Paper Reading AI Learner

DAA*: Deep Angular A Star for Image-based Path Planning

2025-07-12 14:46:42
Zhiwei Xu

Abstract

Path smoothness is often overlooked in path imitation learning from expert demonstrations. In this paper, we introduce a novel learning method, termed deep angular A* (DAA*), by incorporating the proposed path angular freedom (PAF) into A* to improve path similarity through adaptive path smoothness. The PAF aims to explore the effect of move angles on path node expansion by finding the trade-off between their minimum and maximum values, allowing for high adaptiveness for imitation learning. DAA* improves path optimality by closely aligning with the reference path through joint optimization of path shortening and smoothing, which correspond to heuristic distance and PAF, respectively. Throughout comprehensive evaluations on 7 datasets, including 4 maze datasets, 2 video-game datasets, and a real-world drone-view dataset containing 2 scenarios, we demonstrate remarkable improvements of our DAA* over neural A* in path similarity between the predicted and reference paths with a shorter path length when the shortest path is plausible, improving by 9.0% SPR, 6.9% ASIM, and 3.9% PSIM. Furthermore, when jointly learning pathfinding with both path loss and path probability map loss, DAA* significantly outperforms the state-of-the-art TransPath by 6.7% SPR, 6.5% PSIM, and 3.7% ASIM. We also discuss the minor trade-off between path optimality and search efficiency where applicable.

Abstract (translated)

路径平滑性在从专家演示中进行路径模仿学习时常常被忽视。在这篇论文中,我们引入了一种新的学习方法——深度角度A*(DAA*),通过将提出的路径角自由度(PAF)融入A*算法来提高路径相似性,并通过自适应路径平滑性实现这一目标。PAF旨在探索移动角度对路径节点扩展的影响,通过寻找其最小值和最大值之间的权衡,从而为模仿学习提供高度的适应性。DAA*通过联合优化路径缩短和平滑(分别对应启发式距离和PAF)来提高路径最优性,并且与参考路径紧密匹配。 我们在7个数据集上进行了全面评估,包括4个迷宫数据集、2个视频游戏数据集以及一个包含两个场景的真实世界无人机视图数据集。我们展示了DAA*在预测路径与参考路径之间的相似度方面显著优于神经A*,尤其是在最短路径是可能的情况下,路径长度更短。具体而言,在标准化路径评分(SPR)、角度相似性指标(ASIM)和路径相似性指标(PSIM)上分别提高了9.0%、6.9% 和3.9%。 此外,当同时学习路径搜索与路径损失和路径概率地图损失时,DAA*显著优于最先进的TransPath,在上述三个度量标准中分别提高了6.7%、3.7% 和 6.5%。我们还讨论了在适用情况下的路径最优性和搜索效率之间的微小权衡。 通过这种方式,DAA*不仅改善了路径模仿学习的平滑性,还在提高路径相似性和减少预测误差方面超越了现有方法。

URL

https://arxiv.org/abs/2507.09305

PDF

https://arxiv.org/pdf/2507.09305.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