Automatic Parameter Adaptation for Quadrotor Trajectory Planning

TL;DR

This paper introduces an automated parameter adaptation framework for quadrotor trajectory planning that uses Bayesian Optimization and Particle Swarm Optimization to improve real-time performance and adaptability in complex environments.

Contribution

It presents a novel asynchronous optimization framework that enhances parameter tuning for quadrotor planners without human intervention, improving speed and scalability.

Findings

Outperforms existing strategies in benchmark tests.

Enables real-time adaptation to changing obstacle densities.

Demonstrates scalability across different drone platforms and environments.

Abstract

Online trajectory planners enable quadrotors to safely and smoothly navigate in unknown cluttered environments. However, tuning parameters is challenging since modern planners have become too complex to mathematically model and predict their interaction with unstructured environments. This work takes humans out of the loop by proposing a planner parameter adaptation framework that formulates objectives into two complementary categories and optimizes them asynchronously. Objectives evaluated with and without trajectory execution are optimized using Bayesian Optimization (BayesOpt) and Particle Swarm Optimization (PSO), respectively. By combining two kinds of objectives, the total convergence rate of the black-box optimization is accelerated while the dimension of optimized parameters can be increased. Benchmark comparisons demonstrate its superior performance over other strategies. Tests with changing obstacle densities validate its real-time environment adaption, which is difficult for prior manual tuning. Real-world flights with different drone platforms, environments, and planners show the proposed framework's scalability and effectiveness.