounded and how easy it is to do so:
Hey, Amazing AI and ML people, I have an open permanent position in London for a research scientist on my team. If you have expertise in any RL, LLMs, AI-Agents and Bayesian optimisation with a good publication track record at NeurIPS, ICLR, ICML, JMLR and others, don't hesitate to get in touch with me :-D
Everyone wants VLMs in robotics, but well, VLMs are not trained or grounded in robotics! So, we fix that by presenting ExPTeach: Experience is the Best Teacher, where we ground VLMs using self-generated Memory.
It's remarkable to see how it can recover from failures by leveraging past experiences stored in memory.
For machine learning in robotics 🤖 , it is essential to collect data, of course. I am happy to announce that we have now open-sourced Ark Interfaces, which allows you to collect data from your robot via, well, an interface 😍
We started by implementing a PS4 controller, which will allow you to control your robot as if you are playing a PS4 game 🤪
As promised, and after the request of many, we have managed to fit in the first live session about Ark that we will be giving on the 28th of July.
pip install ark-robotics
For those who are already in the messaging channel, all is done, no need to do anything :-D For those interested in registering, please write to me at ark.robotics.uk@gmail.com - then I can add you and send you the invite.
We chose the timing to be 5 pm UK after consulting many of the interested people. Hope it works well for you too?