Great! new paper on combining Hierarchical Reinforcement Learning with Human-Flow Awareness for Robot Task Planning has been published on RA-L! ieeexplore.ieee.org/abstract/docum…

A successful DARKO project stakeholders meeting! A lot of fun with this robot and our team! #robotics #AI #darko #BoschResearch #teamwork

Often criticized, often forgotten. Napoli instead is vibrant, full of life, of energy, of dreams. "Napule e' mille culur" #coldplay #napoli

We're launching Keras Core, a new library that brings the Keras API to JAX and PyTorch in addition to TensorFlow. It enables you to write cross-framework deep learning components and to benefit from the best that each framework has to offer. Read more: keras.io/keras_core/ann…

Check out my "Survey of maps of dynamics for mobile robots" doi.org/10.1177/027836… Aalto University

🚀 Exciting news: "SGRec3D: Self-Supervised 3D Scene Graph Learning via Object-Level Scene Reconstruction" is now available at arxiv.org/abs/2309.15702 Collaboration between Bosch Center for Artificial Intelligence and Universität Ulm Pedro Hermosilla, Narunas Vaskevicius, Mirco Colosi, Timo Ropinski (1/8) A thread 🧵

#IROS2023 is almost over! Had the pleasure to present our work “Semantically informed MPC for context aware exploration” and discuss with many of you our future research directions on AI and robotics. #BCAI #BoschResearch #AI

Launching Lean Co-pilot for LLM-human collaboration to write formal mathematical proofs that are 100% accurate. We use LLMs to suggest proof tactics in Lean and also allow humans to intervene and modify in a seamless manner. github.com/lean-dojo/Lean… Automating theorem proving

VideoPoet is another impressive model capable of synthesizing high quality videos conditioned on different type of input (text, depth and optical flow etc). sites.research.google/videopoet/

🎉Exciting news! Delighted to announce that our LHMP workshop for ICRA 2024 has been accepted! Looking forward to sharing insights, collaborating with experts, and pushing the boundaries of the field. More details motionpredictionicra2024.github.io #ICRA2024 #AI #BoschResearch

Interesting approach for better combining learning and model predictive control #ai

A very interesting work by Sebastian accepted at #CVPR2024: Open3DSG, a novel approach for learning 3D scene graph predictions in an open world without requiring labeled scene graph data, with inter-object relationships predited using a grounded LLM #BCAI #BoschResearch #AI

The call for papers is now open for our #ICRA2024 workshop on Long-term Human Motion Prediction. We welcome the submission of extended abstracts until April 1st. Your contributions are eagerly welcome!motionpredictionicra2024.github.io #BCAI #BoschResearch #AI #Robotics

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Physics to John J. Hopfield and Geoffrey E. Hinton “for foundational discoveries and inventions that enable machine learning with artificial neural networks.”

BREAKING NEWS The Royal Swedish Academy of Sciences has decided to award the 2024 #NobelPrize in Chemistry with one half to David Baker “for computational protein design” and the other half jointly to Demis Hassabis and John M. Jumper “for protein structure prediction.”

Discover GraphEQA, a cutting-edge approach to embodied question answering (EQA) that utilizes 3D scene graphs! It was an absolute pleasure to work with Saumya Saxena, Chris Paxton, Blake Buchanan , Bingqing Chen, Narunas Vaskevicius, Jonathan Francis, and Oliver Kroemer, on this!

Locomotion is definitely improving, but don’t confuse that with dexterity. None of these examples suggest progress in robot manipulation. Progress will come, but let’s be careful not to raise unrealistic expectations.

Our science team has started working on fully reproducing and open-sourcing R1 including training data, training scripts,... Full power of open source AI so that everyone all over the world can take advantage of AI progress! Will help debunk some myths I’m sure too. Thanks

Important recognition for the work of Barto and Sutton! Their contributions allowed RL to be one of the most important field of AI!

A free PDF of my book "Rollout, Policy Iteration, and #ReinforcementLearning " has been posted at my web site web.mit.edu/dimitrib/www/d… An extensive research account on rollout algorithms, including multiagent rollout, and the connection with Newton's method