Skip to content. Skip to main navigation.

avatar

Manfred Huber

Name

[Huber, Manfred]
  • Professor, Department of Computer Science & Engineering

Professional Preparation

    • 1990 'Vordiplom' in Computer ScienceUniversity of Karlsruhe
    • 1993 M.S. in Computer ScienceUniversity of Massachusetts
    • 2000 Ph.D. in Computer ScienceUniversity of Massachusetts

Appointments

    • Sept 2015 to Present Professor
      University of Texas at Arlington
    • Sept 2006 to Aug 2015 Assoc Prof
      University of Texas at Arlington
    • Sept 2000 to Aug 2006 Assist Professor
      University of Texas at Arlington
    • Sept 1999 to Aug 2000 Visiting Assistant Professor
      University of Texas at Arlington

Publications

      Journal Article 2014
      • M. Aurangzeb, F. Lewis, and M. Huber. "Efficient, Swarm-Based Path Finding in Unknown Graphs Using Reinforcement Learning". In Journal of Control and Intelligent Systems, Vol 3, pp 2583-2590, 2014.

        {Journal Article }

      Conference Paper 2013
      • H. Janzadeh and M. Huber. "Learning Policies in Partially Observable MDPs with Abstract Actions Using Value Iteration", To appear in Proceedings of the 26th International FLAIRS Conference (FLAIRS'13), St. Pete Beach, May 2013.

        {Conference Paper }
      2013
      • M. Aurangzeb, F.L. Lewis, M. Huber. "Efficient, Swarm-Based Path Finding in Unknown Graphs Using Reinforcement Learning", In Proceedings of the 10th IEEE International Conference on Control & Automation (ICCA 2013), Hangzhou, China, 2013.

        {Conference Paper }
      2013
      • H. Rahmanian, M. Huber. "Data Modeling Using Channel-Remapped Generalized Features", In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC'13), Manchester, England, October 2013.

        {Conference Paper }
      2013
      • Djurdjevic P, Huber M (2013), Deep Belief Network for Modeling Hierarchical Reinforcement Learning Policies, To appear in Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC'13), Manchester, England, October 2013.

        {Conference Paper }
      2013
      • R. Su, T.M. Dockins, and M. Huber. "ICA Analysis of Face Color for Health Applications", To appear in Proceedings of the 26th International FLAIRS Conference (FLAIRS'13), St. Pete Beach, FL, 2013.

        {Conference Paper }
      2013
      • R. Fakoor, F. Ladhak, A. Nazi, M. Huber. "Using Deep Learning to Enhance Cancer Diagnosis and Classification". In Proceedings of the ICML Workshop on the Role of Machine Learning in Transforming Healthcare (WHEALTH). Atlanta, GA, June 2013.

        {Conference Paper }

      Conference Paper 2012
      • T. Reddy, V. Gopikrishna, and M. Huber. "Inverse Reinforcement Learning for Decentralized Non-Cooperative Multiagent Systems", In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC'12), Seoul, South Korea, 2012.
        {Conference Paper }
      2012
      • R. Fakoor and M. Huber. "Improving Tractability of POMDPs by Separation of Decision and Perceptual Processes", In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC'12), Seoul, South Korea, 2012.
        {Conference Paper }
      2012
      • M. Oladell and M. Huber. "Symbol Generation and Feature Selection for Reinforcement Learning Agents Using Affordances and U-Trees", In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC'12), Seoul, South Korea, 2012.
        {Conference Paper }
      2012
      • R. Fakoor and M. Huber M. "A Sampling-Based Approach to Reducing the Complexity of Continuous State Space POMDPs by Decomposition into Coupled Perceptual and Decision Processes", In Proceedings of the International Conference on Machine Learning and Applications (ICMLA'12), Boca Raton, FL, 2012.
        {Conference Paper }
      2012
      • T.S. Reddy, G.V. Zaruba, and M. Huber. "Game Theoretic Framework for Communication in Fully Observable Multiagent Systems", In Proceedings of the International Conference on Machine Learning and Applications (ICMLA'12), Boca Raton, FL, 2012.
        {Conference Paper }
      2012
      • T.M. Dockins and M. Huber. "Social Influence Modeling for Utility Functions in Model Predictive Control", In Proceedings of the 25th International FLAIRS Conference (FLAIRS'12), Marco Island, FL, 2012.
        {Conference Paper }
      2012
      • M. Oladell and M. Huber. "Symbol Generation and Grounding for Reinforcement Learning Agents Using Affordances and Dictionary Compression", In Proceedings of the 25th International FLAIRS Conference (FLAIRS'12), Marco Island, FL, 2012.
        {Conference Paper }

