Robot policies Latest coverage

Robotic Systems Lab@leggedrobotics· 15:13SignalEditorial score6363

PragmaBot enables robots to learn from real-world failures through online in-context learning, reflecting on past experiences, storing lessons in memory, and retrieving them for new tasks. This approach avoids the need for retraining, addressing limitations in using VLMs for embodied robotics.

Small robot propulsion: low-power twisting enables hopping, swimming

Researchers at the University of Michigan and UCLA have developed a new propulsion mechanism for small robots using low-power twisting of elastic rods. This method enables hopping and swimming motions by utilizing snapping mechanics. The mechanism works on challenging surfaces such as slippery cloth and grass-covered ground, producing frog-like motion. The study, published in Science Advances, was co-led by Khalid Jawed and Xiaonan (Sean) Huang, and demonstrates the potential for miniature robots to maneuver over uneven or slippery terrain.

Robotic lab sets up and runs optics experiments on demand

MIT researchers have developed a reconfigurable robotic lab that autonomously assembles, tunes, and dismantles optical experiments. The system uses robotic arms, 3D-printed component housings, and a cloud-based interface to enable remote operation. It can build and fine-tune a laser cavity in under 30 minutes, demonstrating the potential for fully automated optical experiments.

Robotic help in high-risk twin pregnancies

Researchers at ETH Zurich have developed a robotic platform with a magnetically controllable endoscope to improve the safety and precision of fetal surgery for twin pregnancies with shared placentas. The system uses magnetic fields to bend the endoscope, enabling better access to blood vessels, and combines panoramic imaging with real-time navigation. The technology has been tested in an animal model and is now being refined for human clinical use.

New method enables AI for safety-critical situations

MIT researchers have developed a new technique that helps generative AI models meet strict safety and task-specific constraints without sacrificing output quality. The method, called HardFlow, reformulates constraint satisfaction as a trajectory-optim, allowing models to explore more freely during generation while ensuring final compliance with hard constraints. It is tested on robotics, control, and computer vision tasks, consistently outperforming existing methods in constraint satisfaction and solution quality.

Robots Are Learning to Feel

This article explores how tactile data is helping robots improve their dexterous manipulation skills. Researchers are creating large tactile datasets and models that can use tactile feedback to enhance robot performance in tasks like folding laundry or turning keys. Challenges include the difficulty of integrating tactile data with vision-based models and the need for more diverse and scalable datasets to achieve significant improvements in robot dexterity.

Will a cyborg cockroach paramedic save your life in the future?

Researchers at the University of Queensland and the University of New South Wales have developed 'paraborgs'—cyborg cockroaches equipped with drug-delivery systems for search-and-rescue missions. These insects can navigate through rubble, locate survivors, and administer medication using remote control and spring-loaded needles. While the technology shows promise with high success rates in tests using silicone and pig skin, human trials have not yet been conducted.

Cyborg Roaches Can Stab You With Needles

Researchers at the University of Queensland have developed 'Paraborgs'—cyborg cockroaches equipped with needles and cameras to assist in search-and-rescue missions. These insects, grafted with electronic interfaces, can navigate rubble, deliver drugs, and operate in teams. The study addresses challenges in autonomy, communication, and human interaction with the technology.

Introducing S1: In-Context Learning for Robotics

Skild AI introduces S1, a robotic foundation model that leverages in-context learning to execute complex, long-horizon tasks without post-training. This marks a significant shift from traditional fine-tuning approaches, enabling rapid deployment and reducing data requirements. The model demonstrates strong performance on unseen tasks, including plant potting, pancake cooking, and kit assembly, and shows robustness to perturbations and common-sense reasoning.

Robotic tiles autonomously Lego-snap into floating smart structures

Researchers at MIT have developed FloatForm, a system of robotic tiles that can autonomously assemble into floating structures. Inspired by ant colony behavior, the system uses magnetic latches, sensors, and thrusters to reconfigure dynamically, addressing challenges like hydrodynamics and slipstreams. Potential applications include emergency response, public space, and infrastructure on water.

