Human-Aware Path Planning With Improved Virtual Doppler Method in Highly Dynamic Environments

doi:10.1109/TASE.2022.3175039

Human-Aware Path Planning With Improved Virtual Doppler Method in Highly Dynamic Environments

2023-04-01

8

PRE

AI

DOI：10.1109/TASE.2022.3175039

Original

Original request for help

Save

Abstract

En 中文

Human-aware path planner is essential for achieving harmonious coexistence between humans and robots in highly dynamic environments. In this paper, we propose an integrated framework to find the optimal path in the complex environment with considering collision risk, social norms, and crowded areas. In the proposed framework, a general dynamic group model (g-space) based on the Gaussian Mixed Model (GMM) is proposed as the social norms of dynamic groups, which not only considers the factors of humans (e.g., pose, quantity, distribution, psychology) but also establishes the proximity and human interacting constraints of dynamic groups. An integrated Collision Risk and Human Space (CR&HS) model is applied to achieve human-acceptable behaviors, in which both collision avoidance, human comfort, and interference-free constraints have been involved. Moreover, an Improved Virtual Doppler Method (IVDM) has been used to realize safety navigation to avoid the robot falling into the crowded area. Finally, the proposed framework has been utilized with the sampling-based rapidly-exploring random tree. Experimental results demonstrate that the proposed method can generate the optimal human-aware collision-free path in complex environments.

Keywords:

Robots

Navigation

Collision avoidance

Trajectory

Dynamics

Planning

Heuristic algorithms

Mobile robots

human-aware navigation

dense crowd

social norms

obstacle avoidance

Human-Aware Path Planning With Improved Virtual Doppler Method in Highly Dynamic Environments

Abstract

Journal

Organization