Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Experimental Evaluation of ROS-Causal in Real-World Human-Robot Spatial Interaction Scenarios

Luca Castri, Gloria Beraldo, Sariah Mghames, Marc Hanheide, Nicola Bellotto

TL;DR

This paper addresses the challenge of integrating causal discovery into the ROS robotics stack to model cause-effect relations between robot actions and human responses in shared spaces. It introduces ROS-Causal, a framework that performs onboard data collection and causal discovery on time-series HRI data, using PCMCI and F-PCMCI, and validates it through simulated and real-world experiments with a TIAGo robot and a Velodyne LiDAR, including a time horizon of $120\,s$ at $10\,\text{Hz}$. The main contributions are the first onboard HRSI causal model generation, a lab study with 15 participants, and a public HRSI trajectory dataset; results show consistent causal models between simulation and lab deployments. The work advances practical, real-time reasoning for robots in shared human environments and lays groundwork for extending ROS-Causal to planning and real-time interaction prediction.

Abstract

Deploying robots in human-shared environments requires a deep understanding of how nearby agents and objects interact. Employing causal inference to model cause-and-effect relationships facilitates the prediction of human behaviours and enables the anticipation of robot interventions. However, a significant challenge arises due to the absence of implementation of existing causal discovery methods within the ROS ecosystem, the standard de-facto framework in robotics, hindering effective utilisation on real robots. To bridge this gap, in our previous work we proposed ROS-Causal, a ROS-based framework designed for onboard data collection and causal discovery in human-robot spatial interactions. In this work, we present an experimental evaluation of ROS-Causal both in simulation and on a new dataset of human-robot spatial interactions in a lab scenario, to assess its performance and effectiveness. Our analysis demonstrates the efficacy of this approach, showcasing how causal models can be extracted directly onboard by robots during data collection. The online causal models generated from the simulation are consistent with those from lab experiments. These findings can help researchers to enhance the performance of robotic systems in shared environments, firstly by studying the causal relations between variables in simulation without real people, and then facilitating the actual robot deployment in real human environments. ROS-Causal: https://lcastri.github.io/roscausal

Experimental Evaluation of ROS-Causal in Real-World Human-Robot Spatial Interaction Scenarios

TL;DR

This paper addresses the challenge of integrating causal discovery into the ROS robotics stack to model cause-effect relations between robot actions and human responses in shared spaces. It introduces ROS-Causal, a framework that performs onboard data collection and causal discovery on time-series HRI data, using PCMCI and F-PCMCI, and validates it through simulated and real-world experiments with a TIAGo robot and a Velodyne LiDAR, including a time horizon of at . The main contributions are the first onboard HRSI causal model generation, a lab study with 15 participants, and a public HRSI trajectory dataset; results show consistent causal models between simulation and lab deployments. The work advances practical, real-time reasoning for robots in shared human environments and lays groundwork for extending ROS-Causal to planning and real-time interaction prediction.

Abstract

Deploying robots in human-shared environments requires a deep understanding of how nearby agents and objects interact. Employing causal inference to model cause-and-effect relationships facilitates the prediction of human behaviours and enables the anticipation of robot interventions. However, a significant challenge arises due to the absence of implementation of existing causal discovery methods within the ROS ecosystem, the standard de-facto framework in robotics, hindering effective utilisation on real robots. To bridge this gap, in our previous work we proposed ROS-Causal, a ROS-based framework designed for onboard data collection and causal discovery in human-robot spatial interactions. In this work, we present an experimental evaluation of ROS-Causal both in simulation and on a new dataset of human-robot spatial interactions in a lab scenario, to assess its performance and effectiveness. Our analysis demonstrates the efficacy of this approach, showcasing how causal models can be extracted directly onboard by robots during data collection. The online causal models generated from the simulation are consistent with those from lab experiments. These findings can help researchers to enhance the performance of robotic systems in shared environments, firstly by studying the causal relations between variables in simulation without real people, and then facilitating the actual robot deployment in real human environments. ROS-Causal: https://lcastri.github.io/roscausal
Paper Structure (10 sections, 6 figures)

This paper contains 10 sections, 6 figures.

Table of Contents

  1. INTRODUCTION
  2. RELATED WORK
  3. ROS-CAUSAL FOR HUMAN-ROBOT SPATIAL INTERACTION MODELLING
  4. ROS-Causal
  5. Human-Robot Spatial Interaction Scenario
  6. EXPERIMENTS
  7. ROS-Causal Simulation Evaluation
  8. Dataset and Experimental Setup
  9. ROS-Causal Evaluation in Lab Scenario
  10. CONCLUSION

Figures (6)

  • Figure 1: A high-level overview of the core components of ROS-Causal.
  • Figure 2: ROS-Causal pipeline castri2024ros: (i) data extraction from HRI scenarios; (ii) collection and post-processing of data to derive a high-level representation of the scenario; (iii) causal discovery conducted on the extracted data, with the resulting causal model published on a dedicated rostopic.
  • Figure 3: (a) HRSI experiment in a lab scenario with a TIAGo robot, a person and his/her four goal positions;(b) 2D map of an experiment with a person and TIAGo, with trajectories in orange and blue respectively, and four goal positions (green dot); (c) RViz visualisation of the scenario; (d) TIAGo robot with (1) a Velodyne VLP-16 3D LiDAR used for dataset collection.
  • Figure 4: Heat map of the all participants (left colormap) and robot (right colormap) trajectories during the experiments. The color palette varies based on the hit rate per cell.
  • Figure 5: HRI scenario involving a TIAGo robot and a teleoperated person, created by ROS-Causal_HRISim.
  • ...and 1 more figures