Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Look Before You Leap: Socially Acceptable High-Speed Ground Robot Navigation in Crowded Hallways

Lakshay Sharma, Jonathan P. How

TL;DR

This paper proposes a planner that aims to address the consequent "robot freezing problem" in hallways by allowing for "peek-and-pass" maneuvers and demonstrates in simulation how this planner improves robot time to goal without violating social norms.

Abstract

To operate safely and efficiently, autonomous warehouse/delivery robots must be able to accomplish tasks while navigating in dynamic environments and handling the large uncertainties associated with the motions/behaviors of other robots and/or humans. A key scenario in such environments is the hallway problem, where robots must operate in the same narrow corridor as human traffic going in one or both directions. Traditionally, robot planners have tended to focus on socially acceptable behavior in the hallway scenario at the expense of performance. This paper proposes a planner that aims to address the consequent "robot freezing problem" in hallways by allowing for "peek-and-pass" maneuvers. We then go on to demonstrate in simulation how this planner improves robot time to goal without violating social norms. Finally, we show initial hardware demonstrations of this planner in the real world.

Look Before You Leap: Socially Acceptable High-Speed Ground Robot Navigation in Crowded Hallways

TL;DR

This paper proposes a planner that aims to address the consequent "robot freezing problem" in hallways by allowing for "peek-and-pass" maneuvers and demonstrates in simulation how this planner improves robot time to goal without violating social norms.

Abstract

To operate safely and efficiently, autonomous warehouse/delivery robots must be able to accomplish tasks while navigating in dynamic environments and handling the large uncertainties associated with the motions/behaviors of other robots and/or humans. A key scenario in such environments is the hallway problem, where robots must operate in the same narrow corridor as human traffic going in one or both directions. Traditionally, robot planners have tended to focus on socially acceptable behavior in the hallway scenario at the expense of performance. This paper proposes a planner that aims to address the consequent "robot freezing problem" in hallways by allowing for "peek-and-pass" maneuvers. We then go on to demonstrate in simulation how this planner improves robot time to goal without violating social norms. Finally, we show initial hardware demonstrations of this planner in the real world.
Paper Structure (14 sections, 3 equations, 7 figures)

This paper contains 14 sections, 3 equations, 7 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Pipeline Overview
  4. Mapping
  5. Prediction
  6. Planning
  7. Planner
  8. Problem Formulation
  9. Cost Function
  10. Results
  11. Preliminary Laned Simulation Results
  12. Unlaned Photorealistic Simulation Results
  13. Hardware Demonstration
  14. Conclusions and Future Work

Figures (7)

  • Figure 1: Overview of the proposed planning pipeline.
  • Figure 2: Hallway passing scenario for a fast ground robot stuck behind a slow human.
  • Figure 3: A laned simulation environment where a robot (green) navigates safely around several humans (blue) which are all moving left to right at varying speeds.
  • Figure 4: The laned simulation environment demonstrates that in a structured scenario, the proposed idea of "peek-and-go" successfully increases performance by actively sensing and clearing unknown space.
  • Figure 5: Unlaned
  • ...and 2 more figures