Welcome to the 5th Goal Reasoning Workshop at IJCAI-2017!

Goals are a unifying structure across the variety of intelligent systems, and reasoning about goals takes many forms. In the most encompassing view, intelligent systems can use goal structures (or goal rewards) to manage long-term behavior, anticipate the future, select among priorities, commit to action, generate expectations, assess tradeoffs, resolve the impact of notable events, or learn from experience or find the best explanations https://primeessays.com/ As a result, the broad topic of goal reasoning is studied in diverse subfields of AI such as motivated systems, cognitive science, automated planning, and agent-oriented programming to name but a few. This workshop aims to bring together researchers from sometimes distinct subfields to encourage cross-disciplinary discussion on goal reasoning.

We plan a one-day workshop with discussion of submitted papers with guest speakers Michael Winikoff and Michael Floyd.

Topics include, but are not limited to:

  • Theoretical models of goal reasoning
  • The role of goals in self-motivated systems
  • The role of implicit goals or goal rewards in intelligent system design
  • Goal reasoning in hybrid systems
  • Interactive goal reasoning
  • Goal reasoning in humans
  • Goal management
  • Conversational or narrative reasoning about goals
  • Goal-driven autonomy
  • Explanation and diagnosis of notable objects and events that impact goals
  • Planning, scheduling, and (meta-)reasoning for goals
  • Resolving goals online (e.g., plan repair, replanning, goal deferment, re-goaling)
  • Multi-agent or distributed goal management
  • Learning for goal reasoning
  • Comparisons of goal reasoning with other models of autonomy
  • Evaluation/analyses of goal reasoning
  • Demonstrations or applications of goal reasoning systems

Organizers

Name Affiliation Email Website
Mark 'Mak' Roberts* Naval Research Laboratory, USA mark.roberts AT nrl.navy.mil URL
Michael T. Cox Wright State University, USA michael.cox AT wright.edu URL
Hector Muñoz-Avila Lehigh University hem4 AT lehigh.edu URL

Program Committee

Name Affiliation
David Aha Naval Research Laboratory, USA
Ron Alford MITRE Corporation, USA
Hayley Borck Adventium Labs, USA
Daniel Borrajo Universidad Carlos III de Madrid
Mark Burstein SIFT, USA
Alexandra Coman NRC Postdoc, Naval Research Laboratory, USA
Dustin Dannenhauer Lehigh University
Kellen Gillespie Amazon, Inc.
James Harland RMIT University, Australia
Nick Hawes U. Birmingham, UK
Eva Onaindia University Politecnica de Valencia, Spain
Martin Oxenham Defence Science and Technology Group, Australia
Alexander Pokahr University of Hamburg, Germany
Wheeler Ruml University of New Hampshire, USA
Sebastian Sardina RMIT University, Australia
Swaroop Vattam MIT Lincoln Labs, USA
Neil Yorke-Smith American University of Beirut

Important Dates

Paper Submission - May 5, 2017 EXTENDED May 15, 2017

Author Notification - June 5, 2017 EXTENDED June 9, 2017

IJCAI Early registration deadline - June 20, 2017

Final Version - July 28 - Please submit your final version to EasyChair.

Workshop held - August 19, 2017

Submissions

Submissions should follow the IJCAI formatting requirements except (1) the submissions should contain the author names (reviewing will *not* be anonymous) and (2) the page limit is 8 pages plus one page for references so authors have space to address reviewer comments as needed. Formatting style files are found here.

Submissions will be accepted through easychair: https://easychair.org/conferences/?conf=ijcai2017grw

Related Previous Workshops

2016 4th Workshop on Goal Reasoning at IJCAI 2016 with 15 submissions

2015 Workshop on Goal Reasoning at Advances in Cognitive Systems with 14 submissions

2013 Workshop on Goal Reasoning at Advances in Cognitive Systems with 11 submissions

2010 Workshop on Goal Directed Autonomy at AAAI 2010 with 11 submissions

Schedule

A preliminary schedule is available here.

Guest Speakers

Michael Winikoff -- Goal Reasoning Research in the EMAS Community

Abstract: This talk aims to help bridge between two communities: the Goal Reasoning community, and the Engineering Multi-Agent Systems (EMAS) community. I discuss broadly the different perspectives and assumptions adopted by the two communities, and then proceed to discuss a range of relevant work in the EMAS community. This includes both pointing out some key relevant papers (by others) in the EMAS community, and discussing some of my own relevant prior work. In particular, I discuss work on representing goals, on managing interactions between concurrent goals, and on how to select between different options for attaining a goal. I finish by posing some challenges to the Goal Reasoning community.

Michael Floyd -- Goal Reasoning in Support of Human-Robot Teams

Abstract: Goal Reasoning allows agents to reason about their goals and dynamically modify them in response to opportunistic situations or unexpected events. Goal selection and modification is typically influenced by the environment (e.g., unexpected environment changes) or the agent's self-evaluation (e.g., detecting plan or action failures, reevaluating the utility of goals). Our work focuses on goal reasoning agents that operate in environments with other intelligent agents (e.g., teammates, adversaries, or neutral agents) and, therefore, need to consider the goals and motivations of these other agents when selecting their own goals. More specifically, we consider agents that are members of human-robot (or human-agent) teams. We have developed several techniques that allow an agent to successfully integrate into a team, including the ability to recognize the plans and goals of other agents, modify an agent's goals in response to a detected change in teammates' goals, coordinate with teammates on multi-agent tactics, and incorporate teammate preferences during goal selection. Our Goal Reasoning agents have been used to control autonomous ground vehicles and autonomous aerial vehicles that are members of human-robot teams in simulated scenarios. Additionally, preliminary results show that humans respond positively to having a Goal Reasoning agent as a teammate.

Proceedings

The papers can be downloaded as a single zip file here.

Presentations

TBD