CVSep 14, 2025

End-to-End Visual Autonomous Parking via Control-Aided Attention

arXiv:2509.11090v12 citationsh-index: 8Has Code
Originality Incremental advance
AI Analysis

This work addresses autonomous parking for self-driving cars, presenting an incremental improvement over existing end-to-end methods.

The paper tackles the problem of end-to-end visual autonomous parking by addressing the lack of synergy between perception and control in existing approaches, proposing CAA-Policy with a Control-Aided Attention mechanism that improves accuracy, robustness, and interpretability in CARLA simulator experiments.

Precise parking requires an end-to-end system where perception adaptively provides policy-relevant details-especially in critical areas where fine control decisions are essential. End-to-end learning offers a unified framework by directly mapping sensor inputs to control actions, but existing approaches lack effective synergy between perception and control. We find that transformer-based self-attention, when used alone, tends to produce unstable and temporally inconsistent spatial attention, which undermines the reliability of downstream policy decisions over time. Instead, we propose CAA-Policy, an end-to-end imitation learning system that allows control signal to guide the learning of visual attention via a novel Control-Aided Attention (CAA) mechanism. For the first time, we train such an attention module in a self-supervised manner, using backpropagated gradients from the control outputs instead of from the training loss. This strategy encourages the attention to focus on visual features that induce high variance in action outputs, rather than merely minimizing the training loss-a shift we demonstrate leads to a more robust and generalizable policy. To further enhance stability, CAA-Policy integrates short-horizon waypoint prediction as an auxiliary task, and introduces a separately trained motion prediction module to robustly track the target spot over time. Extensive experiments in the CARLA simulator show that \titlevariable~consistently surpasses both the end-to-end learning baseline and the modular BEV segmentation + hybrid A* pipeline, achieving superior accuracy, robustness, and interpretability. Code is released at https://github.com/Joechencc/CAAPolicy.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes