# Sim-to-Real Learning for Casualty Detection from Ground Projected Point Cloud Data

## TL;DR

This paper presents a deep learning approach for casualty detection from ground-projected point cloud data, using a sim-to-real training strategy with data augmentation to improve real-world performance.

## Contribution

It introduces a novel sim-to-real training method with data augmentation for effective casualty detection using point cloud data in rescue robots.

## Key findings

- Data augmentation significantly improves real-world detection accuracy.
- Synthetic training data can be effectively transferred to real data.
- The proposed method achieves promising detection results in rescue scenarios.

## Abstract

This paper addresses the problem of human body detection---particularly a human body lying on the ground (a.k.a. casualty)---using point cloud data. This ability to detect a casualty is one of the most important features of mobile rescue robots, in order for them to be able to operate autonomously. We propose a deep-learning-based casualty detection method using a deep convolutional neural network (CNN). This network is trained to be able to detect a casualty using a point-cloud data input. In the method we propose, the point cloud input is pre-processed to generate a depth image-like ground-projected heightmap. This heightmap is generated based on the projected distance of each point onto the detected ground plane within the point cloud data. The generated heightmap -- in image form -- is then used as an input for the CNN to detect a human body lying on the ground. To train the neural network, we propose a novel sim-to-real approach, in which the network model is trained using synthetic data obtained in simulation and then tested on real sensor data. To make the model transferable to real data implementations, during the training we adopt specific data augmentation strategies with the synthetic training data. The experimental results show that data augmentation introduced during the training process is essential for improving the performance of the trained model on real data. More specifically, the results demonstrate that the data augmentations on raw point-cloud data have contributed to a considerable improvement of the trained model performance.