Vision-LiDAR-Tactile Fusion Framework Optimized by Artificial Hummingbird Algorithm for Contact-Aware Embodied 3D Scene Perception

Embodied intelligent robots demand comprehensive 3D scene understanding via multimodal sensor fusion for complex manipulation tasks, yet existing methods struggle with insufficient heterogeneous data complementarity and inflexible fusion weight optimization. This paper presents Artificial Hummingbird Algorithm (AHA)-Fusion, a vision-LiDAR-tactile fusion framework optimized by the AHA for contact-aware embodied 3D scene perception. It integrates a multimodal feature extraction pipeline using ResNet-50, PointNet++, and lightweight CNNs, an improved Adaptive Artificial Hummingbird Algorithm (I-AHA) with chaotic traversal and elite learning to optimize fusion weights globally, and a contact-aware dynamic weight modulation mechanism for real-time weight adjustment based on tactile contact states. A multi-level temporal synchronization strategy achieves 3.2±1.1 ms alignment accuracy. Experiments on nuScenes and EmbodiedScan datasets show AHA-Fusion attains 70.2% mAP and 73.8% NDS for 3D object detection, and 67.4% mIoU for semantic segmentation, outperforming state-of-the-art methods. Ablation studies confirm I-AHA surpasses learnable attention weights by 2.3 percentage points with enhanced stability, while the contact-aware mechanism boosts contact region detection by 5.2 percentage points. Robustness tests verify the framework’s resilience to partial sensor failures, providing an effective solution for multimodal collaborative perception in embodied intelligence.