Tsz-Chiu Au      Chiu

Assistant Professor
School of Electrical and Computer Engineering
Ulsan National Institute of Science and Technology

I am an assistant professor at UNIST. Previously I was a postdoc in the Learning Agents Research Group (LARG) and the AI Lab in the Department of Computer Science (UTCS) at UT Austin. Before joining UTCS, I studied at the University of Maryland, College Park, at which I was a member of the AI planning group and the Laboratory for Computational Cultural Dynamics (LCCD).

This is my CV.

News: I am looking for highly qualified Master and PhD students who are interested in Artificial Intelligence research to join my lab. If you are interested, please email me at chiu@unist.ac.kr.


Agents and Robotic Transportation Lab @ UNIST: Our goal is to scientifically investigate the foundations of Artificial Intelligence systems for decision making and problem solving. There are many tasks (e.g., driving and planning) that are manageable for humans but surprisingly difficult for machines and artificial beings with current technology. We are interested in 1) studying how to build intelligent agents that excel in these tasks, and 2) developing systems that can enhance our ability to handle these tasks.

Keywords: Artificial Intelligence, Automated Planning & Scheduling, Autonomous Vehicles, Case-Based Reasoning. Computer Game Playing, Game Theory, Intelligent Agents, Intelligent Transportation Systems, Human Robot Interaction, Machine Learning, Multiagent Systems and Robot Planning & Action.

