Paper Reading AI Learner

Adaptive Lattice-based Motion Planning

2025-08-04 12:35:07
Abhishek Dhar, Sarthak Mishra, Spandan Roy, Daniel Axehill

Abstract

This paper proposes an adaptive lattice-based motion planning solution to address the problem of generating feasible trajectories for systems, represented by a linearly parameterizable non-linear model operating within a cluttered environment. The system model is considered to have uncertain model parameters. The key idea here is to utilize input/output data online to update the model set containing the uncertain system parameter, as well as a dynamic estimated parameter of the model, so that the associated model estimation error reduces over time. This in turn improves the quality of the motion primitives generated by the lattice-based motion planner using a nominal estimated model selected on the basis of suitable criteria. The motion primitives are also equipped with tubes to account for the model mismatch between the nominal estimated model and the true system model, to guarantee collision-free overall motion. The tubes are of uniform size, which is directly proportional to the size of the model set containing the uncertain system parameter. The adaptive learning module guarantees a reduction in the diameter of the model set as well as in the parameter estimation error between the dynamic estimated parameter and the true system parameter. This directly implies a reduction in the size of the implemented tubes and guarantees that the utilized motion primitives go arbitrarily close to the resolution-optimal motion primitives associated with the true model of the system, thus significantly improving the overall motion planning performance over time. The efficiency of the motion planner is demonstrated by a suitable simulation example that considers a drone model represented by Euler-Lagrange dynamics containing uncertain parameters and operating within a cluttered environment.

Abstract (translated)

这篇论文提出了一种自适应格子基础的运动规划解决方案,旨在解决在复杂环境中为非线性模型(该模型可通过线性参数化表示)生成可行轨迹的问题。系统模型被认为具有不确定的模型参数。其核心思想是利用输入/输出数据在线更新包含不确定系统参数的模型集以及动态估计的模型参数,从而随着时间推移减少相关模型估算误差。这反过来改进了基于选定名义估计模型(依据适当标准选取)生成的运动原语的质量。这些运动原语还配备了管状结构以考虑名义估计模型和真实系统模型之间的模型偏差,确保整个运动无碰撞。管状结构的大小是统一且直接与包含不确定系统参数的模型集大小成正比。自适应学习模块保证了模型集合直径以及动态估算参数与真实系统参数之间估计误差的减小,这直接意味着实施的管状结构尺寸减少,并确保所使用的运动原语可以无限接近于真实系统的分辨率最优运动原语,从而随着时间推移显著提高整体运动规划性能。通过考虑包含不确定参数并在复杂环境中操作的无人机模型(以欧拉-拉格朗日动力学表示)的适当仿真示例来展示了该运动计划器的有效性。

URL

https://arxiv.org/abs/2508.02350

PDF

https://arxiv.org/pdf/2508.02350.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