Research map / Probabilistic and scientific modeling / Uncertainty and Gaussian processes
Building Continuous Occupancy Maps With Moving Robots
Ransalu Senanayake, Fabio Ramos
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use BHM instead of VSDGPOM for moving-robot occupancy mapping | continuous occupancy mapping · Dataset 2 and 3 | AUC: 0.80 -> 0.83 (Dataset 2); 0.79 -> 0.92 (Dataset 3) | Improved |
| Use BHM instead of VSDGPOM | continuous occupancy mapping · Dataset 2 and 3 | NLL: 0.37 -> 0.47 (Dataset 2); 0.53 -> 0.36 (Dataset 3) | Mixed |
| Increase number of samples used to compute kernel convolution over region supports (ablation) | BHM · Dataset 1 | accuracy | Improved |
| Use region supports (regionalization) instead of point supports (sample size 1) (ablation) | BHM · Dataset 1 | accuracy | Improved |
| Larger granularity (support spacing) with regionalization (ablation) | BHM · Dataset 1 | accuracy | Mixed |
| Incremental BHM update versus VSDGPOM as more data are captured | mapping runtime · Dataset 2 | update run time | Improved |
| Use BHM kernel versus VSDGPOM for edge fidelity | map quality · Dataset 3 | qualitative map sharpness | Improved |
Closest papers by meaning
- Accurate Training Data for Occupancy Map Prediction in Automated Driving Using Evidence Theory (CVPR 2024 · similarity 0.85)
- EvOcc: Accurate Semantic Occupancy for Automated Driving Using Evidence Theory (CVPR 2025 · similarity 0.85)
- Spatiotemporal Decoupling for Efficient Vision-Based Occupancy Forecasting (CVPR 2025 · similarity 0.84)
- GaussianWorld: Gaussian World Model for Streaming 3D Occupancy Prediction (CVPR 2025 · similarity 0.84)
- GaussianFormer-2: Probabilistic Gaussian Superposition for Efficient 3D Occupancy Prediction (CVPR 2025 · similarity 0.83)
- ODG: Occupancy Prediction Using Dual Gaussians (NeurIPS 2025 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
