Explainable Semantic Mapping for First Responders
This work addresses the problem of enabling first responders to quickly interpret complex environments after disasters, though it appears incremental as it builds on existing deep learning methods for semantic mapping.
The paper tackled the challenge of efficiently analyzing large amounts of data with minimal supervision in semantic mapping for post-disaster environments, resulting in a deep learning-based tool that includes frugal semantic segmentation, few-shot object detection, and explainable cost map learning.
One of the key challenges in the semantic mapping problem in postdisaster environments is how to analyze a large amount of data efficiently with minimal supervision. To address this challenge, we propose a deep learning-based semantic mapping tool consisting of three main ideas. First, we develop a frugal semantic segmentation algorithm that uses only a small amount of labeled data. Next, we investigate on the problem of learning to detect a new class of object using just a few training examples. Finally, we develop an explainable cost map learning algorithm that can be quickly trained to generate traversability cost maps using only raw sensor data such as aerial-view imagery. This paper presents an overview of the proposed idea and the lessons learned.