Robot Navigation based on the Mapping of Coarse Qualitative Route Descriptions to Route Graphs

Abstract

Abstract-This paper describes the use of natural language route descriptions in the mobile robot navigation domain. Guided by corpus analysis and earlier work on coarse qualitative route descriptions, we decompose instructions given by humans into sequences of imprecise route segment descriptions. By applying fuzzy rules for the involved spatial relations and actions, we construct a search tree that can be searched in a depth-first branchand-bound manner for the most probable goal configuration w.r.t. the global workspace knowledge of the robot. The applicability of our approach is shown by a real-world experiment where an operator instructs his automated wheelchair to navigate in an office-like environment.

Semantic map segmentation using function-based energy maximization

“…Related work has been done e.g. by Kollar et al [15], who also use an energy optimization method to determine referents for an expression, and Mandel et al [16], who choose the referent from among Voronoi nodes using fuzzy functions. Both of the above deal with route descriptions, and not with labeling or segmenting maps.…”

Controlling an automated wheelchair via joystick/head-joystick supported by smart driving assistance

“…While such interfaces suit a large audience, certain disabilities may require appropriate alternatives, e. g. Brain-Computer-Interfaces [7], [8], head posture [9] or gaze [10] interpretation, and natural language communication [11], [12], to name but a few.…”

Towards Affordance-Based Robot Control

“…Rolland's linguistic module interprets route descriptions by a human instructor (driver) (Mandel et al 2006). The mappings between linguistic constituents and internal qualitative spatial maps (route graphs) are based on ontological representtations (Ross et al 2005).…”