robotics
The Planner Checked Collisions Inside Gaussian Splat Scenes
An adjustable distance metric joined geometric safety costs with image-conditioned objectives.
Summary
An adjustable distance metric joined geometric safety costs with image-conditioned objectives.
CollisionSplatting defines a probability-inspired distance measure that operates directly on standard 3D Gaussian Splatting scenes. The team integrated it with GPU-accelerated model-predictive and tree-search planners so collision costs can be combined with learned image-space rewards. The authors report collision classification on par with or better than representative baselines, higher checking throughput and lower graphics-memory use, plus real-world navigation and manipulation demonstrations. Exact tradeoffs depend on scene reconstruction quality and the selected conservatism setting.
Why it matters
An adjustable distance metric joined geometric safety costs with image-conditioned objectives.
Limits and context
No additional limitation was separately recorded.
Key claims
An adjustable distance metric joined geometric safety costs with image-conditioned objectives.
Evidence: source-2026-09-29-011
Sources
- arXiv preprint 2609.35619arXiv · primary research
Corrections
No corrections have been recorded for this story.