This book is the compendium of Chinese meteorologist Song Yingjie's research on the 24 solar terms.It encompasses the author's years of accumulated research,data,and cultural knowledge.From a meteorological pe...This book is the compendium of Chinese meteorologist Song Yingjie's research on the 24 solar terms.It encompasses the author's years of accumulated research,data,and cultural knowledge.From a meteorological perspective,this book applies charts based on climate big data,combined with literary writing techniques and meteorological algorithms,to present the knowledge of the twenty-four solar terms to readers.展开更多
Autonomous vehicles with self-evolution capabilities are expected to improve their performance through learning algorithms,to automatically adapt to the external environment.However,due to the infinity,complexity,and ...Autonomous vehicles with self-evolution capabilities are expected to improve their performance through learning algorithms,to automatically adapt to the external environment.However,due to the infinity,complexity,and variability of the actual traffic environment,it is necessary to develop quantitative representation indicators of scenario difficulty and generate targeted scenarios to ensure the evolution gradually,so as to quickly approach the performance limit of the algorithm.Therefore,this paper proposes a data-driven quantitative representation method of scenario difficulty.Specifically,the concept of environment agent is proposed,and a reinforcement learning method combined with mechanism knowledge is constructed for policy search to obtain an agent with an adversarial behavior.The model parameters of the environment agent at different stages in the training process are extracted to construct a policy group,and then agents with different adversarial intensities are obtained,which are used to realize data generation in different difficulty scenarios through the simulation environment.Finally,a data-driven scenario difficulty quantitative representation model is constructed,which is used to output the environment agent policy under different difficulties.Experimental results show the effectiveness of the proposed method.The result analysis shows that the proposed algorithm can generate reasonable and interpretable scenarios with high discrimination and can provide quantifiable difficulty representation without any expert logic rule design.Compared with the rule-based discrete scenario difficulty representation method,the proposed algorithm can achieve continuous difficulty representation.The video link is https://www.youtube.com/watch?v=GceGdqAm9Ys.展开更多
文摘This book is the compendium of Chinese meteorologist Song Yingjie's research on the 24 solar terms.It encompasses the author's years of accumulated research,data,and cultural knowledge.From a meteorological perspective,this book applies charts based on climate big data,combined with literary writing techniques and meteorological algorithms,to present the knowledge of the twenty-four solar terms to readers.
基金the National Key R&D Program of China under Grant No.2022YFB2502900the National Natural Science Foundation of China(Grant Number:U23B2061)+1 种基金the Fundamental Research Funds for the Central Universities of Chinathe Xiaomi Young Talent Program,and we thank the reviewers for the valuable suggestions.
文摘Autonomous vehicles with self-evolution capabilities are expected to improve their performance through learning algorithms,to automatically adapt to the external environment.However,due to the infinity,complexity,and variability of the actual traffic environment,it is necessary to develop quantitative representation indicators of scenario difficulty and generate targeted scenarios to ensure the evolution gradually,so as to quickly approach the performance limit of the algorithm.Therefore,this paper proposes a data-driven quantitative representation method of scenario difficulty.Specifically,the concept of environment agent is proposed,and a reinforcement learning method combined with mechanism knowledge is constructed for policy search to obtain an agent with an adversarial behavior.The model parameters of the environment agent at different stages in the training process are extracted to construct a policy group,and then agents with different adversarial intensities are obtained,which are used to realize data generation in different difficulty scenarios through the simulation environment.Finally,a data-driven scenario difficulty quantitative representation model is constructed,which is used to output the environment agent policy under different difficulties.Experimental results show the effectiveness of the proposed method.The result analysis shows that the proposed algorithm can generate reasonable and interpretable scenarios with high discrimination and can provide quantifiable difficulty representation without any expert logic rule design.Compared with the rule-based discrete scenario difficulty representation method,the proposed algorithm can achieve continuous difficulty representation.The video link is https://www.youtube.com/watch?v=GceGdqAm9Ys.
