Robots asking for directions — The willingness of passers-by to support robots

Abstract

This paper reports about a human-robot interaction field trial conducted with the autonomous mobile robot ACE (Autonomous City Explorer) in a public place, where the ACE robot needs the support of human passers-by to find its way to a target location. Since the robot does not possess any prior map knowledge or GPS support, it has to acquire missing information through interaction with humans. The robot thus has to initiate communication by asking for the way, and retrieves information from passers-by showing the way by gestures (pointing) and marking goal positions on a still image on the touch screen of the robot. The aims of the field trial where threefold: (1) Investigating the aptitude of the navigation architecture, (2) Evaluating the intuitiveness of the interaction concept for the passers-by, (3) Assessing people's willingness to support the ACE robot in its task, i.e. assessing the social acceptability. The field trial demonstrates that the architecture enables successful autonomous path finding without any prior map knowledge just by route directions given by passers-by. An additional street survey and observational data moreover attests the intuitiveness of the interaction paradigm and the high acceptability of the ACE robot in the public place.

Comparing Heads-up, Hands-free Operation of Ground Robots to Teleoperation

“…This study suggests that people are willing to use gestures for robot control, even if they may need some basic training. Weiss and others found that onlookers willingly helped a robot with directions by communicating with it through gestures [13]. The most similar study to ours is Guo and Sharlin's comparison of Wiimote-based gesture control of a robot to keyboard-based control [14].…”

Modeling and Prediction of Pedestrian Behavior based on the Sub-goal Concept

“…From a qualitative analysis, we can see that the sub-goal method depicts that pedestrians mainly just pass through the environment (14-7-3-1-10-9-0-23-17-20-2) but some of them deviate from the main corridor to go to shops (8,13,18), exhibits (16,21) or gates (4,5). The topology method extracts nodes on crossing points between corridors (18,22,24), but other qualitatively meaningful points such as gates or entries of shops are not extracted.…”

“…Knowledge of the current pedestrian density at larger distances, the average behavior of pedestrians in the environment, and even the use of a pedestrian simulator to predict the future behavior of the crowd as a whole may prevent the robot to end in highly populated areas where collision avoidance could not be performed effectively. To provide services such as guiding [1,2], surveillance, shopping assistance [3], giving information [4,5,6], assisting people who get lost, an ability to recognize behavioral patterns and predict future behavior and position is needed.…”

Capturing Expertise: Developing Interaction Content for a Robot Through Teleoperation by Domain Experts

“…Recently, robotics researchers have been investigating the use of humanoid robots to provide services for and interact with people in everyday social environments, such as assisting in nursing homes [1], providing route guidance in a shopping center [2], helping people to do their shopping in a supermarket [3], greeting people at a reception booth [4], and interacting with people on city streets [5]. As such robots become common in society, it will be important for them to provide information to people through humanlike interaction (Fig.…”