计算机科学
任务(项目管理)
动作(物理)
感知
人工智能
基线(sea)
机器学习
先验概率
相似性(几何)
事件(粒子物理)
语义学(计算机科学)
动作选择
碰撞
任务分析
视觉感受
期限(时间)
理论(学习稳定性)
动作识别
区间(图论)
运动(物理)
特征(语言学)
人机交互
集合(抽象数据类型)
数据挖掘
计算机视觉
选择(遗传算法)
机制(生物学)
维数(图论)
避碰
作者
Yeryeong Cho,Jaeyoung Choe,Joongheon Kim
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2025-10-14
卷期号:: 810-812
被引量:1
标识
DOI:10.1109/ictc66702.2025.11388300
摘要
Executing natural-language instructions in dynamic environments requires robust integration of perception, planning, and control. Conventional vision–language models (VLMs) provide open-vocabulary recognition but often leave a perception–action gap and fail to ensure safety under uncertainty. To address this challenge, we propose a Vision-Language Action Model (VLAM) that directly maps visual observations and instructions to actions through adaptive perception and uncertainty-aware control. The algorithm leverages contrastive language-image pretraining (CLIP)-based vision–language similarity to score candidate actions while incorporating rule-based safety priors as a fallback mechanism when confidence is low or collision risk is detected. This design narrows the perception–action gap, maintains semantic grounding, and guarantees stable behavior. We evaluate VLAM in a dynamic multi-agent environment with moving obstacles. Experimental results demonstrate that the proposed method achieves higher task success and reduced inter-agent conflicts compared to baseline strategies.
科研通智能强力驱动
Strongly Powered by AbleSci AI