Abstract
Traversing narrow gates presents a significant challenge and has become a standard benchmark for evaluating agile and precise quadrotor flight. Traditional modularized autonomous flight stacks require extensive design and parameter tuning, while end-to-end reinforcement learning (RL) methods often suffer from low sample efficiency and limited interpretability. In this work, we present a novel hybrid framework that adaptively fine-tunes model predictive control (MPC) parameters online using outputs from a neural network (NN) trained offline. The NN jointly predicts a reference pose and cost-function weights, conditioned on the coordinates of the gate corners and the current drone state. To achieve efficient training, we derive analytical policy gradients not only for the MPC module but also for an optimization-based gate traversal detection module. Furthermore, we introduce a new formulation of the attitude tracking error that admits a simplified representation, facilitating effective learning with bounded gradients. Hardware experiments demonstrate that our method enables fast and accurate quadrotor traversal through narrow gates in confined environments. It achieves several orders of magnitude improvement in sample efficiency compared to naive end-to-end RL approaches.
Abstract (translated)
穿越狭窄的门洞提出了一个重要的挑战,并已成为评估四旋翼机灵巧和精确飞行的标准基准。传统的模块化自主飞行堆栈需要大量的设计和参数调整,而端到端强化学习(RL)方法通常在样本效率低且解释性有限方面存在问题。 在这项工作中,我们提出了一种新颖的混合框架,该框架能够在线自适应地微调模型预测控制(MPC)参数,利用一个经过离线训练的神经网络(NN)的输出。这个神经网络同时根据门洞角点坐标和当前无人机状态来预测参考姿态和代价函数权重。为了实现高效的训练,我们推导出了分析性策略梯度,不仅针对MPC模块,还针对基于优化的门洞穿越检测模块。 此外,我们提出了一种新的姿态跟踪误差公式化方法,该方法允许简化表示,并且具有有界梯度,从而有助于有效的学习过程。硬件实验表明,我们的方法使四旋翼机能够快速准确地在狭窄环境中穿过门洞。与简单的端到端RL方法相比,它在样本效率方面提高了几个数量级。
URL
https://arxiv.org/abs/2508.21592