Optimize car trajectory in constrained time frame using dynamic/kinematic limits and collision as constraints for non-linear optimization problem. Localize with LiDAR scan matching and feed estimated pose to MPC.
Create realistic sensor model that enables optimization of sensor model parameters and reasoning about scene geometry.
Speed up RRT with artifical potential field while being able to escape local minima.
Spatially divide large maps into sub-regions and find high-level paths to provide guidance to low-level ECBS solvers in each sub-region.
Formulate high-level symbolic planning as a smooth optimization problem and combine with low-level CIO framework to optimize over complex contact planning problems.
Accurately model LiDAR sensor in a differentiable framework supporting gradient-based optimizations
Benchmark state-of-the-art motion planners and techniques for wheeled mobile robots to highlight their strengths and weaknesses.