embodied-ai
Google's Gemini Robotics 2 controls a humanoid from feet to fingertips - for a waitlist News
Google DeepMind announced Gemini Robotics 2 with whole-body humanoid control, 22-degree-of-freedom hands and robots that delegate tasks to each other, but only the reasoning model is available to developers; the control models are in private preview.
Asked to sit in a chair it can see, the best AI model misses five times out of seven News
A new benchmark decouples motor control from decision-making and asks nine frontier vision-language models to find an object, walk to it and sit on it - the best completes 16.8% of episodes, and perception is not the problem.
A robot control model now runs 32 times a second on a gaming GPU, in under a gigabyte News
TurboVLA reaches real-time robot control at 32 Hz using 0.9GB of memory on a consumer RTX 4090, by removing the large language model from the control loop entirely rather than compressing it.
Sunday Robotics Says Its Robot Folds Laundry Reliably in Homes It Has Never Seen News
Sunday Robotics previewed ACT-2, a home-robotics model reporting 99.1% zero-shot success at folding laundry across diverse, unseen homes -- and proposed a new reliability metric to move robotics past cherry-picked demos.
LaMem-VLA gives robots a working memory so they stop forgetting what they just did News
A new robotics model, LaMem-VLA, fixes the 'short-horizon bias' that makes robots react only to what's in front of them by weaving compressed memories of past actions directly into the model's internal representation -- so it can handle multi-step tasks that require remembering an earlier state.
Sim-to-Real Transfer: Teaching Robots in a Dream Lesson
Sim-to-real transfer is the practice of training a robot's brain entirely in a fast, cheap computer simulation and then deploying it on real hardware, using tricks like domain randomization to survive the gap between the virtual world and the messy physical one.
Mistral's first robot model navigates unseen buildings with a single camera News
Mistral released Robostral Navigate, an 8-billion-parameter model that steers robots through buildings they have never seen using one ordinary RGB camera and a plain-language instruction, beating multi-sensor systems that rely on LiDAR and depth cameras.
What Are Vision-Language-Action Models? Lesson
A vision-language-action (VLA) model is a single neural network that takes in camera images and a plain-language instruction and outputs the actual motor commands to carry it out, letting one model both understand a scene and physically act on it.
Robot AI Models Ace Colors but Flunk 'Is This Alive?' News
A new study shows vision-language-action models lose most of their commonsense world knowledge when fine-tuned to control robots, scoring near coin-flip on questions their source models answered almost perfectly.
Orca proposes a single 'world latent space' to replace next-token, next-frame, and next-action prediction News
Researchers introduced Orca, a world foundation model that learns one unified latent space from multimodal signals and predicts the next world state rather than the next token or frame, outperforming similar-sized specialists on text, image, and action tasks.
Robostral Navigate Tool
Mistral's 8B embodied model that steers wheeled, legged, or flying robots through unseen environments from a single RGB camera and a plain-language instruction.
Gemini Robotics ER 2 Tool
The embodied-reasoning half of Google DeepMind's new robotics family, and the only part available now - it reasons about physical scenes and plans robot tasks via the Gemini API and AI Studio, while the models that actually drive motors stay in private preview.