{"title":"Improved Gaussian Mixture Probabilistic Model for Pedestrian Trajectory\u0000Prediction of Autonomous Vehicle","authors":"Haonan Li, Xiaolan Wang, Xiao Su, Yansong Wang","doi":"10.2174/0122127976268211231110055647","DOIUrl":"https://doi.org/10.2174/0122127976268211231110055647","url":null,"abstract":"\u0000\u0000Pedestrian trajectory prediction plays a crucial role in ensuring the safe and\u0000efficient operation of autonomous vehicles in urban environments. As autonomous driving technology\u0000continues to advance, accurate anticipation of pedestrians' motion trajectories has become increasingly\u0000important for informing subsequent decision-making processes. Pedestrians are dynamic and unpredictable\u0000agents, and their movements can vary greatly depending on factors, such as their intentions,\u0000interactions with other pedestrians or vehicles, and the surrounding environment. Therefore, developing\u0000effective methods to predict pedestrian trajectories is essential to enable autonomous vehicles to\u0000navigate and interact with pedestrians in a safe and socially acceptable manner. Various methods, both\u0000patented and non-patented, have been proposed, including physics-based and probability-based models,\u0000to capture the regularities in pedestrian motion and make accurate predictions.\u0000\u0000\u0000\u0000This paper proposes a pedestrian trajectory prediction method that combines a Gaussian\u0000mixture model and an artificial potential field.\u0000\u0000\u0000\u0000The study begins with an analysis of pedestrian motion patterns, allowing for the identification\u0000of distinct patterns and incorporating speed as an influential factor in pedestrian interactions.\u0000Next, a Gaussian mixture model is utilized to model and train the trajectories of pedestrians within\u0000each motion pattern cluster, effectively capturing their statistical characteristics. The trained model is\u0000then used with a regression algorithm to predict future pedestrian trajectories based on their past positions.\u0000To enhance the accuracy and safety of the predicted trajectories, an artificial potential field\u0000analysis is employed, considering factors such as collision avoidance and interactions with other entities.\u0000By combining the Gaussian mixture model and artificial potential field, this method provides an\u0000innovative and patentable approach to pedestrian trajectory prediction.\u0000\u0000\u0000\u0000Experimental results on the ETH and UCY datasets demonstrate that the proposed method\u0000combining the Gaussian mixture model and artificial potential field outperforms traditional Linear and\u0000social force models in terms of prediction accuracy. The method effectively improves accuracy while\u0000ensuring collision avoidance.\u0000\u0000\u0000\u0000The proposed method combining a Gaussian mixture model and an artificial potential\u0000field enhances pedestrian trajectory prediction. It successfully captures the differences between pedestrians\u0000and incorporates speed, improving prediction accuracy.\u0000","PeriodicalId":39169,"journal":{"name":"Recent Patents on Mechanical Engineering","volume":"57 16","pages":""},"PeriodicalIF":0.0,"publicationDate":"2023-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138605116","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}