Learning

Proposed Verti-Selector, a novel ACL framework that samples training terrain based on estimates of future learning potential (TD-error). Significantly enhanced navigation performance by 23.08% improvement in terms of success rate compared against a manually designed curriculum, vanilla Reinforcement Learning, and two baseline approaches

Reproduced Faster R-CNN model by integrating Region Proposal Network module with Fast R-CNN. Improved the performance of Faster R-CNN model by 37.4% in terms of recall rate compared with YOLOv3 model on cone annotated dataset

A Scalable Human-Like Guidance System for Travelers with Visual Impairment.