Learning waypoints and timing guides improve multi-quadrotor flight paths
Learning Waypoints and Passage Events for Decentralized Multi-Quadrotor Trajectory Planning
Robotics
Summary
Coordinating several drones to fly safely through a space is hard because they must avoid collisions while following physical limits and timing restrictions. The authors present a way to teach computers to predict key navigation points and timing events for each drone independently, yet keep them coordinated using a shared timeline. Their method combines learning with optimization that respects drone dynamics and thrust limits. Tests show this approach keeps drones on feasible and well-timed paths across new layouts efficiently.
What this means in practice
- •For drone fleet operators: Coordinate multiple drones to navigate complex spaces efficiently without collisions using learned waypoints and timing.
- •For robotics developers: Build decentralized multi-drone systems that generate feasible flight paths respecting vehicle dynamics with improved coordination performance.
Authors
Yunhan Shi, Jia Deng, Zehao Jia, Lin Cheng, Shengping Gong
Abstract
Multi-quadrotor passage planning requires coordinated spatial routes and passage times under vehicle dynamics and actuation constraints. Optimizing these decisions jointly couples temporal allocation, nonlinear motion, and inter-vehicle interactions, creating a computational challenge for local trajectory generation. We propose a learning-optimization framework that predicts spatial waypoints and ordered passage events for independently solved quadrotor planners. A common physical time grid aligns the vehicles, with intermediate events fixed by the networks and terminal progress optimized locally to permit different completion metrics. Differentiable sequential convex programming incorporates rigid-body dynamics and rotor-thrust bounds, allowing collision and completion gradients to train both networks through the generated trajectories. In a two-quadrotor evaluation across 24 layouts, the adapted policy passes physical feasibility and sampled separation checks in all five held-out layouts. Their mean completion metric decreases by 1.52% relative to the inherited policy. The median forward time is 21.01 ms on the held-out exchange layout with matching numerical trajectory references. These results demonstrate that learned spatial and event parameters can coordinate independent rigid-body planners while preserving local vehicle constraints in the evaluated scenarios.