Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Rethinking Social Robot Navigation: Leveraging the Best of Two Worlds

Amir Hossain Raj, Zichao Hu, Haresh Karnan, Rohan Chandra, Amirreza Payandeh, Luisa Mao, Peter Stone, Joydeep Biswas, Xuesu Xiao

TL;DR

This work finds that using a large-scale real-world social navigation dataset, SCAND, it is found that geometric systems can produce trajectory plans that align with the human demonstrations in a large number of social situations.

Abstract

Empowering robots to navigate in a socially compliant manner is essential for the acceptance of robots moving in human-inhabited environments. Previously, roboticists have developed geometric navigation systems with decades of empirical validation to achieve safety and efficiency. However, the many complex factors of social compliance make geometric navigation systems hard to adapt to social situations, where no amount of tuning enables them to be both safe (people are too unpredictable) and efficient (the frozen robot problem). With recent advances in deep learning approaches, the common reaction has been to entirely discard these classical navigation systems and start from scratch, building a completely new learning-based social navigation planner. In this work, we find that this reaction is unnecessarily extreme: using a large-scale real-world social navigation dataset, SCAND, we find that geometric systems can produce trajectory plans that align with the human demonstrations in a large number of social situations. We, therefore, ask if we can rethink the social robot navigation problem by leveraging the advantages of both geometric and learning-based methods. We validate this hybrid paradigm through a proof-of-concept experiment, in which we develop a hybrid planner that switches between geometric and learning-based planning. Our experiments on both SCAND and two physical robots show that the hybrid planner can achieve better social compliance compared to using either the geometric or learning-based approach alone.

Rethinking Social Robot Navigation: Leveraging the Best of Two Worlds

TL;DR

This work finds that using a large-scale real-world social navigation dataset, SCAND, it is found that geometric systems can produce trajectory plans that align with the human demonstrations in a large number of social situations.

Abstract

Empowering robots to navigate in a socially compliant manner is essential for the acceptance of robots moving in human-inhabited environments. Previously, roboticists have developed geometric navigation systems with decades of empirical validation to achieve safety and efficiency. However, the many complex factors of social compliance make geometric navigation systems hard to adapt to social situations, where no amount of tuning enables them to be both safe (people are too unpredictable) and efficient (the frozen robot problem). With recent advances in deep learning approaches, the common reaction has been to entirely discard these classical navigation systems and start from scratch, building a completely new learning-based social navigation planner. In this work, we find that this reaction is unnecessarily extreme: using a large-scale real-world social navigation dataset, SCAND, we find that geometric systems can produce trajectory plans that align with the human demonstrations in a large number of social situations. We, therefore, ask if we can rethink the social robot navigation problem by leveraging the advantages of both geometric and learning-based methods. We validate this hybrid paradigm through a proof-of-concept experiment, in which we develop a hybrid planner that switches between geometric and learning-based planning. Our experiments on both SCAND and two physical robots show that the hybrid planner can achieve better social compliance compared to using either the geometric or learning-based approach alone.
Paper Structure (21 sections, 6 equations, 5 figures, 1 table)

This paper contains 21 sections, 6 equations, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Background
  3. Classical Geometric Navigation
  4. Learning-Based Navigation
  5. scand
  6. Social Compliance Case Study
  7. Defining Social Compliance on scand
  8. Geometric Navigation Systems
  9. move_base movebase
  10. move_base with social layer (move_base(s)) social_layer
  11. Human-Aware Planner kollmitz15ecmr
  12. CoHAN singamaneni2021human
  13. Comparing Geometric and Learning-Based Planner
  14. Rethinking Social Robot Navigation
  15. Physical Experiments
  16. ...and 6 more sections

Figures (5)

  • Figure 0: Different Hausdorff distances between the human demonstration trajectory (green) and geometric planner trajectory (red). White dots denote nearby humans and obstacles. Empirically, navigation systems that align better with human demonstrations are expected to yield a lower Hausdorff distance.
  • Figure 1: Cumulative Distribution Function (CDF) curves illustrating the Hausdorff distance and social scenario percentages for four distinct geometric planners, analyzed on the scand.
  • Figure 2: CDF curves of Geometric, Learning-Based, and Proposed Hybrid Navigation Planners on In-Distribution scand and Out-of-Distribution Test Data.
  • Figure 3: Human Study Average Scores Per Question.
  • Figure 4: GMU Jackal Frontal Approach (Left) and UT Spot Narrow Doorway (Right) Robot Experiments.

Theorems & Definitions (1)

  • Definition 1