Gpu-powered planner speeds up robot arm motion with payloads
cuRoboV2-Fast: Fast Torque-Limited Collision-Free Motion Planning
Robotics
Summary
Planning smooth and safe robot arm movements that consider the weight being carried and avoid collisions can take a long time. The authors developed cuRoboV2-Fast, a method that uses graphics cards to quickly calculate these movements by optimizing curve-based paths and dynamics computations. This makes planning faster and allows the robot to carry payloads while respecting torque limits. Their method was tested on different hardware and setups, showing it can plan much quicker and complete tasks faster than earlier versions.
What this means in practice
- •For industrial robot engineers: Create fast, safe robotic arm motions that adjust in real time to carrying different weights without colliding or damaging the robot.
- •For robotics system integrators: Integrate GPU-accelerated planning to achieve quicker automated pick-and-place cycles in flexible manufacturing environments.
Authors
Balakumar Sundaralingam, Adithyavairavan Murali, Stan Birchfield
Abstract
We present cuRoboV2-Fast, a GPU-accelerated planner that reduces both planning latency and execution time for collision-free, payload-aware, torque-limited motions. B-spline trajectory optimization reduces the required iterations, while accelerated robot computations and differentiable inverse dynamics reduce refinement cost and accommodate changing payloads. TimeOpt optimizes traversal speed along the fixed path under sampled velocity, acceleration, jerk, and torque constraints, exploiting local spline support to solve banded Newton systems efficiently on the GPU. With a 3,kg payload, cuRoboV2-Fast achieves 4.4 ms mean planning time on RTX 5090, 14.7x faster than cuRoboV2. Our method on Jetson AGX Orin plans faster than cuRoboV1 + TOPPRA on RTX 5090. A stereo-camera-based deployment on YAM achieves 5.93 s mean completed pick-and-drop cycles, 34.6% shorter than cuRoboV2. Code (Apache 2.0): www.github.com/NVlabs/curobo , Project Page: www.research.nvidia.com/labs/lpr/curobov2-fast .