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.

Constraint-Informed Learning for Warm Starting Trajectory OptimizationFuture spacecraft and surface robotic missions require increasingly capable autonomy stacks for exploring challenging and unstructured domains and trajectory optimization will be a cornerstone of such autonomy stacks. However, the nonlinear optimization solvers required remain too slow for use on relatively resource constrained flight-grade computers. In this work, we turn towards amortized optimization, a learning-based technique for accelerating optimization run times, and present TOAST: Trajectory Optimization with Merit Function Warm Starts. Offline, using data collected from a simulation, we train a neural network to learn a mapping to the full primal and dual solutions given the problem parameters. Crucially, we build upon recent results from decision-focused learning and present a set of decision-focused loss functions using the notion of merit functions for optimization problems. We show that training networks with such constraint-informed losses can better encode the structure of the trajectory optimization problem and jointly learn to reconstruct the primal-dual solution while also yielding improved constraint satisfaction. Through numerical experiments on a Lunar rover problem, we demonstrate that TOAST outperforms benchmark approaches in terms of both computation times and network prediction constraint satisfaction.

Full Paper