Adding obstacle avoidance to a robotic platform for human robot interaction

Author(s):  
Christopher Abrego ◽  
Panos S. Shiakolas
Author(s):  
Sergio D. Sierra ◽  
Juan F. Molina ◽  
Daniel A. Gomez ◽  
Marcela C. Munera ◽  
Carlos A. Cifuentes

Robotica ◽  
2014 ◽  
Vol 33 (1) ◽  
pp. 1-18 ◽  
Author(s):  
Alberto Poncela ◽  
Leticia Gallardo-Estrella

SUMMARYVerbal communication is the most natural way of human–robot interaction. Such an interaction is usually achieved by means of a human-robot interface (HRI). In this paper, a HRI is presented to teleoperate a robotic platform via the user's voice. Hence, a speech recognition system is necessary. In this work, a user-dependent acoustic model for Spanish speakers has been developed to teleoperate a robot with a set of commands. Experimental results have been successful, both in terms of a high recognition rate and the navigation of the robot under the control of the user's voice.


2020 ◽  
Author(s):  
Bishakha Chaudhury ◽  
Ruud Hortensius ◽  
Martin Hoffmann ◽  
Emily S. Cross

As research examining human-robot interaction moves from the laboratory to the real world, studies seeking to examine how people interact with robots face the question of which robotic platform to employ to collect data in situ. To facilitate the study of a broad range of individuals, from children to clinical populations, across diverse environments, from homes to schools, a robust, reproducible, low-cost and easy-to-use robotic platform is needed. Here, we describe how a commercially available off-the-shelf robot, Cozmo, can be used to study embodied human-robot interactions in a wide variety of settings, including the user’s home. In this Tutorial, we describe the steps required to use this affordable and flexible platform for longitudinal human-robot interaction studies. First, we outline the technical specifications and requirements of this platform and accessories. We present findings from validation work we performed to map the behavioural repertoire of the Cozmo robot and introduce an accompanying interactive emotion classification tool to use with this robot. We then show how log files containing detailed data on the human-robot interaction can be collected and extracted. Finally, we detail the types of information that can be retrieved from these data. This low-cost robotic platform will provide the field with a variety of valuable new possibilities to study human-robot interactions within and beyond the research laboratory, which are user-driven and unconstrained in both time and place.


Author(s):  
Christopher E. Ábrego

In this manuscript, the development and current state of an inexpensive platform for educational purposes and research in the interaction between humans and robots (human-robot interaction) is described. The platform is based on the ubiquitous LabVIEW programming language and an in-house developed two degree of freedom non-holonomic robot. The platform includes multiple interaction modalities, which will be described, between the robot and the user. The procedures followed for the successful software and hardware implementation are explicated. Furthermore, a demonstration of an obstacle avoidance path planning algorithm for a single obstacle is validated in hardware, as well as simulation demonstration of the multiple obstacle avoidance algorithm. These implementations to the platform further demonstrate the ease of augmenting the existing platform to additional modalities. The algorithm uses a vision acquisition system to identify the location and size of an obstacle, in addition to orientation patterns and calibration points, in the workspace and generate the robot path to reach a desired goal while avoiding the obstacle. The manuscript describes into the current research of path planning in the presence of multiple obstacles. The development of a set of criteria, Generation Succession, Arrival Departure, and Side Consistency, for the algorithm are elucidated in the manuscript. The algorithm has been demonstrated to be successful in simulation by avoiding multiple obstacle in various layouts.


Sign in / Sign up

Export Citation Format

Share Document