Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Are We Ready for Planetary Exploration Robots? The TAIL-Plus Dataset for SLAM in Granular Environments

Zirui Wang, Chen Yao, Yangtao Ge, Guowei Shi, Ningbo Yang, Zheng Zhu, Kewei Dong, Hexiang Wei, Zhenzhong Jia, Jing Wu

TL;DR

The paper addresses the challenge of autonomous navigation and robust SLAM for planetary exploration robots operating in deformable granular terrains. It introduces TAIL-Plus, an extended, multi-sensor dataset built on the authors' previous TAIL work, featuring day/night beach experiments with both wheeled and quadruped platforms and a modular sensor suite designed for time-synchronized data collection. The work provides a detailed calibration pipeline and ground-truth generation via IMU-integrated RTK-GPS, along with ten diverse sequences that enable evaluation of LiDAR-inertial, visual-inertial, and LiDAR-visual-inertial SLAM under challenging terrain and illumination conditions. The dataset aims to accelerate development and benchmarking of robust localization and mapping methods for planetary surface missions, with practical impact on autonomy and safety in unstructured environments.

Abstract

So far, planetary surface exploration depends on various mobile robot platforms. The autonomous navigation and decision-making of these mobile robots in complex terrains largely rely on their terrain-aware perception, localization and mapping capabilities. In this paper we release the TAIL-Plus dataset, a new challenging dataset in deformable granular environments for planetary exploration robots, which is an extension to our previous work, TAIL (Terrain-Aware multI-modaL) dataset. We conducted field experiments on beaches that are considered as planetary surface analog environments for diverse sandy terrains. In TAIL-Plus dataset, we provide more sequences with multiple loops and expand the scene from day to night. Benefit from our sensor suite with modular design, we use both wheeled and quadruped robots for data collection. The sensors include a 3D LiDAR, three downward RGB-D cameras, a pair of global-shutter color cameras that can be used as a forward-looking stereo camera, an RTK-GPS device and an extra IMU. Our datasets are intended to help researchers developing multi-sensor simultaneous localization and mapping (SLAM) algorithms for robots in unstructured, deformable granular terrains. Our datasets and supplementary materials will be available at \url{https://tailrobot.github.io/}.

Are We Ready for Planetary Exploration Robots? The TAIL-Plus Dataset for SLAM in Granular Environments

TL;DR

The paper addresses the challenge of autonomous navigation and robust SLAM for planetary exploration robots operating in deformable granular terrains. It introduces TAIL-Plus, an extended, multi-sensor dataset built on the authors' previous TAIL work, featuring day/night beach experiments with both wheeled and quadruped platforms and a modular sensor suite designed for time-synchronized data collection. The work provides a detailed calibration pipeline and ground-truth generation via IMU-integrated RTK-GPS, along with ten diverse sequences that enable evaluation of LiDAR-inertial, visual-inertial, and LiDAR-visual-inertial SLAM under challenging terrain and illumination conditions. The dataset aims to accelerate development and benchmarking of robust localization and mapping methods for planetary surface missions, with practical impact on autonomy and safety in unstructured environments.

Abstract

So far, planetary surface exploration depends on various mobile robot platforms. The autonomous navigation and decision-making of these mobile robots in complex terrains largely rely on their terrain-aware perception, localization and mapping capabilities. In this paper we release the TAIL-Plus dataset, a new challenging dataset in deformable granular environments for planetary exploration robots, which is an extension to our previous work, TAIL (Terrain-Aware multI-modaL) dataset. We conducted field experiments on beaches that are considered as planetary surface analog environments for diverse sandy terrains. In TAIL-Plus dataset, we provide more sequences with multiple loops and expand the scene from day to night. Benefit from our sensor suite with modular design, we use both wheeled and quadruped robots for data collection. The sensors include a 3D LiDAR, three downward RGB-D cameras, a pair of global-shutter color cameras that can be used as a forward-looking stereo camera, an RTK-GPS device and an extra IMU. Our datasets are intended to help researchers developing multi-sensor simultaneous localization and mapping (SLAM) algorithms for robots in unstructured, deformable granular terrains. Our datasets and supplementary materials will be available at \url{https://tailrobot.github.io/}.
Paper Structure (4 sections, 4 figures, 1 table)

This paper contains 4 sections, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. System overview
  3. Data collection
  4. Conclusion

Figures (4)

  • Figure 1: The sensor suite and the quadruped robot platform. This sensor suite is also installed on wheeled robot, which is shown in Figure \ref{['fig:intro_picture']}(a).
  • Figure 2: The calibration chain. Black lines: the extrinsic parameters are obtained by different calibration methods. Green lines: the extrinsic parameters are provided by factory calibrations or measured from the CAD model.
  • Figure 3: The extrinsic calibration between Ouster OS0-128 and Azure Kinect DK color camera. Left: projected checkerboard pointclouds on the color image. Right: the colored pointclouds.
  • Figure 4: Overview of the field experiment locations and trajectories of part of our TAIL-Plus sequences. The experiment locations are at the Double-Moon Bay, Guangdong Province. Its west coast is called wanke and the east coast is called shanhaili.