SocRATES: Towards Automated Scenario-based Testing of Social Navigation Algorithms

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Marpally, Shashank Rao, Goyal, Pranav, Soh, Harold
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912170463199232
author Marpally, Shashank Rao
Goyal, Pranav
Soh, Harold
author_facet Marpally, Shashank Rao
Goyal, Pranav
Soh, Harold
contents Current social navigation methods and benchmarks primarily focus on proxemics and task efficiency. While these factors are important, qualitative aspects such as perceptions of a robot's social competence are equally crucial for successful adoption and integration into human environments. We propose a more comprehensive evaluation of social navigation through scenario-based testing, where specific human-robot interaction scenarios can reveal key robot behaviors. However, creating such scenarios is often labor-intensive and complex. In this work, we address this challenge by introducing a pipeline that automates the generation of context-, and location-appropriate social navigation scenarios, ready for simulation. Our pipeline transforms simple scenario metadata into detailed textual scenarios, infers pedestrian and robot trajectories, and simulates pedestrian behaviors, which enables more controlled evaluation. We leverage the social reasoning and code-generation capabilities of Large Language Models (LLMs) to streamline scenario generation and translation. Our experiments show that our pipeline produces realistic scenarios and significantly improves scenario translation over naive LLM prompting. Additionally, we present initial feedback from a usability study with social navigation experts and a case-study demonstrating a scenario-based evaluation of three navigation algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19595
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle SocRATES: Towards Automated Scenario-based Testing of Social Navigation Algorithms
Marpally, Shashank Rao
Goyal, Pranav
Soh, Harold
Robotics
Artificial Intelligence
Current social navigation methods and benchmarks primarily focus on proxemics and task efficiency. While these factors are important, qualitative aspects such as perceptions of a robot's social competence are equally crucial for successful adoption and integration into human environments. We propose a more comprehensive evaluation of social navigation through scenario-based testing, where specific human-robot interaction scenarios can reveal key robot behaviors. However, creating such scenarios is often labor-intensive and complex. In this work, we address this challenge by introducing a pipeline that automates the generation of context-, and location-appropriate social navigation scenarios, ready for simulation. Our pipeline transforms simple scenario metadata into detailed textual scenarios, infers pedestrian and robot trajectories, and simulates pedestrian behaviors, which enables more controlled evaluation. We leverage the social reasoning and code-generation capabilities of Large Language Models (LLMs) to streamline scenario generation and translation. Our experiments show that our pipeline produces realistic scenarios and significantly improves scenario translation over naive LLM prompting. Additionally, we present initial feedback from a usability study with social navigation experts and a case-study demonstrating a scenario-based evaluation of three navigation algorithms.
title SocRATES: Towards Automated Scenario-based Testing of Social Navigation Algorithms
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2412.19595