クロスビュー変換器による鳥瞰図マップの閉ループ評価：行動クローニング方策への入力として
Closed-Loop Evaluation of Bird's-Eye-View Maps from Cross-View Transformers as Inputs to Behavior-Cloning Policies
自動運転の行動クローニングにおいて、カメラ予測による鳥瞰図（BEV）マップを入力として用いた際の閉ループ性能をCARLAシミュレータで評価し、カーネル密度推定による重み付けが運転性能を向上させることを示した論文。
著者: Felipe Carlos dos Santos, Eric Antonelo, Gustavo Claudio Karl Couto
分類: cs.RO, cs.AI, cs.CV
原文アブストラクト
In autonomous driving, Bird's-Eye View (BEV) representations provide a structured, top-down abstraction of the vehicle's surroundings and have become a key input modality for Behavioral Cloning (BC) policies. While ground-truth BEV maps are readily available in simulation, real-world deployment requires replacing them with camera-predicted counterparts - a substitution that introduces perceptual errors whose downstream impact on closed-loop driving performance is not well understood. In this work, we investigate the use of Cross-View Transformer (CVT)-predicted BEV maps as direct policy inputs for a BC agent in the CARLA simulator. We propose a six-channel BEV representation covering road surface, planned route, lane boundaries, vehicles, pedestrians, and traffic lights, and introduce a Kernel Density Estimation (KDE) weighting scheme that rebalances the segmentation loss towards underrepresented driving maneuvers such as curves and intersections. Closed-loop evaluation across two CARLA towns shows that the KDE-weighted model is the only predicted-BEV agent to complete a full episode without infractions, despite not achieving the highest aggregate IoU. This discrepancy reveals that global segmentation metrics are poor proxies for driving performance: what determines navigation success is prediction quality at geometrically critical locations, and the route channel emerges as the primary bottleneck for reliable agent navigation under predicted BEV inputs.