從本段演講，你將了解如何設計、模擬、分析融合了多種感測器資料的系統，以維持自動駕駛/自主系統的位置、定位、情勢察覺能力。透過幾個範例，我們將：
- 建立多目標追蹤器與感測器融合過濾器
- 產生動作和感測器模型
- 針對真實及綜合的資料來設計資料關聯演算法
- 定義並匯入駕駛情境和路徑來進行模擬
- 針對雷達和攝影機產生綜合性的偵測資料，再配合GPS/IMU等感測器進行車輛的定位
- 透過標準化的利基比較、各種可能情境組合、生動的圖表來評估系統的準確性及性能表現
In this session, you will learn to design, simulate, and analyze systems that fuse data from multiple sensors to maintain position, orientation, and situational awareness for automated driving/autonomous systems. Through several examples, we will:
- Create multi-object trackers and sensor fusion filters
- Generate motion and sensor models
- Design data association algorithms for real and synthetic data
- Define and import scenarios and trajectories for simulation
- Generate synthetic detection data for radar and camera sensors, along with GPS/IMU sensors for localization
- Evaluate system accuracy and performance with standard benchmarks, metrics, and animated plots
|
