武汉大学李必军--中文主页

已经得到个称赞给我点赞

论文成果

当前位置: 中文主页 >> 科学研究 >> 论文成果

Reinforcement-Fine-Tuned LLM Navigation Decision-Making System: A Dynamic Obstacle Avoidance Method Based on the Time-decay Reward Mechanism

发表刊物：2025 Conference on Ubiquitous Positioning Indoor Navigation and Location Based Services-UPINLBS-Annual
论文类型：会议论文
ISSN号：2372-1685
是否译文：否
发表时间：2026-08-04

上一条：Risk-guided car-following and lane-changing model for safe navigation of autonomous driving vehicles

下一条：Positioning Uncertainty Estimation of LiDAR SLAM Based on Multifault Hypothesis Solution Separation and Lie Group Theory