Socially-aware Object Transportation by a Mobile Manipulator in Static Planar Environments with Obstacles

TL;DR

This paper introduces a novel socially-aware navigation method for mobile manipulators that coordinates base and arm movements to safely transport objects in human environments, outperforming mobile-only approaches.

Contribution

The paper presents a Risk-RRT* based approach for coordinated manipulation and navigation, addressing the gap in socially-aware navigation for mobile manipulators.

Findings

Outperforms mobile-only socially-aware navigation methods in simulations.

Enables collision-free, socially-comfortable object transportation.

Highlights the need for manipulator-specific navigation techniques.

Abstract

Socially-aware robotic navigation is essential in environments where humans and robots coexist, ensuring both safety and comfort. However, most existing approaches have been primarily developed for mobile robots, leaving a significant gap in research that addresses the unique challenges posed by mobile manipulators. In this paper, we tackle the challenge of navigating a robotic mobile manipulator, carrying a non-negligible load, within a static human-populated environment while adhering to social norms. Our goal is to develop a method that enables the robot to simultaneously manipulate an object and navigate between locations in a socially-aware manner. We propose an approach based on the Risk-RRT* framework that enables the coordinated actuation of both the mobile base and manipulator. This approach ensures collision-free navigation while adhering to human social preferences. We compared our approach in a simulated environment to socially-aware mobile-only methods applied to a mobile manipulator. The results highlight the necessity for mobile manipulator-specific techniques, with our method outperforming mobile-only approaches. Our method enabled the robot to navigate, transport an object, avoid collisions, and minimize social discomfort effectively.