Paper Reading AI Learner

A Novel Narrow Region Detector for Sampling-Based Planners' Efficiency: Match Based Passage Identifier

2025-09-27 13:02:07
Yafes Enes \c{S}ahiner, Esat Yusuf G\"undo\u{g}du, Volkan Sezer

Abstract

Autonomous technology, which has become widespread today, appears in many different configurations such as mobile robots, manipulators, and drones. One of the most important tasks of these vehicles during autonomous operations is path planning. In the literature, path planners are generally divided into two categories: probabilistic and deterministic methods. In the analysis of probabilistic methods, the common problem of almost all methods is observed in narrow passage environments. In this paper, a novel sampler is proposed that deterministically identifies narrow passage environments using occupancy grid maps and accordingly increases the amount of sampling in these regions. The codes of the algorithm is provided as open source. To evaluate the performance of the algorithm, benchmark studies are conducted in three distinct categories: specific and random simulation environments, and a real-world environment. As a result, it is observed that our algorithm provides higher performance in planning time and number of milestones compared to the baseline samplers.

Abstract (translated)

今天广泛使用的自主技术以多种形式存在,如移动机器人、机械臂和无人机。在这些车辆的自主操作过程中,路径规划是最重要的任务之一。文献中通常将路径规划方法分为概率方法和确定性方法两大类。在对概率方法进行分析时,几乎所有方法在狭窄通道环境中都遇到了共同的问题。本文提出了一种新颖的采样器,该采样器使用占用栅格地图以确定性方式识别狭窄通道环境,并相应地增加这些区域内的采样量。算法代码作为开源提供。为了评估算法性能,我们在三类不同的基准测试中进行了研究:特定和随机仿真环境以及真实世界环境。结果表明,与基线采样器相比,我们的算法在规划时间和里程碑数量方面表现更优。

URL

https://arxiv.org/abs/2509.23288

PDF

https://arxiv.org/pdf/2509.23288.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot