日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

群制御arXiv:2412.03095

合意ベース推定とほぼ等速モデルによる分散型移動目標追跡

Decentralized Mobile Target Tracking Using Consensus-Based Estimation with Nearly-Constant-Velocity Modeling

シェア:XThreadsFacebookLINEはてブBluesky

ほぼ等速モデルと合意ベース推定フィルタを組み合わせ、通信制約やノイズ下でも複数エージェントが協調して移動目標を追跡する分散型フレームワークを提案した。

著者: Amir Ahmad Ghods, Mohammadreza Doostmohammadian

分類: cs.MA, cs.RO, cs.SY, eess.SP, eess.SY, math.OC

原文アブストラクト

Mobile target tracking is crucial in various applications such as surveillance and autonomous navigation. This study presents a decentralized tracking framework utilizing a Consensus-Based Estimation Filter (CBEF) integrated with the Nearly-Constant-Velocity (NCV) model to predict a moving target's state. The framework facilitates agents in a network to collaboratively estimate the target's position by sharing local observations and achieving consensus despite communication constraints and measurement noise. A saturation-based filtering technique is employed to enhance robustness by mitigating the impact of noisy sensor data. Simulation results demonstrate that the proposed method effectively reduces the Mean Squared Estimation Error (MSEE) over time, indicating improved estimation accuracy and reliability. The findings underscore the effectiveness of the CBEF in decentralized environments, highlighting its scalability and resilience in the presence of uncertainties.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3Google DeepMind、ロボット向けAIを発表新製品・発表
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開

PR・アフィリエイト広告

OZ GAMING(GPU搭載BTOゲーミングPC)

OZ GAMING(GPU搭載BTOゲーミングPC)の公式広告バナーOZ GAMINGで完成品PCを見る ↗
PR本紙発行元 EmplifAI