paper-with-me

홈 › Papers

Cross-Modal Reinforcement Learning for Navigation with Degraded Depth Measurements

2026-03-23 · Omkar Sawant, Luca Zanatta, Grzegorz Malczyk, Kostas Alexis arxiv

This paper presents a cross-modal learning framework that exploits complementary information from depth and grayscale images for robust navigation. We introduce a Cross-Modal Wasserstein Autoencoder that learns shared latent representations by enforcing cross-modal consistency, enabling the system to infer depth-relevant features from grayscale observations when depth measurements are corrupted. The learned representations are integrated with a Reinforcement Learning-based policy for collision-free navigation in unstructured environments when depth sensors experience degradation due to adverse conditions such as poor lighting or reflective surfaces. Simulation and real-world experiments demonstrate that our approach maintains robust performance under significant depth degradation and successfully transfers to real environments.

📄 PDF Abstract BibTeX arXiv:2603.22182

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Vision-Depth Landmarks and Inertial Fusion for Navigation in Degraded Visual Environments

2019-03-05 · Shehryar Khattak, Christos Papachristos, Kostas Alexis

This paper proposes a method for tight fusion of visual, depth and inertial data in order to extend robotic capabilities for navigation in GPS-denied, poorly illuminated, and texture-less environments. Visual and depth i…

Cross-Modal Contrastive Learning of Representations for Navigation using Lightweight, Low-Cost Millimeter Wave Radar for Adverse Environmental Conditions

2021-01-10 · Jui-Te Huang, Chen-Lung Lu, Po-Kai Chang, Ching-I Huang 외

Deep reinforcement learning (RL), where the agent learns from mistakes, has been successfully applied to a variety of tasks. With the aim of learning collision-free policies for unmanned vehicles, deep RL has been used f…

Autonomous NavigationContrastive LearningDeep Reinforcement LearningReinforcement Learning (RL)

GeomPrompt: Geometric Prompt Learning for RGB-D Semantic Segmentation Under Missing and Degraded Depth

2026-04-13 · Krishna Jaganathan, Patricio Vela arxiv

Multimodal perception systems for robotics and embodied AI often assume reliable RGB-D sensing, but in practice, depth is frequently missing, noisy, or corrupted. We thus present GeomPrompt, a lightweight cross-modal ada…

Semantic Segmentation

InconSeg: Residual-Guided Fusion With Inconsistent Multi-Modal Data for Negative and Positive Road Obstacles Segmentation

2023-05-02 · journal 2023 5 · Zhen Feng ID, Yanning Guo ID, David Navarro-Alarcon ID, Yueyong Lyu ID 외

Segmentation of road obstacles, including negative and positive obstacles, is critical to the safe navigation of autonomous vehicles. Recent methods have witnessed an increasing interest in using multi-modal data fusion …

Autonomous VehiclesDecoderRoad Damage DetectionSegmentation

Path-conditioned Reinforcement Learning-based Local Planning for Long-Range Navigation

2026-03-14 · Mateo Haro, Julia Richter, Fan Yang, Cesar Cadena 외 arxiv

Long-range navigation is commonly addressed through hierarchical pipelines in which a global planner generates a path, decomposed into waypoints, and followed sequentially by a local planner. These systems are sensitive …

Reinforcement Learning