A Benchmark Synthetic Dataset for C-SLAM in Service Environments

Harin Park, Inha Lee, Minje Kim, Hyungyu Park, Kyungdon Joo

Keywords: Robot learning: Datasets and Benchmarks, Assistive, Entertainment and Service Robots, Human-Robot Interaction

TL;DR: We propose the first benchmark synthetic C-SLAM dataset in service environments.

Abstract: In this work, we introduce a new multi-modal C-SLAM dataset for multiple service robots in various indoor service environments, called C-SLAM dataset in Service Environments (CSE). We use the NVIDIA Isaac Sim to build data in various indoor service environments with the challenges that may occur in real-world service environments. By using simulation, we can provide accurate and precisely time-synchronized sensor data, such as stereo RGB, stereo depth, IMU, and GT poses. We configure three common indoor service environments (Hospital, Office, and Warehouse), each of which includes multiple dynamic objects that perform motions suitable to each environment. In addition, we navigate the robots to mimic the actions of real service robots. Through these factors, we generate a more realistic C-SLAM dataset for multiple service robots. We demonstrate our dataset by evaluating diverse state-of-the-art multi-robot SLAM methods.

Submission Number: 12