Selected Projects:
  • Autonomous Vehicle Control for Improving Traffic. Fully autonomous vehicles are technologically feasible with the current generation of hardware, as demonstrated by recent robot car competitions. While the control of these autonomous vehicles are good enough for driving on today's roads, a more precise control of autonomous vehicles can lead to better utilization of road surfaces and reduce traffic congestion. As the first step, I theoretically examined the relationship between the precision of cars' motion control and the throughput of an intersection, and help developing a mixed-reality simulation platform to empirically show that our setpoint scheduler for brake and throttle actuators can reduce the chance that a vehicle stops before intersections.
  • Autonomous Traffic Management. Looking ahead to the time when autonomous cars will be common, we study how to utilize the capacity of autonomous vehicles to make transportation systems much more efficient. Dresner and Stone proposed an intersection control protocol for autonomous vehicle traffic called Autonomous Intersection Management (AIM), which is more efficient than traffic signals and stop signs. In this project, we expand the scope of AIM to traffic management in road networks, and aim to find out the best transportation infrastructure for traffic that consists of a mix of autonomous vehicles and human-controlled vehicles.
  • UTCS Gates Building Prediction Market (Work in progress). Prediction markets are popular tools for aggregating opinions regarding the likelihood of future events. The UTCS Gates Building Prediction Market is a new prediction market on the opening date of the Bill & Melinda Gates Computer Science Complex, the new home for the Computer Science Department at UT Austin. This project will test whether the new automated, liquidity-sensitive market maker algorithm jointly developed by Yahoo! and CMU can improve the performance of the market. Moreover, we will explore methods for improving prediction market accuracy by social networking services.
  • Combining best skills in observed agent's behaviors. To create better agents in multiagent environments, one may want to examine the observed behaviors of existing agents in order to combine their best skills. But the agents being observed may exhibit incompatible behaviors---the agents choose to do different things in some situations---and it is not immediately clear which behavior is better. I proposed a technique to identify the best subset of observed behaviors, in forms of interaction traces, that can be combined together to form a new strategy called composite strategy that potentially outperforms all agents being observed. In our experiments, the performance of nearly all agents increased after augmenting with composite strategies.
  • How to deal with noise in social games. An important question in many multiagent systems is how self-interested agents can resolve conflicts and coordinate with each other to accomplish a task. While existing strategies such as Tit-For-Tat and Pavlov work well in simple games such as Iterated Prisoner's Dilemma, they perform badly in the presence of noise, which randomly change the agents' actions or communications and cause huge problems in maintaining cooperation among agents. To deal with this long-standing problem in the study of the evolution of cooperation, I proposed several noise detection techniques and demonstrated that the noise detection approach is very effective in a number of non-zero-sum games.
  • Acquiring and managing volatile data for planning agents. In many planning problems such as robotic task planning and web service composition, an agent may need to acquire external information during planning. An important issue in planning with external information is information volatility---the collected information may change or expire before the termination of the planning process. For example, a web-based trip planner can generate incorrect travel plans if it does not know the information provided by an airline company has changed. To address this problem, we proposed several query management strategies for handling volatile data, and theoretically analyzed the conditions under which the solutions returned by the planning process remain valid.
Selected Publications:
  • T.-C. Au, C.-L. Fok, S. Vishwanath, C. Julien, and P. Stone. Evasion Planning for Autonomous Vehicles at Intersections. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2012), 2012. [pdf] [bibtex].
  • C.-L. Fok, M. Hanna, S. Gee, T.-C. Au, P. Stone, C. Julien, and S. Vishwanath. A Platform for Evaluating Autonomous Intersection Management Policies. In ACM/IEEE Third International Conference on Cyber-Physical Systems (ICCPS), pp. 87-96, 2012. [pdf] [bibtex].
  • T.-C. Au, M. Quinlan, and P. Stone. Setpoint Scheduling for Autonomous Vehicle Controllers. In IEEE International Conference on Robotics and Automation (ICRA), pp. 2055-2060, 2012. [pdf] [bibtex].
  • T.-C. Au, N. Shahidi, and P. Stone. Improving Transportation Efficiency for Sustainable Society by Autonomous Traffic Management. In Sustainability at UT Austin 2011 Symposium, The University of Texas at Austin, September 2011. [pdf] [bibtex].
  • M. Hausknecht, T.-C. Au, P. Stone, D. Fjardo, and S. T. Waller. Dynamic Lane Reversal in Autonomous Traffic Management. In IEEE Intelligent Transportation Systems Conference (ITSC 2011). [pdf] [bibtex].
  • M. Hausknecht, T.-C. Au, and P. Stone. Autonomous Intersection Management: Multi-Intersection Optimization. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011). [pdf] [bibtex].
  • T.-C. Au, N. Shahidi, and P. Stone. Enforcing Liveness in Autonomous Traffic Management. In Proceedings of the Twenty-Fifth Conference on Artificial Intelligence (AAAI-11), pp. 1561-1564, August 2011. [pdf] [bibtex] [proofs].
  • D. Fajardo, T.-C. Au, S. T. Waller, P. Stone, and D. Yang. Automated Intersection Control: Performance of a Future Innovation Versus Current Traffic Signal Control. In Transportation Research Record : Journal of the Transportation Research Board, 2259, pp. 223-232, 2012. [pdf] [bibtex].
  • N. Shahidi, T.-C. Au, and P. Stone. Batch Reservations in Autonomous Intersection Management. In Proceedings of the Tenth International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS 2011), May 2011. [pdf] [bibtex].
  • T.-C. Au and P. Stone. Motion Planning Algorithms for Autonomous Intersection Management. In AAAI 2010 Workshop on Bridging The Gap Between Task And Motion Planning (BTAMP), 2010. [pdf] [bibtex].
  • M. Quinlan, T.-C. Au, J. Zhu, N. Stiurca, and P. Stone. Bringing Simulation to Life: A Mixed Reality Autonomous Intersection. In Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2010), October 2010. [pdf] [bibtex] [video]. (The corresponding workshop paper in ICAPS-10: [pdf])
  • T.-C. Au, U. Kuter, and D. Nau. Planning for Interactions among Autonomous Agents. In International Workshop on Programming Multi-Agent Systems (ProMAS'08), 2009. [pdf] [bibtex].
  • T.-C. Au, S. Kraus, and D. Nau. Synthesis of Strategies from Interaction Traces. In Proceedings of the Seventh International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS'08), pp. 855-862, May 2008. [pdf] [data] [bibtex].
  • T.-C. Au and D. Nau. Is it Accidental or Intentional? A Symbolic Approach to the Noisy Iterated Prisoner's Dilemma. The Iterated Prisoners' Dilemma: 20 Years on, pp.231-262, World Scientific, 2007. [pdf] [bibtex].
  • T.-C. Au, S. Kraus, and D. Nau. Symbolic noise detection in the noisy iterated chicken game and the noisy iterated battle of the sexes. In First International Conference on Computational Cultural Dynamics (ICCCD-2007), pp. 16-25, August 2007. [pdf] [bibtex].
  • T.-C. Au. Dynamic Programming with Stochastic Opponent Models in Social Games: A Preliminary Report. In First International Conference on Computational Cultural Dynamics (ICCCD-2007), pp. 9-15, August 2007. [pdf] [bibtex].
  • T.-C. Au and D. Nau. Reactive Query Policies: A Formalism for Planning with Volatile External Information. IEEE Symposium on Computational Intelligence and Data Mining (CIDM), pp. 243-250, 2007. [pdf] [bibtex].
  • T.-C. Au and D. Nau. The Incompleteness of Planning with Volatile External Information. In Proceedings of the European Conference on Artificial Intelligence (ECAI), August 2006. [pdf] [bibtex].
  • T.-C. Au and D. Nau. Maintaining Cooperation in Noisy Environments. In Proceedings of the Twenty-First National Conference on Artificial Intelligence (AAAI-06). NECTAR paper. pp. 1561-1564, 2006. [pdf] [bibtex].
  • T.-C. Au and D. Nau. Accident or Intention: That is the Question (in the Noisy Iterated Prisoner's Dilemma). In Proceedings of the Fifth International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS'06). pp. 561-568, May 2006. [pdf] [bibtex].
  • T.-C. Au, U. Kuter and D. Nau. Web Service Composition with Volatile Information. In Proceedings of the 4th International Semantic Web Conference (ISWC-2005), pp. 52-66, 2005. [pdf] [bibtex].
  • D. Nau, T.-C. Au, O. Ilghami, U. Kuter, H. Muņoz-Avila, J. W. Murdock, D. Wu, and F. Yaman. Applications of SHOP and SHOP2. IEEE Intelligent Systems 20:2, pp. 34-41, 2005. [pdf] [html] [bibtex].
  • T.-C. Au, D. Nau, and V. Subrahamanian. Utilizing volatile external information during planning. In Proceedings of the European Conference on Artificial Intelligence (ECAI), pp. 647-651, August 2004. [pdf] [bibtex].
  • D. Nau, T.-C. Au, O. Ilghami, U. Kuter, J. W. Murdock, D. Wu, and F. Yaman. SHOP2: An HTN planning system. Journal of Artificial Intelligence Research (JAIR) 20:379-404, December 2003. [pdf] [html] [bibtex].
  • T.-C. Au, H. Muņoz-Avila, and D. S. Nau. On the complexity of plan adaptation by derivational analogy in a universal classical planning framework. In Proceedings of the European Conference on Case-Based Reasoning (ECCBR), pp. 13-27, September 4-7 2002. [pdf] [bibtex].
Contact Information:
  • Email: chiu (at) unist.ac.kr
  • Phone: +82-52-217-6287
  • Address:
    School of Electrical and Computer Engineering (ECE)
    Ulsan National Institute of Science and Technology (UNIST)
    UNIST-gil 50, Eonyang-eup, Ulju-gun
    Ulsan, Republic of Korea, 689-798