Seeing through Uncertainty: Robust Task-Oriented Optimization in Visual Navigation

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pan, Yiyuan, Xu, Yunzhe, Liu, Zhe, Wang, Hesheng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917030284754944
author Pan, Yiyuan
Xu, Yunzhe
Liu, Zhe
Wang, Hesheng
author_facet Pan, Yiyuan
Xu, Yunzhe
Liu, Zhe
Wang, Hesheng
contents Visual navigation is a fundamental problem in embodied AI, yet practical deployments demand long-horizon planning capabilities to address multi-objective tasks. A major bottleneck is data scarcity: policies learned from limited data often overfit and fail to generalize OOD. Existing neural network-based agents typically increase architectural complexity that paradoxically become counterproductive in the small-sample regime. This paper introduce NeuRO, a integrated learning-to-optimize framework that tightly couples perception networks with downstream task-level robust optimization. Specifically, NeuRO addresses core difficulties in this integration: (i) it transforms noisy visual predictions under data scarcity into convex uncertainty sets using Partially Input Convex Neural Networks (PICNNs) with conformal calibration, which directly parameterize the optimization constraints; and (ii) it reformulates planning under partial observability as a robust optimization problem, enabling uncertainty-aware policies that transfer across environments. Extensive experiments on both unordered and sequential multi-object navigation tasks demonstrate that NeuRO establishes SoTA performance, particularly in generalization to unseen environments. Our work thus presents a significant advancement for developing robust, generalizable autonomous agents.
format Preprint
id arxiv_https___arxiv_org_abs_2510_00441
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Seeing through Uncertainty: Robust Task-Oriented Optimization in Visual Navigation
Pan, Yiyuan
Xu, Yunzhe
Liu, Zhe
Wang, Hesheng
Robotics
Visual navigation is a fundamental problem in embodied AI, yet practical deployments demand long-horizon planning capabilities to address multi-objective tasks. A major bottleneck is data scarcity: policies learned from limited data often overfit and fail to generalize OOD. Existing neural network-based agents typically increase architectural complexity that paradoxically become counterproductive in the small-sample regime. This paper introduce NeuRO, a integrated learning-to-optimize framework that tightly couples perception networks with downstream task-level robust optimization. Specifically, NeuRO addresses core difficulties in this integration: (i) it transforms noisy visual predictions under data scarcity into convex uncertainty sets using Partially Input Convex Neural Networks (PICNNs) with conformal calibration, which directly parameterize the optimization constraints; and (ii) it reformulates planning under partial observability as a robust optimization problem, enabling uncertainty-aware policies that transfer across environments. Extensive experiments on both unordered and sequential multi-object navigation tasks demonstrate that NeuRO establishes SoTA performance, particularly in generalization to unseen environments. Our work thus presents a significant advancement for developing robust, generalizable autonomous agents.
title Seeing through Uncertainty: Robust Task-Oriented Optimization in Visual Navigation
topic Robotics
url https://arxiv.org/abs/2510.00441