CONACyT: Integration of Logical and Probabilistic Models for Gesture Recognition with Mobile Robots

该项目的主要理论目标是开发一种将逻辑的表达能力与概率技术的稳健性相结合的表示法，包括从经验中学习和适应的能力。为此，PI打算将归纳逻辑编程与贝叶斯网络相结合。在具有潜在高社会影响的领域内对该方法进行经验验证，将侧重于移动机器人的手势识别，以加强双边合作伙伴的专业知识。这一研究成果将极大地促进人机交互界面设计的发展。

The main theoretical objective of the project is to develop a representation that combines the expressive power of logic with the robustness of probabilistic techniques, including the ability to learn and adapt from experience. To this end, the PIs intend to integrate inductive logic programming with Bayesian networks. Empirical validation of the approach within the context of a domain with potential high social impact will focus on gesture recognition by mobile robots, in order to build upon the expertise of the bilateral partners. The results of this research will significantly advance the state of the art in human-robot interface design.