What is ABOD3?
ABODE is an integrated development environment (IDE) for Behavior Oriented Design (BOD). ABOD3 is the latest iteration of the ABODE, providing new functionalities such as our novel approach to AI-debugging.
Unlike previous updates of ABODE, it was built from scratch, without any usage of the existing source code. In addition to new functionalities, the new version aims at using modular, clean-code, with all the features and performance enhancements of Java 8. The GUI framework used, JavaFX, gives the new version a clean, modern look, while maintaining cross-platform compatibility.
Where can I get it from?
Who are the developers?
Alexandros Rotsidi, an EngD student at the University of Bath, is working towards porting ABOD3 to Android phones.
Robbert (Rob) R. Wortham and Joanna J. Bryson from University of Bath contributed by helping with the design and testing of the final deliverable. Rob is the developer of Instinct, a transparent planner. His GitHub can be found here.
We are always happy to accept contributions and feedback by third party users! Get in touch via Twitter or GitHub, if interested.
How can I cite ABOD3?
Theodorou, A. (2017). ABOD3: A Graphical Visualization and Real-Time Debugging Tool for BOD Agent, CEUR Workshop Proceedings, 1855
Theodorou, A., Wortham R.H. and Bryson J.J., (2017). Designing and implementing transparency for real time inspection of autonomous robots, Connection Science: Special Issue in the Principles of Robotics
Research publications related to ABOD3
Wortham, R. H. (2018), Using other minds: Transparency as a Fundamental Design Consideration of Artificial Intelligence Systems, PhD Thesis, University of Bath
Wortham, R. H., Theodorou, A. and Bryson, J. J. (2017), Robot transparency: Improving understanding of intelligent behaviour for designers and users} In: Gao, Y., Fallah, S., Jin, Y. and Lakakou, C., eds. Towards Autonomous Robotic Systems: 18th Annual Conference, TAROS 2017, Guildford, UK, July 19–21, 2017. Berlin: Springer, pp. 274-289. (Lecture Notes in Artificial Intelligence; 10454)
Wortham, R.H., Theodorou, A. and Bryson J.J. (2017), Improving Robot Transparency: Real-Time Visualisation of Robot AI Substantially Improves Understanding in Naive Observers}, RO-MAN, Lisbon, Portugal
Wortham, R.H., Theodorou, A. and Bryson J.J. (2017), Robot Transparency: Improving Understanding of Intelligent Behaviour for Designers and Users}, TAROS 2017, Guildford, UK
Wortham, R.H., Theodorou, A. and Bryson J.J., (2016), What Does the Robot Think? Transparency as a Fundamental Design Requirement for Intelligent Systems}, IJCAI 2016 Ethics for Artificial Intelligence Workshop, New York, US
ABOD3 in teaching
Joanna Bryson's [Intelligent Cognitive Control Systems] (http://www.cs.bath.ac.uk/~jjb/here/CM50230/ai-course-sched.html) module.