Multisensor Online Transfer Learning for 3D LiDAR-based Human Detection with a Mobile Robot

TL;DR

This paper presents a multisensor online transfer learning framework enabling a mobile robot to improve 3D LiDAR-based human detection by leveraging data from multiple sensors and detectors in real-time.

Contribution

It introduces a novel semi-supervised learning approach that uses trajectory probability to train a 3D LiDAR human classifier from various sensors over time.

Findings

The system effectively learns from multiple sensors.

Performance of 3D LiDAR human classification improves with more sensors.

The framework is validated on real-world robot-collected data.

Abstract

Human detection and tracking is an essential task for service robots, where the combined use of multiple sensors has potential advantages that are yet to be exploited. In this paper, we introduce a framework allowing a robot to learn a new 3D LiDAR-based human classifier from other sensors over time, taking advantage of a multisensor tracking system. The main innovation is the use of different detectors for existing sensors (i.e. RGB-D camera, 2D LiDAR) to train, online, a new 3D LiDAR-based human classifier, exploiting a so-called trajectory probability. Our framework uses this probability to check whether new detections belongs to a human trajectory, estimated by different sensors and/or detectors, and to learn a human classifier in a semi-supervised fashion. The framework has been implemented and tested on a real-world dataset collected by a mobile robot. We present experiments illustrating that our system is able to effectively learn from different sensors and from the environment, and that the performance of the 3D LiDAR-based human classification improves with the number of sensors/detectors used.