Continuous integration for iterative validation of simulated robot models

Authors:
Florian Lier;Simon Schulz;Ingo Lütkebohle
Affiliations:
Center of Excellence Cognitive Interaction Technology (CITEC), Bielefeld, Germany;Center of Excellence Cognitive Interaction Technology (CITEC), Bielefeld, Germany;CoR-Lab Research Institute for Cognition and Robotics, Bielefeld, Germany
Venue:
SIMPAR'12 Proceedings of the Third international conference on Simulation, Modeling, and Programming for Autonomous Robots
Year:
2012

Citing 5
Cited 2

Continuous integration: improving software quality and reducing risk

Continuous integration: improving software quality and reducing risk
Robot simulation physics validation

PerMIS '07 Proceedings of the 2007 Workshop on Performance Metrics for Intelligent Systems
Design and validation of a Whegs robot in USARSim

PerMIS '07 Proceedings of the 2007 Workshop on Performance Metrics for Intelligent Systems
An open-source simulator for cognitive robotics research: the prototype of the iCub humanoid robot simulator

PerMIS '08 Proceedings of the 8th Workshop on Performance Metrics for Intelligent Systems
Developing Intelligent Environments: A Development Tool Chain for Creation, Testing and Simulation of Smart and Intelligent Environments

IE '11 Proceedings of the 2011 Seventh International Conference on Intelligent Environments

The role of emotional congruence in human-robot interaction

Proceedings of the 8th ACM/IEEE international conference on Human-robot interaction
Reality check!: a physical robot versus its simulation

Proceedings of the 2014 ACM/IEEE international conference on Human-robot interaction

Quantified Score

Hi-index	0.00

Visualization

Abstract

Simulated environments often provide the first, and are usually the most frequent, test environment for robotic systems, primarily due to their cost and safety advantages. Unfortunately, changing aspects of both, the simulation and the real robot, as well as actuator control algorithms are often not taken into account when relying on simulation results. In this paper we present a continuous integration approach to verify simulated robot models in an integrated and frequent manner, comprising a simulated and a real robot for comparison. The central aspect of our concept is to iteratively assess the fidelity of simulated robot models. In an exemplary case study we distilled a first set of requirements and metrics, which can be used by developers to verify their algorithms and to automatically detect further system changes.