You could find the dog's code here: https://github.com/Robotics-Ark/ark_unitree_go_2
Haitham Bou Ammar PRO
hba123
AI & ML interests
LLMs, VLMs, Robotics, Reinforcement Learning, Bayesian Optimisation
Recent Activity
Organizations
None yet
replied to
their
post
24 days ago
replied to
their
post
24 days ago
Nope. We have Arms and we also have The Robot Dog Unitree Go2. We are currently implementing the G1 humanoid and plan to support drones next.
replied to
their
post
24 days ago
We already do interface with the hardware. All the code is open sourced https://github.com/Robotics-Ark. Please notice we already interface with UnitreeGo2, and many arms :-) It is not just in simulation :-D We support ROS if needed but we do better with LCM yet at the same communication speed.
reacted to
their
post with 🚀
27 days ago
Post
2819
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:
Check it out: https://huggingface.co/blog/hba123/ark
Check it out: https://huggingface.co/blog/hba123/ark
-
- 5 replies
posted
an
update
27 days ago
Post
2819
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:
Check it out: https://huggingface.co/blog/hba123/ark
Check it out: https://huggingface.co/blog/hba123/ark
-
-
- 5 replies
reacted to
their
post with 🔥
28 days ago
Post
3298
After so many requests, I want to update everyone on the status of Ark, i.e., doing robotics in Python. First, thanks a lot for the amazing and impressive interest we got in it. We are now @ 1.13 K downloads, which is beyond my wildest expectations (https://pepy.tech/projects/ark-robotics?timeRange=threeMonths&category=version&includeCIDownloads=true&granularity=daily&viewType=line&versions=0.1.1%2C0.1%2C0.0.1)!
0. First and foremost, we are pip installable (https://pypi.org/project/ark-robotics/)
1. We are currently working on supporting more robots: G1 and Drones are in the works with a cool set of amazing, fantastic colleagues. Those are coming.
2. We have support for multiple sensors and interfaces (https://github.com/Robotics-Ark/ark_interfaces)
3. We also now have support for machine learning via diffusion policies (https://github.com/Robotics-Ark/ark_diffusion_policies_on_franka)
4. We have a set of tutorials that detail each step (https://arkrobotics.notion.site/ARK-Home-22be053d9c6f8096bcdbefd6276aba61)
You can read the paper here: https://robotics-ark.github.io/ark_robotics.github.io/static/images/2506.21628v2.pdf
Have fun building robotics with Python people! Please star our repo (https://github.com/Robotics-Ark/ark_framework), so we can continue our open-sourcing endeavour!
0. First and foremost, we are pip installable (https://pypi.org/project/ark-robotics/)
1. We are currently working on supporting more robots: G1 and Drones are in the works with a cool set of amazing, fantastic colleagues. Those are coming.
2. We have support for multiple sensors and interfaces (https://github.com/Robotics-Ark/ark_interfaces)
3. We also now have support for machine learning via diffusion policies (https://github.com/Robotics-Ark/ark_diffusion_policies_on_franka)
4. We have a set of tutorials that detail each step (https://arkrobotics.notion.site/ARK-Home-22be053d9c6f8096bcdbefd6276aba61)
You can read the paper here: https://robotics-ark.github.io/ark_robotics.github.io/static/images/2506.21628v2.pdf
Have fun building robotics with Python people! Please star our repo (https://github.com/Robotics-Ark/ark_framework), so we can continue our open-sourcing endeavour!
posted
an
update
28 days ago
Post
3298
After so many requests, I want to update everyone on the status of Ark, i.e., doing robotics in Python. First, thanks a lot for the amazing and impressive interest we got in it. We are now @ 1.13 K downloads, which is beyond my wildest expectations (https://pepy.tech/projects/ark-robotics?timeRange=threeMonths&category=version&includeCIDownloads=true&granularity=daily&viewType=line&versions=0.1.1%2C0.1%2C0.0.1)!
0. First and foremost, we are pip installable (https://pypi.org/project/ark-robotics/)
1. We are currently working on supporting more robots: G1 and Drones are in the works with a cool set of amazing, fantastic colleagues. Those are coming.
