Career Profile

My primary research areas include artificial intelligence, machine learning, advanced autonomy, neuro-symbolic systems, automated planning and acting, cognitive architectures, reinforcement learning, motion planning, hierarchical task planning, and goal reasoning.


Research Scientist

2021 - Present
Metron Inc, Virgina, VA

Conduct research and develope autonomy algorithms for underwater vehicles.

Research Scientist

2019 - 2021
Knexus Research Corp., Maryland

Conduct research and develop systems in goal reasoning, cognitive architectures, theory of mind and automated planning applied toward a range of autonomous systems for DARPA.

Research Assistant

2015 - 2019

Investigated autonomous agents operating in dynamic environments.

Developed an interface between the MIDCA cognitive architecture and a Baxter humanoid robot.

Studied the relationship between Perception, Planning, and Interpretation.

Research Assistant

2013 – 2015
Kno.e.sis Center, Dayton, OH

Conducted research in areas of cloud computing, big data and machine learning in distributed frameworks.

Worked on an approach to scale up existing Euclidean embedding algorithms for Big Data.

Software Developer

2012 - 2013
Agah Co

Developed a customized online shopping store using Grails and My SQL.

Software Developer

2011 – 2012

Developed a Valuation system to estimate share prices of banks.

Developed an Excel Add-in that shows on-line trading information.

Developed a duplex WCF service that pushes new data to subscribed clients.

Software Developer

2009 – 2011
Arish Co

Developed apps to read utility meters remotely using varied technologies (GPRS, etc.)


  • Dannenhauer, Z. A. “Anticipation in Dynamic Environments; Knowing What to Monitor.” Doctoral dissertation, Wright State University, College of Engineering and Computer Science, Dayton.
  • [AIC-18] Dannenhauer, Z. A., & Cox, M. T. (2018). “Rationale-based Perceptual Monitors.” In AI Communications Journal 31.2, pp. 197–212.
  • [ACS-17] Cox, M. T., & Dannenhauer, Z. A. (2017). “Perceptual goal monitors for cognitive agents in changing environments.” In The Fifth Annual Conference on Advances in Cognitive Systems (pp. 1-16). Palo Alto, CA: Cognitive Systems Foundation.
  • [FLAIRS-17] Dannenhauer, Z. A., & Cox, M. T. (2017).“Rationale-based visual planning monitors for cognitive systems.” In V. Rus & Z. Markov (Eds.), Proceedings of the 30th International FLAIRS Conference (pp. 182-185). Palo Alto, CA: AAAI Press.
  • [IJCAI-16 Goal Reasoning Workshop] Alavi, Z. and Cox, M.T. (2016). “Rationale-based Visual Planning Monitors.” In Working Notes of the 4th Workshop on Goal Reasoning. New York, IJCAI-16.
  • [AAAI-16] Cox, M. T., Alavi, Z., Dannenhauer, D., Eyorokon, V., & Munoz-Avila, H. (2016). “MIDCA: A metacognitive, integrated dual-cycle architecture for self-regulated autonomy.” Proceedings of the 30th AAAI Conference on Artificial Intelligence. Palo Alto, CA: AAAI Press.
  • [CLOUD-15] Alavi, Z., Sharma, S., Zhou, L., & Chen, K. (2015, June). “Scalable Euclidean Embedding for Big Data.” In Cloud Computing (CLOUD), 2015 IEEE 8th International Conference on (pp.773-780). IEEE.
  • [VLDB-14] Alavi, Z., Zhou, L., Powers, J., &Chen, K. (2014). “RASP-QS: Efficient and Confidential Query Services in the Cloud.” Proceedings of the VLDB Endowment, 7(13).
  • [ICCAE-10] Rahbarinia, B., Pedram, M. M., Arabnia, H., & Alavi, Z. (2010, February). “A multi-objective scheme to hide sequential patterns.” In Computer and Automation Engineering (ICCAE), 2010 The 2nd International Conference on(Vol. 1, pp. 153-158). IEEE.
  • [EJSR-10] Djahantighi, F. S., Feizi-Derakhshi, M. R., Pedram, M. M., & Alavi, Z. (2010). “An effective algorithm for mining users behaviour in time-periods.” European Journal of Scientific Research, 40(1), 81-90.


PRIDE - Designed and developed a collection of AI based reasoning components: Cognitive Appraisal: appraising the actions of others, determining the intent of actions, and updating the agent’s emotions in response. Goal Reasoning: the agent’s ability to choose which goals to act upon based on its identified emotions and beliefs. Multi-agent Planning: the agent’s abilitytogenerateplanstoachieveitsgoals in an adversarial dynamic environment.
PRESNA : Lead the AI effort to simulate realistic crowd behavior in a crisis monitoring system.
MIDCA (METACOGNITIVE INTEGRATED DUAL CYCLE ARCHITECTURE) - My work focused on integrating Perception, Planning and Interpretation to help an agent to respond to unexpected changes in dynamic world. We claim that an intelligent agent should actively watch for what can go wrong and anticipate mistakes before they occur. Some world changes affect the agent’s goals and some affect the agent’s plan. The agent should be able to respond to these changes appropriately to successfully accomplish its tasks.
( Video of MIDCA Controlling a Robot ); In this demo, someone makes a change in the world while Baxter is planning. Using plan monitors, Baxter can observe the change and adapt its plan for the new situation.
RASP-QS : Efficient and Confidential Query Services in the Cloud ( Query Processing Demo and Visualization )


Distributed Computing - MapReduce, Pig, Hadoop
Machine Learning - Deep Learning (RNN), Deep Learning Platforms (TensorFlow), SVM, Dimensionality Reduction Techniques, Classification and Clustering Algorithms.
Programming - JAVA, C#, Python, Prolog, Answer Set Programming, Scheme
Databases - MY SQL, SQL Server
Knowledge Representation - RDF, RDFS, OWL
Robotics - ROS, Gazebo

Professional Activities

Organizer for the 4th Integrating Planning, Acting, and Execution (IntEx) and 8th Goal Reasoning (GR) held at ICAPS-2020

Served as a reviewer for IJCAI-16 GR Workshop, AAAI-16, ACS-17, and ICAPS-19.