卓汉逵-如何让大语言模型协助经典智能规划

如何让大模型辅助智能规划卓汉逵zhuohank@gmail.comhttps://www.xplan-lab.org动机•问题：质量不稳定，效率低•目标：完成工序，提高质量、稼动率•特点：动态，混料，柔性，实时动机Long term benefitLarge scale orders Large scale resource schedulingLots of manufacturing stepsComplicated supply chainLabor intensive•1.知识获取=》规划领域模型：质量和规模•2.规划求解=》动作序列：效率和质量智能规划问题•Symbolic planning:•domain models•synthesizing plans to transit initial states to goals•Different from classical control and classification problems, the solutions are complex and must be optimized in multi-step reasoning.location 1location 2location 1location 2s1s3s4takeputlocation 1location 2location 1location 2s0s2s5move1puttakemove1move1move2loadunloadmove2move2location 1location 2location 1location 2初始状态目标状态•智能规划问题：(O, s0, g)•O是动作模型的集合•s0是初始状态•g是目标状态•智能规划问题的解•规划：  = a1, a2, …, an•规划是智能规划问题的解，如果该规划可被执行，并最终实现目标g： (s0,a1) = s1  (s1,a2) = s2 …  (sn–1,an) = snsn satisfies g智能规划问题•三个不同的解：•take(crane1,loc1,c3,c1,p1), move(r1,loc2,loc1), move(r1,loc1,loc2), move(r1,loc2,loc1), load(crane1,loc1,