Planning, Fast and Slow: A Framework for Adaptive Real-Time Safe Trajectory Planning
For autonomous systems operating in unknown environments, this work provides a method to adapt motion plans in real-time while maintaining safety guarantees, addressing a key limitation of existing planners.
This paper introduces a meta-planning framework that extends FaSTrack to allow safe switching between online planners, enabling adaptive real-time trajectory planning with strict safety guarantees. The approach is validated in simulation and on a Crazyflie 2.0 quadrotor.
Motion planning is an extremely well-studied problem in the robotics community, yet existing work largely falls into one of two categories: computationally efficient but with few if any safety guarantees, or able to give stronger guarantees but at high computational cost. This work builds on a recent development called FaSTrack in which a slow offline computation provides a modular safety guarantee for a faster online planner. We introduce the notion of "meta-planning" in which a refined offline computation enables safe switching between different online planners. This provides autonomous systems with the ability to adapt motion plans to a priori unknown environments in real-time as sensor measurements detect new obstacles, and the flexibility to maneuver differently in the presence of obstacles than they would in free space, all while maintaining a strict safety guarantee. We demonstrate the meta-planning algorithm both in simulation and in hardware using a small Crazyflie 2.0 quadrotor.