Simultaneous Path Planning and Topological Mapping (SP2ATM) for environment exploration and goal oriented navigation

  • Authors:

  • Shuzhi Sam Ge;Qun Zhang;Aswin Thomas Abraham;Brice Rebsamen

  • Affiliations:

  • Interactive & Digital Media Institute (IDMI), Department of Electrical and Computer Engineering, National University of Singapore, Singapore 117576;NUS Graduate School for Integrative Sciences and Engineering (NGS), National University of Singapore, Singapore 117456;NUS Graduate School for Integrative Sciences and Engineering (NGS), National University of Singapore, Singapore 117456;Temasek Laboratories, National University of Singapore, Singapore 117411

  • Venue:
  • Robotics and Autonomous Systems
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, a novel approach, Simultaneous Path Planning and Topological Mapping (SP^2ATM), is presented to address the problem of path planning in unknown environments by concurrent and incremental construction of a map, which strictly exploits only the topology rather than grid representation. For local topological information representation, a new concept, Admissible Space Tree (AST), is presented to describe the admissible free space in the environment as a group of nodes and graphs. The global map of the explored environment is encoded in a Hierarchical Topological Map (HTM), which by embedding the AST, serves as the least information to facilitate path planning. For simplicity, the algorithm is implemented in a planar space on our differentially driven mobile robot X1, based on its range sensing and self-localization capabilities. Experiments' results show that SP^2ATM is effective and globally convergent in complex and dynamic environments.