Robust Robotic Exploration and Mapping Using Generative Occupancy Map Synthesis

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Achey, Lorin, Reed, Alec, Crowe, Brendan, Hayes, Bradley, Heckman, Christoffer
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911344362520576
author Achey, Lorin
Reed, Alec
Crowe, Brendan
Hayes, Bradley
Heckman, Christoffer
author_facet Achey, Lorin
Reed, Alec
Crowe, Brendan
Hayes, Bradley
Heckman, Christoffer
contents We present a novel approach for enhancing robotic exploration by using generative occupancy mapping. We implement SceneSense, a diffusion model designed and trained for predicting 3D occupancy maps given partial observations. Our proposed approach probabilistically fuses these predictions into a running occupancy map in real-time, resulting in significant improvements in map quality and traversability. We deploy SceneSense on a quadruped robot and validate its performance with real-world experiments to demonstrate the effectiveness of the model. In these experiments we show that occupancy maps enhanced with SceneSense predictions better estimate the distribution of our fully observed ground truth data ($24.44\%$ FID improvement around the robot and $75.59\%$ improvement at range). We additionally show that integrating SceneSense enhanced maps into our robotic exploration stack as a ``drop-in'' map improvement, utilizing an existing off-the-shelf planner, results in improvements in robustness and traversability time. Finally, we show results of full exploration evaluations with our proposed system in two dissimilar environments and find that locally enhanced maps provide more consistent exploration results than maps constructed only from direct sensor measurements.
format Preprint
id arxiv_https___arxiv_org_abs_2506_20049
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Robust Robotic Exploration and Mapping Using Generative Occupancy Map Synthesis
Achey, Lorin
Reed, Alec
Crowe, Brendan
Hayes, Bradley
Heckman, Christoffer
Robotics
Artificial Intelligence
We present a novel approach for enhancing robotic exploration by using generative occupancy mapping. We implement SceneSense, a diffusion model designed and trained for predicting 3D occupancy maps given partial observations. Our proposed approach probabilistically fuses these predictions into a running occupancy map in real-time, resulting in significant improvements in map quality and traversability. We deploy SceneSense on a quadruped robot and validate its performance with real-world experiments to demonstrate the effectiveness of the model. In these experiments we show that occupancy maps enhanced with SceneSense predictions better estimate the distribution of our fully observed ground truth data ($24.44\%$ FID improvement around the robot and $75.59\%$ improvement at range). We additionally show that integrating SceneSense enhanced maps into our robotic exploration stack as a ``drop-in'' map improvement, utilizing an existing off-the-shelf planner, results in improvements in robustness and traversability time. Finally, we show results of full exploration evaluations with our proposed system in two dissimilar environments and find that locally enhanced maps provide more consistent exploration results than maps constructed only from direct sensor measurements.
title Robust Robotic Exploration and Mapping Using Generative Occupancy Map Synthesis
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2506.20049