METRIC-SEMANTIC MAPPING BASED ON DEEP NEURAL NETWORKS FOR SYSTEMS OF INDOOR AUTONOMOUS NAVIGATION
Annotation
Results of a study aimed at developing an intelligent autonomous navigation system for warehouse and office logistics using deep neural networks, are presented. The modern and most versatile tools for depth maps retrieval and semantic data segmentation on images in different environments are analyzed. A comparison of depth maps retrieved hardware from RGB-D camera, neural network algorithms, and a modified Hirschmuller algorithm is carried out. Results of testing performed with a specially prepared dataset shot in an office space, including many complex objects such as glass, mirrors, and multiple light sources demonstrate that the proposed solution outperforms the alternatives in accuracy and uses fewer computational resources in the process.
Keywords
Постоянный URL
Articles in current issue
- STRUCTURAL-PARAMETRIC SYNTHESIS OF PLANAR UNDERACTUATED LINKAGES FOR ANTHROPOMORPHIC ROBOTIC HANDS
- HARDWARE AND SOFTWARE ARCHITECTURE FOR ANTHROPOMORPHIC ROBOT HAND CONTROL SYSTEM
- DESIGN OF AN UNDERACTUATED JUMPING ROBOT WITH FLEXIBLE JOINTS
- MODIFIED INTELLIGENT BIDIRECTIONAL RANDOM TREE ALGORITHM FOR PLANNING THE MOVEMENT OF ANTHROPOMORPHIC MANIPULATORS
- OBJECTS SEGMENTATION WITH RETRAINING FUNCTION
- METRIC-SEMANTIC MAPPING BASED ON DEEP NEURAL NETWORKS FOR SYSTEMS OF INDOOR AUTONOMOUS NAVIGATION
- OPTIMIZATION ALGORITHMS FOR IMPROVING THE ACCURACY AND ROBUSTNESS OF VISUAL ODOMETRY OF GROUND-BASED MOBILE ROBOTS