See LLM-GROP by Yan Ding and Xiaohan Zhang at IROS Extract semantic knowledge from LLMs like GPT to perform multi step object rearrangement on real robots, like setting the table

Thanks Communications of the ACM for highlighting our seeing-eye robot work! It will be presented at #CoRL2023 next week.

Nice work from Jeannette Bohg 's lab led by Jingyun Yang Jingyun Yang and Congyue Deng showing how to build SIM(3)-equivariant representations for manipulation. A few notes: 👇

We submit this work to LangRob Workshop at CoRL 2023! See you in the poster session!

The reason why physical AI is harder than generative AI is because of their respective customers. Humans can easily forgive any errors, physics is unforgivable.

It took a little longer but our AURO special issue on LLMs in Robotics is finally here: link.springer.com/collections/be… Edited together with Brian Ichter Fei Xia Shuran Song with help from the main AURO editor Gaurav Sukhatme Let's go over the papers in the special issue 👇

Can we leverage VLMs for robot manipulation in the open world? Checkout our new work MOKA, a simple and effective visual prompting method!

If you're interested in learning SOTA of optimization-based task and motion planning, please give it a read of our recent survey paper, ranging from classical to learning methods. kelvinzhaozg_ Shuo Cheng Yan Ding Ziyi Zhou Shiqi Zhang Danfei Xu arxiv.org/pdf/2404.02817…