The Autonomous City Explorer: Towards Natural Human-Robot Interaction in Urban Environments

Abstract

The Autonomous City Explorer (ACE) project combines research from autonomous outdoor navigation and human-robot interaction. The ACE robot is capable of navigating unknown urban environments without the use of GPS data or prior map knowledge. It finds its way by interacting with pedestrians in a natural and intuitive way and building a topological representation of its surroundings. In a recent experiment the robot managed to successfully travel a 1.5 km distance from the campus of the Technische Universität München to Marienplatz, the central square of Munich.This article describes the principles and system components for navigation in urban environments, information retrieval through natural human-robot interaction, the construction of a suitable semantic representation as well as results from the field experiment.

Why did the robot cross the road? — Learning from multi-modal sensor data for autonomous road crossing

“…However, few approaches have addressed this problem for pedestrian robots. Bauer et al present an autonomous outdoor navigation pedestrian robot operating in outdoor urban environments [3]. The robot is capable of navigating through signalized crossings by detecting and classifying traffic lights and signals at the intersection.…”

Toward Information Theoretic Human-Robot Dialog

“…In this paper, we present an approach for enabling robots to recover from failures like these by asking a clarifying question, the same strategy that humans use when faced with ambiguous 1 The first two authors contributed equally to this paper.…”

Clarifying Commands with Information-Theoretic Human-Robot Dialog

“…Others have created robotic systems that interact using dialog (Cantrell et al, 2012;Dzifcak et al, 2009;Hsiao, Tellex, Vosoughi, Kubat, & Roy, 2008;Skubic et al, 2004). (Bauer et al, 2009) built a robot that can find its way through an urban environment by interacting with pedestrians using a touch screen and gesture recognition system. (Fong, Nourbakhsh, & Dautenhahn, 2003) developed a collaborative control system in which robots asked human partners questions via a PDA interface.…”

“…Previous approaches to robotic question-asking do not directly map between unconstrained natural language and perceptually-grounded aspects of the external world, and prior methods do not incorporate additional information from free-form natural language answers in order to disambiguate the command (Bauer et al, 2009;Doshi & Roy, 2008;Rosenthal, Veloso, & Dey, 2011). As a result, the robot cannot take advantage of its external world knowledge to determine the most ambiguous parts of an arbitrary natural language command and identify a targeted question to ask.…”