A5006036325- Advanced Image and Video Retrieval Techniques
- Robotics and Sensor-Based Localization
- 3D Surveying and Cultural Heritage
- Memory and Neural Mechanisms
- Robotic Path Planning Algorithms
Anhui Polytechnic University
2021
A Biomimetic SLAM Algorithm Based on Growing Self-Organizing Map (GSOM-BSLAM), inspired by spatial cognitive mechanism of mammalian hippocampus, is proposed to resolve uncertainty problems in location identification and lack real-time performance simultaneous localization mapping. The algorithm connects activation characteristics the place cell neurons output layer neural network construct a topological map space using self-organizing growable mapping network. It utilizes self-motion-aware...
Aiming at the problem that visual SLAM algorithm is easily disturbed by complex environmental factors, resulting in poor closed-loop accuracy and real-time performance. An improved detection based on a dynamic increase or decrease mechanism proposed. The can dynamically number of words bag real time according to complexity scene; optimize selected keyframes through double-threshold keyframe selection strategy reduce redundancy keyframes, thus improving system's this paper achieve...
A biologically heuristic map construction and autonomous localization algorithm is proposed inspired by the cognitive mechanism of hippocampal structures to address problems limited accuracy environmental noise interference in simultaneous mapping mobile robots unknown environments. The self-motion information robot external visual landmark were used as inputs build location-aware model from grid cell place model, respectively. extracted combined with location obtained through Hebbian...