Technical Directions
Robotics coverage relating to imitation learning.
110 selected reportsLast 30 days 90 recordsAll coverage 498 records
NVIDIA has released the 'gr00t17-lerobot-libero_object-640' model, a cross-embodiment foundation model for humanoid robot reasoning and skills. It uses a Cosmos-Reason2/Qwen3-VL backbone and a flow-matching action transformer, trained with LeRobot and available under the Apache 2.0 license. The model supports training and deployment through LeRobot, with detailed instructions provided.
NVIDIA has released a cross-embodiment foundation model for humanoid robots, leveraging a Cosmos-Reason2/Qwen3-VL backbone and a flow-matching action transformer. The model is trained using LeRobot and is available for training and deployment via the Hugging Face Hub.
Boston Dynamics explores how football can inform robot movement by using human demonstrations and reinforcement learning to train Atlas to perform a complex 'Ghost Rabona' kick, highlighting the intersection of sports and robotics in developing dynamic, whole-body control.
Universal Robots and Scale AI have unveiled the UR AI Trainer, an imitation learning system designed to accelerate AI model training by capturing high-fidelity, synchronized robot and vision data. This system enables direct lab-to-factory AI training using UR robots with Direct Torque Control and force feedback, addressing challenges in data capture and hardware fragmentation. The collaboration also includes a large-scale industrial dataset and showcases real-world robotic foundation model performance.
Helix 02, a single neural system that controls the full body directly from pixels, now performs end-to-end living room cleanup, including tasks like cleaning surfaces, handling flexible objects, and bimanual manipulation. The system learns new capabilities through data without requiring new algorithms or specialized engineering.
Dexterity introduces Foresight, a world model that enables robots to reason about the physical world, predict outcomes, and act confidently in real environments. Trained on over 100 million autonomous actions in production, Foresight is designed for interpretability, safety, and performance, with capabilities like predictive branching and pragmatic decision-making. It addresses complex tasks like spatial packing and includes a game and API challenge for further exploration.
Dexterity introduces 'Transactable World Models' as a foundational component for Physical AI, emphasizing interpretability, physics integration, and real-time consistency. The approach treats world models as operators rather than data stores, enabling multi-agent coordination and robust manipulation in complex environments. This contrasts with traditional world models that focus on data compression and replay, lacking causal reasoning and physical grounding.
Hugging Face announces LeRobot v0.4.0, a major upgrade for open-source robotics with Dataset v3.0, new VLA models like PI0.5 and GR00T N1.5, and a plugin system for hardware integration. The release also adds support for LIBERO and Meta-World simulations, multi-GPU training, and a new Hugging Face Robot Learning Course.
PickNik announces the release of MoveIt Pro, a commercial robotics software platform built on the open-source MoveIt project. The update highlights new features such as support for FANUC and Kawasaki robots, integration with Meta Quest for AI data collection, Diffusion Policies for end-to-end AI training, and enhanced simulation capabilities with IMU and 3D Lidar support. The platform is designed for unstructured environments, providing tools for motion planning, grasping, perception, and behavior sequencing.
NASA showcased its robotic technologies and future space exploration vision at the 2025 FIRST Robotics World Championship, engaging over 55,000 students and 75,000 parents and mentors. The event featured interactive exhibits, including lunar rovers, robotic arms, and the Mars Perseverance Rover, with NASA centers highlighting innovations like automated assembly systems and surface manipulation technologies.
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).