VISTA: Open-Vocabulary, Task-Relevant Robot Exploration with Online Semantic Gaussian Splatting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Nagami, Keiko, Chen, Timothy, Yu, Javier, Shorinwa, Ola, Adang, Maximilian, Dougherty, Carlyn, Cristofalo, Eric, Schwager, Mac
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908429951434752
author Nagami, Keiko
Chen, Timothy
Yu, Javier
Shorinwa, Ola
Adang, Maximilian
Dougherty, Carlyn
Cristofalo, Eric
Schwager, Mac
author_facet Nagami, Keiko
Chen, Timothy
Yu, Javier
Shorinwa, Ola
Adang, Maximilian
Dougherty, Carlyn
Cristofalo, Eric
Schwager, Mac
contents We present VISTA (Viewpoint-based Image selection with Semantic Task Awareness), an active exploration method for robots to plan informative trajectories that improve 3D map quality in areas most relevant for task completion. Given an open-vocabulary search instruction (e.g., "find a person"), VISTA enables a robot to explore its environment to search for the object of interest, while simultaneously building a real-time semantic 3D Gaussian Splatting reconstruction of the scene. The robot navigates its environment by planning receding-horizon trajectories that prioritize semantic similarity to the query and exploration of unseen regions of the environment. To evaluate trajectories, VISTA introduces a novel, efficient viewpoint-semantic coverage metric that quantifies both the geometric view diversity and task relevance in the 3D scene. On static datasets, our coverage metric outperforms state-of-the-art baselines, FisherRF and Bayes' Rays, in computation speed and reconstruction quality. In quadrotor hardware experiments, VISTA achieves 6x higher success rates in challenging maps, compared to baseline methods, while matching baseline performance in less challenging maps. Lastly, we show that VISTA is platform-agnostic by deploying it on a quadrotor drone and a Spot quadruped robot. Open-source code will be released upon acceptance of the paper.
format Preprint
id arxiv_https___arxiv_org_abs_2507_01125
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VISTA: Open-Vocabulary, Task-Relevant Robot Exploration with Online Semantic Gaussian Splatting
Nagami, Keiko
Chen, Timothy
Yu, Javier
Shorinwa, Ola
Adang, Maximilian
Dougherty, Carlyn
Cristofalo, Eric
Schwager, Mac
Robotics
We present VISTA (Viewpoint-based Image selection with Semantic Task Awareness), an active exploration method for robots to plan informative trajectories that improve 3D map quality in areas most relevant for task completion. Given an open-vocabulary search instruction (e.g., "find a person"), VISTA enables a robot to explore its environment to search for the object of interest, while simultaneously building a real-time semantic 3D Gaussian Splatting reconstruction of the scene. The robot navigates its environment by planning receding-horizon trajectories that prioritize semantic similarity to the query and exploration of unseen regions of the environment. To evaluate trajectories, VISTA introduces a novel, efficient viewpoint-semantic coverage metric that quantifies both the geometric view diversity and task relevance in the 3D scene. On static datasets, our coverage metric outperforms state-of-the-art baselines, FisherRF and Bayes' Rays, in computation speed and reconstruction quality. In quadrotor hardware experiments, VISTA achieves 6x higher success rates in challenging maps, compared to baseline methods, while matching baseline performance in less challenging maps. Lastly, we show that VISTA is platform-agnostic by deploying it on a quadrotor drone and a Spot quadruped robot. Open-source code will be released upon acceptance of the paper.
title VISTA: Open-Vocabulary, Task-Relevant Robot Exploration with Online Semantic Gaussian Splatting
topic Robotics
url https://arxiv.org/abs/2507.01125