SLAMSqueezeBench benchmarks nine SLAM systems under realistic edge compute and memory constraints
zhenjun_zhao · x · 2026-09-19
arXiv paper SLAMSqueezeBench (Mohamed Hefny, Karthik Dantu, Steven Y. Ko) notes that SLAM runs alongside planning and manipulation on edge hardware, yet most systems are tested in isolation as if they were the only workload.
- The framework constrains compute and memory available to SLAM at runtime and simulates realistic camera acquisition with frame drops when a finite buffer fills.
- It benchmarks nine SLAM systems spanning classical, learning-based, and Gaussian splatting approaches.
- The testing framework will be released to the community upon publication.
More from Embodied
- ROS Weekly: ROSCon Global next week in Toronto, InOrbit open-sources Robot Ops — kscottz · 2026-09-19
- MOSS robot demo replays real Jev decisions in simulation, switching tasks from cans to bottles — kamathsblog · 2026-09-19
- Niantic Spatial launches Gaussian Splat Relighting beta for embodied AI simulation — Scobleizer · 2026-09-19
- AMB3R-SLAM: Kilometer-Scale Monocular SLAM on One Consumer GPU, 70% Lower ATE — zhenjun_zhao · 2026-09-19
- EliGSiR: continual RGB-D Gaussian Splatting mapping under bounded compute hits 21.52 dB on TUM RGB-D — zhenjun_zhao · 2026-09-19
- ABC-130K: largest open bimanual teleop dataset with 3,500 hours, headed to CoRL 2026 — pabbeel · 2026-09-19