Constraint-Informed Learning for Warm-Starting Trajectory Optimization 

Schematic of the TOAST: Trajectory Optimization with Merit Function Warm Starts approach for learning warm starts using task-relevant merit functions. The problem parameters θ are used to make a prediction for the warm start to the optimization problem (shown in green). The neural network (shown in pink) with parameters ϕ used to generate this prediction is trained offline to minimize the task-relevant merit function associated with the optimization problem using offline data.