智能决策与规划

We develop a preference-conditioned graph reinforcement learning framework for fast Pareto set approximation in multi-objective flexible job shop scheduling. The method parallelizes preference-based learning and substantially improves both solution quality and computational speed on large-scale scheduling problems.

We propose a graph reinforcement learning framework with evolution strategies for dynamic job shop scheduling under machine breakdown and stochastic processing times. The approach formulates the scheduling problem as an MDP and learns robust policies that outperform reinforcement-learning-based and traditional baselines.

We introduce a formal modeling and design framework for self-evolvable robots that supports both structural and functional reconfiguration. The approach uses reconfiguration grammars and a correct-by-construction synthesis strategy to generate robot designs guaranteed to satisfy task specifications in a given workspace.