Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Human-Robot Collaboration for the Remote Control of Mobile Humanoid Robots with Torso-Arm Coordination

Nikita Boguslavskii, Lorena Maria Genua, Zhi Li

TL;DR

The paper tackles the challenge of coordinating a moving torso and robotic arm in mobile humanoid robots under remote teleoperation. It presents a spectrum of human-initiated and robot-initiated HRC approaches, including Preset Heights, Velocity, Proximity, Scaling, Chasing, Task-Based proactive autonomy, and RelaxedIK as a baseline. Through a 17-participant user study, it reveals that robot-initiated modes like Chasing and Scaling, along with Task-Based automation, improve long-range task performance and are favored by users, while RelaxedIK underperforms in timing and user alignment yet offers strong manipulability. The findings offer practical guidance on selecting torso-arm coordination strategies based on task range, energy considerations, and operator experience, with future work aimed at enhancing intent estimation and predictive torso control.

Abstract

Recently, many humanoid robots have been increasingly deployed in various facilities, including hospitals and assisted living environments, where they are often remotely controlled by human operators. Their kinematic redundancy enhances reachability and manipulability, enabling them to navigate complex, cluttered environments and perform a wide range of tasks. However, this redundancy also presents significant control challenges, particularly in coordinating the movements of the robot's macro-micro structure (torso and arms). Therefore, we propose various human-robot collaborative (HRC) methods for coordinating the torso and arm of remotely controlled mobile humanoid robots, aiming to balance autonomy and human input to enhance system efficiency and task execution. The proposed methods include human-initiated approaches, where users manually control torso movements, and robot-initiated approaches, which autonomously coordinate torso and arm based on factors such as reachability, task goal, or inferred human intent. We conducted a user study with N=17 participants to compare the proposed approaches in terms of task performance, manipulability, and energy efficiency, and analyzed which methods were preferred by participants.

Human-Robot Collaboration for the Remote Control of Mobile Humanoid Robots with Torso-Arm Coordination

TL;DR

The paper tackles the challenge of coordinating a moving torso and robotic arm in mobile humanoid robots under remote teleoperation. It presents a spectrum of human-initiated and robot-initiated HRC approaches, including Preset Heights, Velocity, Proximity, Scaling, Chasing, Task-Based proactive autonomy, and RelaxedIK as a baseline. Through a 17-participant user study, it reveals that robot-initiated modes like Chasing and Scaling, along with Task-Based automation, improve long-range task performance and are favored by users, while RelaxedIK underperforms in timing and user alignment yet offers strong manipulability. The findings offer practical guidance on selecting torso-arm coordination strategies based on task range, energy considerations, and operator experience, with future work aimed at enhancing intent estimation and predictive torso control.

Abstract

Recently, many humanoid robots have been increasingly deployed in various facilities, including hospitals and assisted living environments, where they are often remotely controlled by human operators. Their kinematic redundancy enhances reachability and manipulability, enabling them to navigate complex, cluttered environments and perform a wide range of tasks. However, this redundancy also presents significant control challenges, particularly in coordinating the movements of the robot's macro-micro structure (torso and arms). Therefore, we propose various human-robot collaborative (HRC) methods for coordinating the torso and arm of remotely controlled mobile humanoid robots, aiming to balance autonomy and human input to enhance system efficiency and task execution. The proposed methods include human-initiated approaches, where users manually control torso movements, and robot-initiated approaches, which autonomously coordinate torso and arm based on factors such as reachability, task goal, or inferred human intent. We conducted a user study with N=17 participants to compare the proposed approaches in terms of task performance, manipulability, and energy efficiency, and analyzed which methods were preferred by participants.
Paper Structure (21 sections, 2 figures, 6 algorithms)

This paper contains 21 sections, 2 figures, 6 algorithms.

Table of Contents

  1. Introduction
  2. Related Work
  3. Proposed HRC Torso-Arm Coordination
  4. Human-Initiated Approaches
  5. Robot-Initiated Approaches
  6. User Study Evaluation
  7. Experiment setup
  8. Task Design
  9. Experiment Procedure
  10. Participants
  11. Evaluation Metrics and Measurements
  12. Results
  13. Overall Task Completion Time
  14. Short-range Completion Time
  15. Long-range Completion Time
  16. ...and 6 more sections

Figures (2)

  • Figure 1: The experimental setup consists of two workspaces. The robotic workspace features a shelf unit with four shelves. IONA robot featuring a motorized torso and a 7-degree-of-freedom robotic arm is located next to the shelf. A workspace camera captures the torso, arm and provides a complete view of the manipulation area. The operator workspace includes a screen displaying a graphical user interface (GUI), which streams video from the workspace camera with augmented reality (AR) cues overlaid. The operator uses a MetaQuest 2 handheld controller to control the robot. An additional operator camera is placed above the screen to capture the participant's posture, with key body landmarks tracked for physical workload estimation.
  • Figure 2: Results for completion time for long-range motion, manipulability index and torso motion time (metric of torso energy consumption).