Sixth-Sense: Self-Supervised Learning of Spatial Awareness of Humans from a Planar Lidar

TL;DR

This paper introduces a self-supervised method enabling robots with 1D LiDARs to detect and estimate human positions and orientations omnidirectionally, enhancing safety and interaction in shared spaces.

Contribution

It presents a novel self-supervised learning approach that uses RGB-D camera detections to train 1D LiDAR-based human detection and pose estimation models without manual labeling.

Findings

Achieved 71% precision and 80% recall in human detection

Estimated distance with 13cm mean absolute error

Estimated orientation with 44° mean absolute error

Abstract

Reliable localization of people is fundamental for service and social robots that must operate in close interaction with humans. State-of-the-art human detectors often rely on RGB-D cameras or costly 3D LiDARs. However, most commercial robots are equipped with cameras with a narrow field of view, leaving them unaware of users approaching from other directions, or inexpensive 1D LiDARs whose readings are hard to interpret. To address these limitations, we propose a self-supervised approach to detect humans and estimate their 2D pose from 1D LiDAR data, using detections from an RGB-D camera as supervision. Trained on 70 minutes of autonomously collected data, our model detects humans omnidirectionally in unseen environments with 71% precision, 80% recall, and mean absolute errors of 13cm in distance and 44{\deg} in orientation, measured against ground truth data. Beyond raw detection accuracy, this capability is relevant for robots operating in shared public spaces, where omnidirectional awareness of nearby people is crucial for safe navigation, appropriate approach behavior, and timely human-robot interaction initiation using low-cost, privacy-preserving sensing. Deployment in two additional public environments further suggests that the approach can serve as a practical wide-FOV awareness layer for socially aware service robotics.