Sergio Guadarrama

Language Grounding and Robotics

Grounding Spatial Relations for Human-Robot Interaction

 

We propose a system for human-robot interaction that learns both models for spatial prepositions and for object recognition. Our system grounds the meaning of an input sentence in terms of visual percepts coming from the robot's sensors in order to send an appropriate command to the PR2 or respond to spatial queries. To perform this grounding, the system recognizes the objects in the scene, determines which spatial relations hold between those objects, and semantically parses the input sentence. The proposed system uses the visual and spatial information in conjunction with the semantic parse to interpret statements that refer to objects (nouns), their spatial relationships (prepositions), and to execute commands (actions). The semantic parse is inherently compositional, allowing the robot to understand complex commands that refer to multiple objects and relations such as: “Move the cup close to the robot to the area in front of the plate and behind the tea box”. Our system correctly parses 94% of the 210 online test sentences, correctly interprets 91% of the correctly parsed sentences, and correctly executes 89% of the correctly interpreted sentences.
[PDF] [BibTex]

Approximate robotic mapping from sonar data by modeling perceptions with antonyms

Information Sciences 10 

This work, inspired by the idea of “Computing with Words and Perceptions” proposed by Zadeh, focuses on how to transform measurements into perceptions for the problem of map building by Autonomous Mobile Robots. We propose to model the perceptions obtained from sonar-sensors as two grid maps: one for obstacles and another for empty-spaces. The rules used to build and integrate these maps are expressed by linguistic descriptions and modeled by fuzzy rules. The main difference of this approach from other studies reported in the literature is that the method presented here is based on the hypothesis that the concepts “occupied” and “empty” are antonyms rather than complementary (as it happens in probabilistic approaches), or independent (as it happens in the previous fuzzy models).

Controlled experimentation with a real robot in three representative indoor environments has been performed and the results presented. We offer a qualitative and quantitative comparison of the estimated maps obtained by the probabilistic approach, the previous fuzzy method and the new antonyms-based fuzzy approach. It is shown that the maps obtained with the antonyms-based approach are better defined, capture better the shape of the walls and of the empty-spaces, and contain less errors due to rebounds and short-echoes. Furthermore, in spite of noise and low resolution inherent to the sonar-sensors used, the maps obtained are accurate and tolerant to imprecision.
[PDF] [BibTex]