Grasp-MPC adjusts robotic grasps in real time, refining motion as the robot approaches an object instead of following a fixed plan.NVIDIA Robots trained entirely in simulation are beginning to perform ...

NVIDIA's latest robotics research, unveiled at ICRA 2026, shows breakthroughs in sim-to-real transfer. Key advances include multi-arm coordination, adaptable navigation, and precision grasping. NVIDIA ...

Tesla’s Optimus robot just took a giant leap forward, literally. In a pair of newly released videos, Elon Musk reveals Optimus performing complex dance moves, now entirely untethered and autonomous.

As robotics evolves beyond fixed automation, manufacturers are adopting a new generation of systems designed for flexibility, intelligence and real-world adaptability. In some cases, that shift is ...

The promise of physical AI is that engineers will be able to program physical agents the same way they do digital ones. We’re not there yet. Robotics is still held back by a paucity of data from ...

Reinforcement learning (RL) for robotics is often associated with large GPU clusters, distributed infrastructure, and x86-based development environments. Training a humanoid robot with high-fidelity ...

The system supports both real-time control and offline trajectory simulation: Real-time mode: interactive control via Web GUI with live MATLAB response Offline mode: trajectory generation and replay ...

The company Twist Robotics has unveiled an updated version of the Obriy Anti-Shahed simulator. The platform’s key focus is the ability to practice scenarios for intercepting long-range drones.

PTC is connecting its cloud-native Onshape CAD and PDM platform with NVIDIA IsaacSim open simulation framework. Image courtesy of PTC. In this Special Focus Issue, learn about the latest developments ...

MOUNTAIN VIEW, Calif.--(BUSINESS WIRE)--Sharpa presents new research demonstrating significant improvements in simulation methods for robot training, in collaboration with NVIDIA. Sharpa aims to ...