2. We have support for multiple sensors and interfaces (https://github.com/Robotics-Ark/ark_interfaces)
3. We also now have support for machine learning via diffusion policies (https://github.com/Robotics-Ark/ark_diffusion_policies_on_franka)
4. We have a set of tutorials that detail each step (https://arkrobotics.notion.site/ARK-Home-22be053d9c6f8096bcdbefd6276aba61)
You can read the paper here: https://robotics-ark.github.io/ark_robotics.github.io/static/images/2506.21628v2.pdf
Have fun building robotics with Python people! Please star our repo (https://github.com/Robotics-Ark/ark_framework), so we can continue our open-sourcing endeavour!
0. First and foremost, we are pip installable (https://pypi.org/project/ark-robotics/)
1. We are currently working on supporting more robots: G1 and Drones are in the works with a cool set of amazing, fantastic colleagues. Those are coming.
2. We have support for multiple sensors and interfaces (https://github.com/Robotics-Ark/ark_interfaces)
3. We also now have support for machine learning via diffusion policies (https://github.com/Robotics-Ark/ark_diffusion_policies_on_franka)
4. We have a set of tutorials that detail each step (https://arkrobotics.notion.site/ARK-Home-22be053d9c6f8096bcdbefd6276aba61)
You can read the paper here: https://robotics-ark.github.io/ark_robotics.github.io/static/images/2506.21628v2.pdf
Have fun building robotics with Python people! Please star our repo (https://github.com/Robotics-Ark/ark_framework), so we can continue our open-sourcing endeavour!
reacted to
their
post with 👀
about 1 month ago
Post
260
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
Please email me at [email protected]
Please email me at [email protected]
posted
an
update
about 1 month ago
Post
260
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
Please email me at [email protected]
Please email me at [email protected]
replied to
their
post
about 1 month ago
Do you have any specific goals? Or any specific fields of interest?
I can tell you how I learned AI, and it might not be the way people do it today, but it is the right way :P
I began by learning the necessary mathematics. A subset of those was Linear Algebra, Calculus, Probability and Statistics. Then I started learning probabilistic machine learning from books like Bishop (https://www.microsoft.com/en-us/research/wp-content/uploads/2006/01/Bishop-Pattern-Recognition-and-Machine-Learning-2006.pdf)
After that I started to learn the field I wanted to be in. In my case, it was reinforcement learning so I studied the following books:
http://rlbook.busoniu.net/ - This is one of my favourite books on the topic.
(https://www.deisenroth.cc/pdf/fnt_corrected_2014-08-26.pdf)
I then started to read papers on the topics in ICML, ICLR, NeurIPS, JMLR, and the like.
In terms of coding, I learned Python and PyTorch. For that, I simply followed the tutorials online.
Then, transformers came, so I had to learn that, of course, followed by LLMs, VLMs, diffusions and so forth.
Hope this helps :-)
reacted to
their
post with 🔥
about 1 month ago
Post
1297
I am happy to announce that we are over 1K downloads now! 🥳🥳🥳🥳🥳
https://pypi.org/project/ark-robotics/0.1/
https://pypi.org/project/ark-robotics/0.1/
-
- 2 replies
posted
an
update
about 1 month ago
Post
1297
I am happy to announce that we are over 1K downloads now! 🥳🥳🥳🥳🥳
https://pypi.org/project/ark-robotics/0.1/
https://pypi.org/project/ark-robotics/0.1/
-
-
- 2 replies
reacted to
AdinaY's
post with 🔥
about 1 month ago
Post
1648
Qwen team did it again!!
They just released Qwen3-Coder-30B-A3B-Instruct on the hub🔥
Qwen/Qwen3-Coder-30B-A3B-Instruct
✨ Apache 2.0
✨30B total / 3.3B active (128 experts, 8 top-k)
✨ Native 256K context, extendable to 1M via Yarn
✨ Built for Agentic Coding
They just released Qwen3-Coder-30B-A3B-Instruct on the hub🔥
Qwen/Qwen3-Coder-30B-A3B-Instruct
✨ Apache 2.0
✨30B total / 3.3B active (128 experts, 8 top-k)
✨ Native 256K context, extendable to 1M via Yarn
✨ Built for Agentic Coding
reacted to
merve's
post with 🚀
about 1 month ago
Post
2246
Cohere just dropped
CohereLabs/command-a-vision-07-2025, a 112B (dense!) vision LM
> based on SigLIP2 & Command-A
> built for enterprise use cases 🔥
> use with Inference Providers or transformers 🤗
read their blog https://huggingface.co/blog/CohereLabs/introducing-command-a-vision-07-2025
> based on SigLIP2 & Command-A
> built for enterprise use cases 🔥
> use with Inference Providers or transformers 🤗
read their blog https://huggingface.co/blog/CohereLabs/introducing-command-a-vision-07-2025
- 2 replies
replied to
their
post
about 2 months ago
Don't get me started on Elon :P
reacted to
their
post with 🚀
about 2 months ago
Post
1732
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.
