GTSAM 4.3 released with CUDA-accelerated optimization and legged robot state estimation
fdellaert · x · 2026-10-08
GTSAM, the C++ factor-graph inference/optimization library, released 4.3. Highlights: expanded IMU preintegration and invariant filtering with legged-robot proprioceptive state estimation (with Seoul National University), and an experimental opt-in CUDA backend offering GPU-accelerated Levenberg–Marquardt optimization via cuDSS, plus continuous-time estimation, certifiable optimization, hybrid inference, and satellite navigation. Author Frank Dellaert recommends upgrading.
More from Embodied
- NVIDIA and MIT Release Long-WAM: 19.2s Visual Context Boosts Robot Success to 78.7% — songhan_mit · 2026-10-09
- BiGym 2.0: LLM-Written Policies Hit 65% From One Demo, But π0.5 Still Leads at 75% — stepjamUK · 2026-10-09
- Dev builds interactive teardown of a humanoid robot with 56 actuated joints using Claude Opus — techartist_ · 2026-10-09
- multimodalart gets hands on a microduck prototype hardware — multimodalart · 2026-10-09
- Interface, a $99 Handheld Controller for AI Agents, Opens Waitlist Ahead of January Ship — cneuralnetwork · 2026-10-09
- Apple announces surprise Oct 13 'Welcome home' event: smart home hub, Apple TV, LG devices — tomwarren · 2026-10-09