JRDB: A Dataset and Benchmark of Egocentric Robot Visual Perception of Humans in Built Environments

TL;DR

JRDB is a comprehensive egocentric dataset from a social robot, including multimodal sensor data and annotations, designed to advance research in robot perception, navigation, and social interaction in human environments.

Contribution

The paper introduces JRDB, a new multimodal egocentric dataset with extensive annotations, covering diverse indoor and pedestrian scenes for robot perception research.

Findings

Provides over 64 minutes of annotated multimodal data.

Includes 2.3 million bounding boxes and 1.8 million 3D cuboids.

Establishes a benchmark for person detection and tracking.

Abstract

We present JRDB, a novel egocentric dataset collected from our social mobile manipulator JackRabbot. The dataset includes 64 minutes of annotated multimodal sensor data including stereo cylindrical 360$^\circ$ RGB video at 15 fps, 3D point clouds from two Velodyne 16 Lidars, line 3D point clouds from two Sick Lidars, audio signal, RGB-D video at 30 fps, 360$^\circ$ spherical image from a fisheye camera and encoder values from the robot's wheels. Our dataset incorporates data from traditionally underrepresented scenes such as indoor environments and pedestrian areas, all from the ego-perspective of the robot, both stationary and navigating. The dataset has been annotated with over 2.3 million bounding boxes spread over 5 individual cameras and 1.8 million associated 3D cuboids around all people in the scenes totaling over 3500 time consistent trajectories. Together with our dataset and the annotations, we launch a benchmark and metrics for 2D and 3D person detection and tracking. With this dataset, which we plan on extending with further types of annotation in the future, we hope to provide a new source of data and a test-bench for research in the areas of egocentric robot vision, autonomous navigation, and all perceptual tasks around social robotics in human environments.