Guaranteeing safety in motion planning is a crucial bottleneck on the path towards wider adoption of autonomous driving technology. A promising direction is to pose safety requirements as planning constraints in nonlinear optimization problems of motion synthesis. However, many implementations of this approach are hindered by uncertain convergence and localoptimality of the solutions, affecting the planner’s overall robust-ness. In this paper, we propose a novel two-stage optimization framework: we first find the solution to a Mixed-Integer Linear Programming (MILP) approximation of the motion synthesis problem, which in turn initializes a second Nonlinear Program-ming (NLP) formulation. We show that initializing the NLP stage with the MILP solution leads to better convergence, lower costs, and outperforms a state-of-the-art Nonlinear Model Predictive Control baseline in both progress and comfort metrics.