Robotics, autonomy & world models for advanced learners
48 resources · page 2 of 2
LeRobot
by Hugging Face
Hugging Face LeRobot GitHub repo: models, datasets and tools for real-world robot learning.
Runway research
by Runway
Runway research page: papers and posts on video generation and world models such as Gen-4, Aleph and Act-Two.
UniAD
by OpenDriveLab
OpenDriveLab UniAD GitHub repo (CVPR 2023): planning-oriented end-to-end autonomous driving model.
Skild AI
by Skild AI
Skild AI: company building general-purpose robot foundation models.
Skywork Matrix-Game
by Skywork
Skywork Matrix-Game GitHub repo: streaming neural rendering models for playable interactive worlds.
UN Regulation No. 157 (ALKS) on EUR-Lex
by EUR-Lex (Publications Office of the European Union)
EUR-Lex publication of UN Regulation No. 157 on Automated Lane Keeping Systems.
UN Regulation No. 171 (DCAS): UN treaty depositary record
UN treaty depositary record for UN Regulation No. 171 on Driver Control Assistance Systems.
First Global Regulatory Framework For Autonomous Vehicles: Key Takeaways For Canada (Bennett Jones)
Bennett Jones blog post (2026) on the UNECE global technical regulation for automated driving systems.
Unitree
Unitree Robotics: maker of quadruped and humanoid robots used in research.
V-JEPA 2 (Meta)
Meta V-JEPA 2 GitHub repo: PyTorch code and models for self-supervised video learning.
Waymo goes driverless in Las Vegas, with Denver, San Diego, Tampa next (Electrek)
by Electrek
Electrek report on Waymo launching driverless operations in Las Vegas, with Denver, San Diego and Tampa next.
Gemini Robotics
Google DeepMind Gemini Robotics page describing its vision-language-action models for robot control.
NVIDIA GR00T
by NVIDIA
NVIDIA Isaac GR00T page: research initiative and platform for humanoid robot foundation models and data pipelines.
ACT / ALOHA
by Tony Z. Zhao et al. (Stanford University)
arXiv paper (2023) introducing ACT and the ALOHA low-cost hardware for fine-grained bimanual robot manipulation.
Champion-level drone racing using deep reinforcement learning (Swift)
by Elia Kaufmann et al. (University of Zurich)
Nature paper (2023) on Swift, a deep RL drone that beat human champions in drone racing.
TD3
by Scott Fujimoto et al. (McGill University)
arXiv paper (2018) introducing TD3, addressing function approximation error in actor-critic methods.