NVIDIA's CUDA-accelerated robot library: collision-free motion generation in tens of milliseconds via massively parallel trajectory optimization, GPU IK and MPC — the engine behind Isaac ROS cuMotion for reactive industrial manipulation.
NVIDIA's CUDA-accelerated robot library: collision-free motion generation in tens of milliseconds via massively parallel trajectory optimization, GPU IK and MPC — the engine behind Isaac ROS cuMotion for reactive industrial manipulation.
Save it, compare it, request a quote or record that you have used it — with an account.
cuRobo is a CUDA-accelerated library of robotics primitives — batched forward/inverse kinematics, collision checking against meshes, cuboids and nvblox ESDFs, numerical integration and trajectory optimization — composed into a motion-generation pipeline that plans collision-free, time-optimized manipulator trajectories roughly 60x faster than CPU state-of-the-art. It seeds a particle-based optimizer and parallel L-BFGS across thousands of GPU threads, and also offers model-predictive control (MPPI) for reactive behavior. Distributed under Apache-2.0, it integrates with PyTorch/warp, Isaac Sim, and ships in production form as Isaac ROS cuMotion for ROS 2.
This product is part of the Birdwave Atlas community.
Contribute evaluations, share integrations and help improve compatibility data.
Discussions, evaluations, integrations and updates