MIT News August 10, 2021
Researchers at MIT developed a multi-fidelity Bayesian optimization framework that models the feasibility constraints based on analytical approximation, numerical simulation, and real-world flight experiments. By combining evaluations at different fidelities, trajectory time is optimized while the number of costly flight experiments is kept to a minimum. The algorithm is thoroughly evaluated for the trajectory generation problem in two different scenarios: (1) connecting predetermined waypoints; (2) planning in obstacle-rich environments. They found that a drone trained with their algorithm flew through a simple obstacle course up to 20 percent faster than a drone trained on conventional planning algorithms. In some cases, it chose to slow a drone down to handle a tricky curve or save its energy. Resulting trajectories were found to be significantly faster than those obtained through minimum-snap trajectory planning…read more. Open Access TECHNICAL ARTICLE
Overview of the proposed algorithm that models dynamic feasibility constraints based on simulation and flight data to efficiently find the time-optimal trajectory. Credit: The International Journal of Robotics, July 29, 2021Â