STITCHER: Real-Time Trajectory Planning with Motion Primitive Search

TL;DR

STITCHER is an optimization-free, real-time trajectory planning framework for autonomous navigation that stitches short trajectory segments using graph search, enabling fast, safe, and feasible long-range trajectories in complex environments.

Contribution

The paper introduces STITCHER, a novel graph search-based planning method that avoids optimization, allowing real-time generation of long-range trajectories by stitching short segments.

Findings

Generates trajectories in milliseconds covering tens of meters

Outperforms optimization-based planners in safety and speed

Works effectively in complex, large environments

Abstract

Autonomous high-speed navigation through large, complex environments requires real-time generation of agile trajectories that are dynamically feasible, collision-free, and satisfy constraints. Most modern trajectory planning techniques rely on numerical optimization because high-quality, expressive trajectories that satisfy constraints can be systematically computed. However, strict requirements on computation time and the risk of numerical instability can limit the use of optimization-based planners in safety-critical situations. This work presents an optimization-free planning framework called STITCHER that leverages graph search to generate long-range trajectories by stitching short trajectory segments together in real time. STITCHER is shown to outperform modern optimization-based planners through its innovative planning architecture and several algorithmic developments that make real-time planning possible. Simulation results show safe trajectories through complex environments can be generated in milliseconds that cover tens of meters.