Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Toward Wheeled Mobility on Vertically Challenging Terrain: Platforms, Datasets, and Algorithms

Aniket Datar, Chenhui Pan, Mohammad Nazeri, Xuesu Xiao

TL;DR

Conventional wheeled robots are limited to flat environments; this paper addresses mobility on vertically challenging terrain. It introduces two open-source platform designs (Verti-Wheelers) and collects two datasets of teleoperated crawls over rocks to enable data-driven mobility. It presents three controllers—open-loop, rule-based, and end-to-end imitation learning—and evaluates them indoors and outdoors, showing that conventional wheels can traverse rugged terrain with appropriate control. The work publishes hardware designs, software, and datasets to spur further research and potential real-world applications in off-road robotics.

Abstract

Most conventional wheeled robots can only move in flat environments and simply divide their planar workspaces into free spaces and obstacles. Deeming obstacles as non-traversable significantly limits wheeled robots' mobility in real-world, extremely rugged, off-road environments, where part of the terrain (e.g., irregular boulders and fallen trees) will be treated as non-traversable obstacles. To improve wheeled mobility in those environments with vertically challenging terrain, we present two wheeled platforms with little hardware modification compared to conventional wheeled robots; we collect datasets of our wheeled robots crawling over previously non-traversable, vertically challenging terrain to facilitate data-driven mobility; we also present algorithms and their experimental results to show that conventional wheeled robots have previously unrealized potential of moving through vertically challenging terrain. We make our platforms, datasets, and algorithms publicly available to facilitate future research on wheeled mobility.

Toward Wheeled Mobility on Vertically Challenging Terrain: Platforms, Datasets, and Algorithms

TL;DR

Conventional wheeled robots are limited to flat environments; this paper addresses mobility on vertically challenging terrain. It introduces two open-source platform designs (Verti-Wheelers) and collects two datasets of teleoperated crawls over rocks to enable data-driven mobility. It presents three controllers—open-loop, rule-based, and end-to-end imitation learning—and evaluates them indoors and outdoors, showing that conventional wheels can traverse rugged terrain with appropriate control. The work publishes hardware designs, software, and datasets to spur further research and potential real-world applications in off-road robotics.

Abstract

Most conventional wheeled robots can only move in flat environments and simply divide their planar workspaces into free spaces and obstacles. Deeming obstacles as non-traversable significantly limits wheeled robots' mobility in real-world, extremely rugged, off-road environments, where part of the terrain (e.g., irregular boulders and fallen trees) will be treated as non-traversable obstacles. To improve wheeled mobility in those environments with vertically challenging terrain, we present two wheeled platforms with little hardware modification compared to conventional wheeled robots; we collect datasets of our wheeled robots crawling over previously non-traversable, vertically challenging terrain to facilitate data-driven mobility; we also present algorithms and their experimental results to show that conventional wheeled robots have previously unrealized potential of moving through vertically challenging terrain. We make our platforms, datasets, and algorithms publicly available to facilitate future research on wheeled mobility.
Paper Structure (19 sections, 2 equations, 7 figures, 1 table)

This paper contains 19 sections, 2 equations, 7 figures, 1 table.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORK
  3. Conventional Wheeled Mobility
  4. Novel Hardware for Vertically Challenging Terrain
  5. Data-Driven Robot Mobility
  6. PLATFORMS AND DATASETS
  7. Verti-6-Wheeler (V6W)
  8. Verti-4-Wheeler (V4W)
  9. Testbed
  10. Datasets
  11. ALGORITHMS
  12. Open-Loop Controller
  13. Classical Rule-Based Controller
  14. End-to-End Learning-Based Controller
  15. EXPERIMENTS
  16. ...and 4 more sections

Figures (7)

  • Figure 1: The Verti-Wheelers: Conventional Wheeled Vehicles Moving through Vertically Challenging Terrain.
  • Figure 2: Components of the Verti-Wheelers.
  • Figure 3: System Architecture of the Verti-Wheelers.
  • Figure 4: Custom-Built Testbed with V6W and V4W and Example Traversals by the Three Algorithms (OL, RB, and BC).
  • Figure 5: Example RGB (Left) and Depth (Right) Images in the Verti-Wheelers Dataset.
  • ...and 2 more figures