Open Source SLAM Library GTSAM Adds CUDA Backend
fdellaert · x · 2026-08-22
GTSAM is introducing an experimental CUDA backend for nonlinear factor-graph optimization in its upcoming 4.3 release. Developed by Ruogu Li, it brings GPU acceleration to robotics, SLAM, and computer vision tasks.
Related event: GTSAM 4.3 Adds Experimental CUDA Backend for Faster Optimization(2 posts)→
More from Embodied
- Neuralink in 7 Years: From Pig Brain Signals to 27+ Humans Controlling Machines by Thought — XFreeze · 2026-08-22
- FetchMan: Vision-Based Humanoid Policy Trained in Simulation — kevin_zakka · 2026-08-22
- Evolution of the Robotic Horse — SaganPupil · 2026-08-22
- Sunday Robotics ACT-2 achieves zero-shot generalization breakthrough — tonyzzhao · 2026-08-22
- WCM: A JEPA-Based World Critic Model Beats SOTA on 149 VLA Robot Tasks — jiqizhixin · 2026-08-22
- Raspberry Pi 5 Robotic Claw Project Involves Complex Calculus — kamathsblog · 2026-08-22