Publications

A planning framework for floating-base multi-link robots that has been demonstrated on a real robot to generate continuous, collision-free, and dynamically feasible trajectories directly from raw point-cloud inputs, without relying on handcrafted obstacle models.

We introduce NEO-Planner, which uses a neural network to initialize trajectory optimization for autonomous drones, cutting computation by 26% without sacrificing quality.

An RRT-based path planning algorithm enables UAVs to replan safe paths when dynamic threats emerge.

A novel multi-UAV mobile edge computing framework, aiming to provide better Quality-of-Service and path planning based on reinforcement learning.