Paper Reading AI Learner

Learning Agile Gate Traversal via Analytical Optimal Policy Gradient

2025-08-29 12:48:39
Tianchen Sun, Bingheng Wang, Longbin Tang, Yichao Gao, Lin Zhao

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

PDF

https://arxiv.org/pdf/2508.21592.pdf


Tags
3D Action Action_Localization Action_Recognition Activity Adversarial Agent Attention Autonomous Bert Boundary_Detection Caption Chat Classification CNN Compressive_Sensing Contour Contrastive_Learning Deep_Learning Denoising Detection Dialog Diffusion Drone Dynamic_Memory_Network Edge_Detection Embedding Embodied Emotion Enhancement Face Face_Detection Face_Recognition Facial_Landmark Few-Shot Gait_Recognition GAN Gaze_Estimation Gesture Gradient_Descent Handwriting Human_Parsing Image_Caption Image_Classification Image_Compression Image_Enhancement Image_Generation Image_Matting Image_Retrieval Inference Inpainting Intelligent_Chip Knowledge Knowledge_Graph Language_Model LLM Matching Medical Memory_Networks Multi_Modal Multi_Task NAS NMT Object_Detection Object_Tracking OCR Ontology Optical_Character Optical_Flow Optimization Person_Re-identification Point_Cloud Portrait_Generation Pose Pose_Estimation Prediction QA Quantitative Quantitative_Finance Quantization Re-identification Recognition Recommendation Reconstruction Regularization Reinforcement_Learning Relation Relation_Extraction Represenation Represenation_Learning Restoration Review RNN Robot Salient Scene_Classification Scene_Generation Scene_Parsing Scene_Text Segmentation Self-Supervised Semantic_Instance_Segmentation Semantic_Segmentation Semi_Global Semi_Supervised Sence_graph Sentiment Sentiment_Classification Sketch SLAM Sparse Speech Speech_Recognition Style_Transfer Summarization Super_Resolution Surveillance Survey Text_Classification Text_Generation Time_Series Tracking Transfer_Learning Transformer Unsupervised Video_Caption Video_Classification Video_Indexing Video_Prediction Video_Retrieval Visual_Relation VQA Weakly_Supervised Zero-Shot