Gemini Robotics ER 2: Powering Robotics with Video Understanding, Task Orchestration, and Multi-Robot Collaboration

Google DeepMind has launched Gemini Robotics ER 2, a new model that enhances robotics through video understanding, task orchestration, and multi-robot collaboration. It enables robots to perform complex tasks, adapt in real-time, and work together in shared environments. The model also improves safety and spatial reasoning capabilities, with performance benchmarks showing significant gains over previous versions.

How to Train a Robot: From Real-World Learning to Deployment

NEURA Robotics presents a seven-stage pipeline for training robots, from defining use cases and capturing real-world data to model training, optimization, and deployment. The process emphasizes physical AI, multimodal data collection, and iterative refinement to ensure reliable, scalable robotic capabilities.

If you planned to buy a Chinese robot in the US, we've got bad news

The US is banning the sale of foreign-made robots, including those from China, due to national security concerns. The FCC cites risks such as vulnerabilities in networked capabilities and potential exploitation of remote connectivity. The ban also extends to inverters with Wi-Fi, cellular, or Bluetooth control. Existing products already sold are unaffected, but companies can apply for approval to continue selling in the US.

Hy-Embodied-0.5-VLA — LeRobot Model Conversion

LeRobot has converted the Hy-Embodied-0.5-VLA-RoboTwin model, achieving full forward parity with the original policy. The model supports 16D dual-arm pose/gripper actions and passes all validation checks, though it cannot handle more complex action spaces.

Hy-Embodied-0.5-VLA — LeRobot Model Conversion

LeRobot has released a converted version of the Hy-Embodied-0.5-VLA-UMI model, ensuring full tensor compatibility and validation. The model supports a 16D dual-arm embodiment but cannot express 12D mobile-manipulator actions, indicating limitations in the current representation.

Gemini Robotics 2 brings whole body intelligence to robots

Google DeepMind has released Gemini Robotics 2, a new model that enables robots to perform complex tasks with whole-body intelligence, advanced dexterity, and multi-robot collaboration. The model supports real-time reasoning, on-device adaptation, and safety features for human-robot interaction.

NVIDIA Cosmos-H-Dreams: Bringing Real-Time Generative Simulation to Surgical Robotics

NVIDIA introduces Cosmos-H-Dreams, a real-time, action-conditioned generative simulator for surgical robotics. It distills the capabilities of Cosmos-H-Surgical-Simulator into a causal, few-step student model, enabling interactive environments for policy evaluation and synthetic data generation. The system runs on a single NVIDIA RTX PRO 6000 GPU and supports integration with surgical platforms like Versius.

NVIDIA Open Sources First GPU-Accelerated Medical Physics Simulation Framework

NVIDIA has released an open-source, GPU-accelerated Medical Physics Simulation framework as part of its Isaac for Healthcare platform. This tool enables developers to model anatomy-device interactions, generate complex scenarios, and train robot policies in simulation, significantly reducing development time and improving regulatory readiness.

New flapping robot swims and flies like a diving bird

Engineers at MIT and EPFL have developed a flapping-wing robot, or FAAV, that can swim underwater and then flap into the air, mimicking the movement of diving birds. The robot, weighing less than 300 grams, can transition between water and air using optimized wing size, flapping frequency, and tail angle. The study, published in Science, could enable new aerial-aquatic drones for oceanographic research and environmental monitoring.

NVIDIA and Hugging Face Bring New Models and Frameworks to LeRobot for the Open Robotics Community

NVIDIA and Hugging Face are releasing the NVIDIA Isaac GR00T 1.7 model and Isaac Teleop framework into LeRobot, an open-source robotics library, to provide developers with shared tools for training, evaluating, and deploying robot foundation models. NVIDIA Cosmos 3, a frontier world model for physical AI, is also set to be integrated soon.