Integrating Topological and Metric Maps for Mobile Robot Navigation: A Statistical Approach

The problem of concurrent mapping and localization has received considerable attention in the mobile robotics community. Existing approachescan largely be grouped into two distinct paradigms: topological and metric. This paper proposes a method that integrates both. It posesthe mappingproblem as a statistical maximum likelihood problem, and devises an efficient algorithm for search in likelihood space. It presents an novel mapping algorithm that integrates two phases: a topological and a metric mapping phase. The topological mapping phasesolves a global position alignment problem between potentially indistinguishable, significant places. The subsequent metric mapping phase produces a fine-grained metric map of the environment in floating-point resolution. The approach is demonstrated empirically to scale up to large, cyclic, and highly ambiguous environments.

• Type: Conference
• Year: 1998
• Where: AAAI
• Authors: Sebastian Thrun, Jens-Steffen Gutmann, Dieter Fox, Wolfram Burgard, Benjamin Kuipers
• Keywords: AAAI 1998, Intelligent Agents, Metric Mapping Phase, Subsequent Metric Mapping, Topological