Filter
Exclude
Time range
-
Near
militarpiurano_pe retweeted
Buenoteeee ese robocook
ROBOCCOK23CM 350k

9
40
1,481
This week's #PaperILike is "RoboCook: Long-Horizon Elasto-Plastic Object Manipulation with Diverse Tools" (Shi et al., CoRL 2023). So much to like in one paper: planning, learning, deformable manipulation, GNNs, 15 3D-printed tools, and dumplings! PDF: arxiv.org/abs/2306.14447
2
39
2,344
Buy propane and a propane stove if you don’t have an LPG or conventional stovetop. Even better if you have a Robocook or Instapot. Fill your car or bike tanks. If the fuel bunk allows you to carry extra, keep a little in cans. There is no fuel shortage as of now, thanks to the government’s readiness. Do not complain about LPG. Adjust. Vegetable and pulse prices shouldn’t be affected much. This might actually be a good time to reduce oil consumption and stay away from deep-fried food. It will likely be a difficult phase for the middle class. They are not eligible for government ration or monetary assistance, so be prepared. Forwarded as received from my CA
Get ready men!
12
1,025
I use Geek Robocook and is quite good.
3
6
913
How futuristic robocook SHOULD look like! - has agentic AI system which alerts and makes purchases of ingredients on your behalf - has inbuilt refrigerator with smart identification system (identifies veggies, flour etc). They need to be filled only once. - separate compartment for oil, ghee etc which needs to be filled only once - unit which auto cleans inbuilt utensils and steam dries them - determines best way to cook the dish using available ingredients. - just three commands : on - select dish/quantity and time In short, it should identify ingredients, order on my behalf, chop vegetables and do all the cooking work, give output at the end of estimated time and self clean
23 Aug 2025
My new kitchen robot just made me one of the best paneer butter masalas I’ve ever had in my life.
2
4
558
20 Jun 2025
Replying to @elonmusk
When can robocook? 🤔
1
7
268
Craved Tex-Mex tonight and asked ChatGPT for a recipe. Best homemade Tex-Mex I’ve ever made! 🌮 Now imagine: a humanoid robot with an LLM scans your fridge like ‘You’ve got cilantro, shame, and expired yogurt… I can work with this’ then handles whatever you don’t want to do. Love cooking but hate prep work? Robot does the chopping. Hate cooking entirely? Robot handles it all. Love cooking but despise dishes? You cook, robot cleans. It’s about outsourcing the parts YOU don’t enjoy. Yes, it’ll be weird at first having RoboCook judge your grocery choices, but remember when smartphones felt strange? Now they’re just part of life. Give it 10 years and we’ll customize our kitchen partners to handle exactly what we want to delegate while we focus on what we actually love doing. 🤖👨‍🍳
1
3
148
25 Oct 2024
We're doubling down on structured world models for robotics! Our new #CoRL2024 paper combines dynamic 3D Gaussian Splattings (GS) with Graph-Based Neural Dynamics (GBND) models for **Action-Conditioned 3D Video Prediction**. Key takeaways: 1. Our approach effectively creates a neural-based digital twin of real deformable objects, derived solely from real-world interactions and observations. 2. Gaussian splattings serve as a Lagrangian representation, seamlessly bridging geometry/appearance reconstruction with dynamics identification. 3. Graph-based dynamics models, trained directly on real-world data, offer outstanding stability and generalization. Models trained on ropes can be paired with the appearance of a stuffed animal, delivering realistic 3D video prediction results. 4. In an era of extensive data collection, our method complements large-scale imitation learning by building models from on-policy, offline, and play data. We're excited to scale up toward large-scale world models! This excellent work was led by the amazing Mingtong (@alexzhang_robo) and Kaifeng (@kaiwynd). Check out their beautiful demos on our website: gs-dynamics.github.io/. Interested in our graph-based neural dynamics models (GBND)? Explore these previous works: 1. DPI-Net (ICLR-19): dpi.csail.mit.edu/ 2. RoboCook (CoRL-23): hshi74.github.io/robocook/ 3. DynRes (RSS-23): robopil.github.io/dyn-res-pi… 4. AdaptiGraph (RSS-24): robopil.github.io/adaptigrap…