Check it out here: Experience is the Best Teacher: Grounding VLMs for Robotics through Self-Generated Memory (2507.16713)
It's remarkable to see how it can recover from failures by leveraging past experiences stored in memory.
Check it out here: Experience is the Best Teacher: Grounding VLMs for Robotics through Self-Generated Memory (2507.16713)
-
- 2 replies
posted
an
update
about 2 months ago
Post
1732
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.
Check it out here: Experience is the Best Teacher: Grounding VLMs for Robotics through Self-Generated Memory (2507.16713)
It's remarkable to see how it can recover from failures by leveraging past experiences stored in memory.
Check it out here: Experience is the Best Teacher: Grounding VLMs for Robotics through Self-Generated Memory (2507.16713)
-
-
- 2 replies
reacted to
their
post with ❤️
about 2 months ago
Post
2193
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 🤪
Have a look at the code here: https://github.com/Robotics-Ark/ark_interfaces/tree/main/arkinterfaces
Have a look at the tutorial here: https://arkrobotics.notion.site/PS4-Controller-238e053d9c6f80a989ccdb163a76e538?pvs=23
What is the next interface you'd want implemented?
Have fun with Robotics in Python - which is pip installable now BTW: https://pypi.org/project/ark-robotics/
Thanks, Jiacheng Qiu, for your Ark contributions 🙃
As always, thanks to Christopher Mower, Sarthak Das and Magnus Dierking for Ark all together!
We are hosting a live session on the 28th for Ark! Let me know if you want to join by sending an email to: [email protected]!!
We started by implementing a PS4 controller, which will allow you to control your robot as if you are playing a PS4 game 🤪
Have a look at the code here: https://github.com/Robotics-Ark/ark_interfaces/tree/main/arkinterfaces
Have a look at the tutorial here: https://arkrobotics.notion.site/PS4-Controller-238e053d9c6f80a989ccdb163a76e538?pvs=23
What is the next interface you'd want implemented?
Have fun with Robotics in Python - which is pip installable now BTW: https://pypi.org/project/ark-robotics/
Thanks, Jiacheng Qiu, for your Ark contributions 🙃
As always, thanks to Christopher Mower, Sarthak Das and Magnus Dierking for Ark all together!
We are hosting a live session on the 28th for Ark! Let me know if you want to join by sending an email to: [email protected]!!
posted
an
update
about 2 months ago
Post
2193
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 🤪
Have a look at the code here: https://github.com/Robotics-Ark/ark_interfaces/tree/main/arkinterfaces
Have a look at the tutorial here: https://arkrobotics.notion.site/PS4-Controller-238e053d9c6f80a989ccdb163a76e538?pvs=23
What is the next interface you'd want implemented?
Have fun with Robotics in Python - which is pip installable now BTW: https://pypi.org/project/ark-robotics/
Thanks, Jiacheng Qiu, for your Ark contributions 🙃
As always, thanks to Christopher Mower, Sarthak Das and Magnus Dierking for Ark all together!
We are hosting a live session on the 28th for Ark! Let me know if you want to join by sending an email to: [email protected]!!
We started by implementing a PS4 controller, which will allow you to control your robot as if you are playing a PS4 game 🤪
Have a look at the code here: https://github.com/Robotics-Ark/ark_interfaces/tree/main/arkinterfaces
Have a look at the tutorial here: https://arkrobotics.notion.site/PS4-Controller-238e053d9c6f80a989ccdb163a76e538?pvs=23
What is the next interface you'd want implemented?
Have fun with Robotics in Python - which is pip installable now BTW: https://pypi.org/project/ark-robotics/
Thanks, Jiacheng Qiu, for your Ark contributions 🙃
As always, thanks to Christopher Mower, Sarthak Das and Magnus Dierking for Ark all together!
We are hosting a live session on the 28th for Ark! Let me know if you want to join by sending an email to: [email protected]!!
replied to
their
post
about 2 months ago
