This paper explores the problem of collision-free motion generation for manipulators by formulating it as a global motion optimization problem. We develop a parallel optimization technique to solve this problem and demonstrate its effectiveness on massively parallel GPUs. We show that combining simple optimization techniques with many parallel seeds leads to solving difficult motion generation problems within 50ms on average, 60x faster than state-of-the-art (SOTA) trajectory optimization methods. We achieve SOTA performance by combining L-BFGS step direction estimation with a novel parallel noisy line search scheme and a particle-based optimization solver. To further aid trajectory optimization, we develop a parallel geometric planner that plans within 20ms and also introduce a collision-free IK solver that can solve over 7000 queries/s. We package our contributions into a state of the art GPU accelerated motion generation library, cuRobo and release it to enrich the robotics community. Additional details are available at https://curobo.org

Dense, volumetric maps are essential for safe robot navigation through cluttered spaces, as well as interaction with the environment. For latency and robustness, it is best if these can be computed on-board on computationally-constrained hardware from camera or LiDAR-based sensors. Previous works leave a gap between CPU-based systems for robotic mapping, which due to computation constraints limit map resolution or scale, and GPU-based reconstruction systems which omit features that are critical to robotic path planning. We introduce a library, nvblox, that aims to fill this gap, by GPU-accelerating robotic volumetric mapping, and which is optimized for embedded GPUs. nvblox delivers a significant performance improvement over the state of the art, achieving up to a 177x speed-up in surface reconstruction, and up to a 31x improvement in distance field computation, and is available open-source.