🚀 Watch robots predict the future! 🤖🔮 Our latest research in action-conditioned video prediction utilizes 3D Gaussian Splatting with graph-based neural dynamics, providing robots the power to predict how objects behave with interactions! 🎥 This paper has been accepted to CoRL 2024! 🌟 See how robots are learning dynamic object behavior and shaping the future of robotic manipulation! 🔗 [Learn more here!] gs-dynamics.github.io/
2
14
118
20,975
Electric Pressure Cookers - #ArivomGreatIndian Instant Pot SS 6 L (Rs.7999) : amzn.to/4dn5v4v Wellspire SS 6L (Rs.5999): amzn.to/3Y1zPxi Geek Robocook (Rs.8690) : amzn.to/3ZBZU7f
2
1
2
3,559
Robocook
Wevolver

4
1
12
1,176
i just know some of my mutuals would watch the shit out of RoboCook
2
343
11 Jul 2024
Check out our #RSS2024 paper (also the Best Paper Award at the #ICRA2024 deformable object manipulation workshop) on dynamics modeling of diverse materials for robotic manipulation. 🤖 We considered a diverse set of objects, including ropes, clothes, granular media, and rigid objects with different mass distributions. The key to this capability is again the Graph-Based Neural Dynamics (GBND), which extends our series of work on DPI-Net, RoboCraft, RoboCook, and RoboPack. We conditioned GBND with material parameters and used it for inverse problems such as (1) material adaptation and (2) model-based planning. Key Takeaways: 1. Graph-based structured scene representations show surprising effectiveness in capturing the scene dynamics for diverse materials. 2. Material conditioning allows precise modeling and effective manipulation of objects in the same category but with distinct dynamics (e.g., stiff ropes like cables and soft ropes like yarn and shoelaces). 3. Huge potential still lies ahead in extending to even larger-scale and heterogeneous environments. Kudos to @kaiwynd and @BaoyuLi6 for leading this project. Check out Kaifeng's thread for more details and come chat with us at #RSS2024!
11 Jul 2024
(1/8) Introducing AdaptiGraph, our new paper accepted by #RSS2024 We show that a GNN dynamics model can model deformable objects with varying physical properties. Website: robopil.github.io/adaptigrap… ArXiv: arxiv.org/abs/2407.07889 Work done w/ @BaoyuLi6, Kris Hauser, @YunzhuLiYZ
1
29
170
20,264
3 Jul 2024
Robotic packing requires a fine-grained understanding of whether a squeezing action can create space. Our latest paper at RSS 2024 (@RoboticsSciSys) demonstrates the critical role of tactile sensing in modeling and planning physical interactions for packing tasks. 🤖 This work, led by the fantastic @BoAi0110 and @stephentian_, advances our research on graph-based neural dynamics models (DPI-Net, RoboCraft, and RoboCook), using particles as the state representation for detailed visuo-tactile interaction modeling.
3 Jul 2024
#RSS24 Can robots better understand the world dynamics through visual and tactile sensing? 🤖 We introduce RoboPack, a framework that integrates tactile-informed state estimation, dynamics prediction, and planning for complex tasks like packing. 🧵1/N robo-pack.github.io
1
4
59
6,453
As a follow-up to RoboCraft and RoboCook, we explore how to embed tactile information into GNN-based dynamics learning in RoboPack! We find that particle-based representation with tactile features benefits in challenging tasks like dense packing📦! Big congrats to @BoAi0110!
3 Jul 2024
#RSS24 Can robots better understand the world dynamics through visual and tactile sensing? 🤖 We introduce RoboPack, a framework that integrates tactile-informed state estimation, dynamics prediction, and planning for complex tasks like packing. 🧵1/N robo-pack.github.io
6
39
3,763
ギョーザの皮を包めるロボット登場 驚異のAI技術RoboCookとは xtrend.nikkei.com/atcl/conte… #日経クロストレンド

6
2,354
ギョーザの皮を包めるロボット登場 驚異のAI技術RoboCookとは xtrend.nikkei.com/atcl/conte… #日経クロストレンド

2
173
Replying to @f1ora1f1xat1on
problematically hot robocook
2
83