Towards Robust Perception for Assistive Robotics: An RGB-Event-LiDAR Dataset and Multi-Modal Detection Pipeline

TL;DR

This paper introduces a multi-modal dataset combining RGB, event, LiDAR, and IMU data for assistive robotics, highlighting challenges in 3D localization and evaluating detection models to advance robust perception for visually impaired assistance.

Contribution

The paper provides a new publicly available dataset for multi-modal perception in assistive robotics, facilitating research on robust detection and localization.

Findings

Current event-based detection models have limited performance in dynamic scenarios.

Fusion of 2D images and LiDAR data presents challenges in accurate 3D localization.

The dataset supports development of safer, more reliable assistive robotic systems.

Abstract

The increasing adoption of human-robot interaction presents opportunities for technology to positively impact lives, particularly those with visual impairments, through applications such as guide-dog-like assistive robotics. We present a pipeline exploring the perception and "intelligent disobedience" required by such a system. A dataset of two people moving in and out of view has been prepared to compare RGB-based and event-based multi-modal dynamic object detection using LiDAR data for 3D position localisation. Our analysis highlights challenges in accurate 3D localisation using 2D image-LiDAR fusion, indicating the need for further refinement. Compared to the performance of the frame-based detection algorithm utilised (YOLOv4), current cutting-edge event-based detection models appear limited to contextual scenarios, such as for automotive platforms. This is highlighted by weak precision and recall over varying confidence and Intersection over Union (IoU) thresholds when using frame-based detections as a ground truth. Therefore, we have publicly released this dataset to the community, containing RGB, event, point cloud and Inertial Measurement Unit (IMU) data along with ground truth poses for the two people in the scene to fill a gap in the current landscape of publicly available datasets and provide a means to assist in the development of safer and more robust algorithms in the future: https://uts-ri.github.io/revel/.