Graphs of convex sets with Bezier paths and a simplified bicycle model produce trajectories that closely match nonlinear optimal control results but with better speed and initialization robustness in CommonRoad driving scenarios.
Title resolution pending
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
representative citing papers
Featurized Occupation Measures create a primal-dual framework that couples explicit HJB subsolutions with scalable trajectory optimization, proving asymptotic consistency and shifting dimensionality limits to system interconnection topology.
The authors derive a computable lower bound on the continuous second variation from discrete KKT points and residuals, providing a sufficient certificate for second-order sufficiency when the bound is positive.
GATO is a new batched GPU trajectory optimization solver that achieves real-time MPC throughput with 18-21x speedups over CPU baselines for tens to low-hundreds of simultaneous solves.
Neural network predicts raceline offsets from local track geometry using Formula 1 data to initialize minimum-time optimal control, accelerating solver convergence on 17 tracks while preserving lap times.
citing papers explorer
-
Motion Planning for Autonomous Vehicles using Optimization over Graphs of Convex Sets
Graphs of convex sets with Bezier paths and a simplified bicycle model produce trajectories that closely match nonlinear optimal control results but with better speed and initialization robustness in CommonRoad driving scenarios.
-
Featurized Occupation Measures for Structured Global Search in Numerical Optimal Control
Featurized Occupation Measures create a primal-dual framework that couples explicit HJB subsolutions with scalable trajectory optimization, proving asymptotic consistency and shifting dimensionality limits to system interconnection topology.
-
A Posteriori Second-Order Guarantees for Bolza Problems via Collocation
The authors derive a computable lower bound on the continuous second variation from discrete KKT points and residuals, providing a sufficient certificate for second-order sufficiency when the bound is positive.
-
GATO: GPU-Accelerated and Batched Trajectory Optimization for Scalable Edge Model Predictive Control
GATO is a new batched GPU trajectory optimization solver that achieves real-time MPC throughput with 18-21x speedups over CPU baselines for tens to low-hundreds of simultaneous solves.
-
Efficient Trajectory Optimization for Autonomous Racing via Formula-1 Data-Driven Initialization
Neural network predicts raceline offsets from local track geometry using Formula 1 data to initialize minimum-time optimal control, accelerating solver convergence on 17 tracks while preserving lap times.