The author explores the parameterized complexity of motion planning for rectangular robots, focusing on axis-aligned translations and different motion modes, providing fixed-parameter tractable algorithms.
The author presents a robust motion planning algorithm that learns obstacle uncertainties to improve safety and feasibility in dynamic environments.
PINSAT introduces systematic parallelization in INSAT to reduce planning times while maintaining lower costs.
REDEFINED proposes a novel real-time motion planning algorithm using neural networks for safe trajectory design.