日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

モデル予測制御arXiv:2308.06742

限界走行時の車両障害物回避のためのモデル予測輪郭制御

Model Predictive Contouring Control for Vehicle Obstacle Avoidance at the Limit of Handling

シェア:XThreadsFacebookLINEはてブBluesky

自動運転車が限界走行時に障害物を回避するため、非線形モデル予測輪郭制御(MPCC)を提案し、操舵とブレーキを最適化してリアルタイム性能と安定性を検証した。

著者: Alberto Bertipaglia, Mohsen Alirezaei, Riender Happee, Barys Shyrokau

分類: cs.RO, cs.SY, eess.SY

原文アブストラクト

This paper proposes a non-linear Model Predictive Contouring Control (MPCC) for obstacle avoidance in automated vehicles driven at the limit of handling. The proposed controller integrates motion planning, path tracking and vehicle stability objectives, prioritising obstacle avoidance in emergencies. The controller's prediction model is a non-linear single-track vehicle model with the Fiala tyre to capture the vehicle's non-linear behaviour. The MPCC computes the optimal steering angle and brake torques to minimise tracking error in safe situations and maximise the vehicle-to-obstacle distance in emergencies. Furthermore, the MPCC is extended with the tyre friction circle to fully exploit the vehicle's manoeuvrability and stability. The MPCC controller is tested using real-time rapid prototyping hardware to prove its real-time capability. The performance is compared with a state-of-the-art Model Predictive Control (MPC) in a high-fidelity simulation environment. The double lane change scenario results demonstrate a significant improvement in successfully avoiding obstacles and maintaining vehicle stability.

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. 2GXO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
  3. 3newmo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
  4. 4NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  5. 5UC BerkeleyとNVIDIAの研究者、AIエージェントでロボット制御コードを仮想環境で改善研究・技術

PR・アフィリエイト広告

FRONTIER(GPU搭載BTOパソコン)

FRONTIER(GPU搭載BTOパソコン)の公式広告バナーFRONTIERでGPU搭載PCを見る ↗
PR本紙発行元 EmplifAI