Integration of Computer Vision with Adaptive Control for Autonomous Driving Using ADORE

2025-08-25

AI Summary

To address insufficient perception-decision coupling robustness in autonomous driving under uncertain conditions—such as sudden weather changes and encounters with unknown objects—this paper proposes a synergistic framework integrating context-aware visual perception with rule-driven adaptive decision-making. Methodologically, the perception module is enhanced based on YOLO to improve detection accuracy and real-time performance across diverse weather conditions; a closed-loop evaluation environment is established using the CARLA simulator and ADORE framework, with low-latency coordination among perception, decision, and control enabled via ROS bridging; and a dynamic rule engine is incorporated to handle anomalous scenarios. Experimental results demonstrate that the proposed approach achieves a 12.3% average improvement in mean Average Precision (mAP) under rain, fog, and snow conditions, while maintaining decision response latency below 85 ms—significantly enhancing system safety and environmental adaptability.

Technology Category

• Computer Vision: Vision for Robotics & Autonomous Driving
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Reasoning under Uncertainty: Sequential Decision Making

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Ensuring safety in autonomous driving requires a seamless integration of perception and decision making under uncertain conditions. Although computer vision (CV) models such as YOLO achieve high accuracy in detecting traffic signs and obstacles, their performance degrades in drift scenarios caused by weather variations or unseen objects. This work presents a simulated autonomous driving system that combines a context aware CV model with adaptive control using the ADORE framework. The CARLA simulator was integrated with ADORE via the ROS bridge, allowing real-time communication between perception, decision, and control modules. A simulated test case was designed in both clear and drift weather conditions to demonstrate the robust detection performance of the perception model while ADORE successfully adapted vehicle behavior to speed limits and obstacles with low response latency. The findings highlight the potential of coupling deep learning-based perception with rule-based adaptive decision making to improve automotive safety critical system.

Problem

• Integrating computer vision with adaptive control for autonomous driving
• Addressing performance degradation in drift scenarios and weather variations
• Ensuring safety through robust perception and decision-making under uncertainty

Innovation

• Combines context-aware computer vision with adaptive control
• Integrates CARLA simulator with ADORE via ROS bridge
• Couples deep learning perception with rule-based decision making