SinoTechIntel Academic Portal
Official PDF TranslationFrontiers of Information Technology & Electronic Engineering

E2MN: human-inspired end-to-end mapless navigation with oscillation suppression and short-term memory

Authors: Yinan Yang; Zhiye Wang; Xuan Kong; Peng Zhi; Dapeng Zhang; Rui Zhou; Qingguo Zhou

DOI: 10.1631/FITEE_2500348Status: Verified Translated Edition
Sponsored AdvertisementAd Placement Area
reCAPTCHA Bot Shield Active

Preparing Secure Academic Download

Verifying human reader & generating high-resolution document...

Verifying Document Integrity15s remaining
← Back to Article
Protected by Google reCAPTCHA v3.PrivacyTerms
Sponsored ContentAdSense In-Feed Ad Slot

Key Findings in This Report

• Proposes a lightweight, interpretable mapless navigation method using only 2D LiDAR, mimicking human strategies to escape dead ends without requiring prior maps. • Effectively suppresses oscillations and enables autonomous recovery from local minimum traps, addressing key challenges in mapless navigation. • Achieves map-like performance without a map, reducing average path length by 50.51% compared to the classical Bug2 algorithm. • Increases path length by only 17.57% compared to map-based navigation, demonstrating robustness across diverse environments.