Online Goal Recognition using Path Signature and Dynamic Time Warping
基于路径签名和动态时间规整的在线目标识别
机构 * Pontifícia Universidade Católica do Rio Grande do Sul(圣保罗天主教大学里约格兰德杜斯乌尔古斯分校) ; King’s College London(伦敦国王学院) ; University of Aberdeen(阿伯丁大学)
AI总结 本文提出一种基于路径签名和动态时间规整的在线目标识别方法,通过高效编码轨迹和有效比较轨迹,提升预测准确性和在线规划效率。
Comments Accepted as part of the 35th International Joint Conference on Artificial Intelligence