      Conference Paper 2011
      • P-H. Ciu and M. Huber. "Reinforcement Field". In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC'11) (Anchorage, AK, 2011).
        {Conference Paper }
      2011
      • S. Rajendran and M. Huber. "Autonomous Identification, Categorization and Generalization of Policies Based on Task Type". In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC'11), Anchorage, AK, 2011.
        {Conference Paper }
      2011
      • P-H. Ciu and M. Huber. "Generalized Reinforcement Learning with Concept-Driven Abstract Actions". In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC'11), Anchorage, AK, 2011.
        {Conference Paper }
      2011
      • S. Thirumuruganathan and M. Huber. "Building Bayesian Network based Expert Systems from Rules". In Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC'11), Anchorage, AK, 2011.
        {Conference Paper }

      Conference Proceeding 2010
      • J. B. Brown and M. Huber. "Pseudo-Hierarchical Ant-Based Clustering: Using Automatic Boundary Formation and a Heterogeneous Agent Hierarchy to Improve Ant-Based Clustering Performance," in Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC'10) (Istanbul, Turkey, 2010).
        {Conference Proceeding }
      2010
      • J. B. Brown and M. Huber. "Pseudo-Hierarchical Ant-Based Clustering Using a Heterogeneous Agent Hierarchy and Automatic Boundary Formation," in Proceedings of the Genetic and Evolutionary Computation Conference (GECCO'10) (Portland, OR, 2010).
        {Conference Proceeding }
      2010
      • C. F. Jr, D. Nguyen, G. B. Guerra, and H. M. Filho. "Identification of Static and Dynamic Muscle Activation Patterns for Intuitive Human/Computer Interfaces," in Proceedings of the 3rd International Conference on Pervasive Technologies Related to Assistive Environments (PETRA'10) (Samos, Greece, 2010).
        {Conference Proceeding }
      2010
      • A. Iqbal, L. Zhou, M. Huber, and G. Zaruba. "Optimizing Path of Mobile Beacon with Genetic Algorithm to Localize Sensor Network," in Proceedings of the 3rd International Conference on Pervasive Technologies Related to Assistive Environments (PETRA'10) (Samos, Greece, 2010).
        {Conference Proceeding }

      Journal Article 2010
      • B. Holbert and M. Huber. "Design and Evaluation of Haptic Effects for Use in a Computer Desktop for the Physically Disabled," International Journal on Universal Access in the Information Society, 2010.
        {Journal Article }

      Conference Proceeding 2009
      • V. Gopikrishna and M. Huber. "A Temporal Potential Function Approach For Path Planning in Dynamic Environments," in Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC'09) (San Antonio, TX, 2009).
        {Conference Proceeding }
      2009
      • G. D'Silva and M. Huber. "Encoding User Motion Preferences in Harmonic Function Path Planning," in Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'09) (Saint Louis, MO, 2009).
        {Conference Proceeding }
      2009
      • S. Rajendran and M. Huber. "Generalizing and Categorizing Skills in Reinforcement Learning Agents Using Partial Policy Homomorphisms," in Proceedings of the 22nd International FLAIRS Conference (Sanibel Island, FL, 2009).
        {Conference Proceeding }
      2009
      • K. Hsiao, P. Nangeroni, M. Huber, A. Saxena, and A. Y. Ng. "Reactive Grasping Using Optical Proximity Sensors," in Proceedings of the 2009 IEEE International Conference on Robotics and Automation (ICRA'09) (Kobe, Japan, 2009).
        {Conference Proceeding }
      2009
      • P. Chiu and M. Huber. "Clustering Similar Actions in Sequential Decision Processes," in Proceedings of the 8th International Conference on Machine Learning and Applications (ICMLA'09) (Miami Beach, FL, 2009).
        {Conference Proceeding }
      2009
      • J. H. C. Staton and M. Huber. "An Assistive Navigation Paradigm Using Force Feedback," in Proceedings of the IEEE Workshop on Advanced Robotics and its Social Impacts (ARSO'09) (Tokyo, Japan, 2009).
        {Conference Proceeding }
      2009
      • S. Rajendran and M. Huber. "Learning to Generalize and Reuse Skills Using Approximate Partial Policy Homomorphisms," in Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (SMC'09) (San Antonio, TX, 2009).
        {Conference Proceeding }

      Poster Abstract 2008
      • Ramachandran, D., Maiti, A., Mwangi, G., Huber, M., Levine, D., Kamangar, F., Schoech, R., & Zaruba, G. (2008). Technology to Help Patients Adhere to Treatment Plans - A Brief Introduction to the Teleherence Project. Poster session presented at Biotechnology and Bioinformatics Symposium (BIOT'08), Arlington, TX.
        {Poster Abstract }
      2008
      • Reddy, T. S., Levine, D., Huber, M., & Ranganathan, N. (2008). BGrid - Component based Architecture for Bioinformatics on the Grid. Poster session presented at Biotechnology and Bioinformatics Symposium (BIOT'08), Arlington, TX.
        {Poster Abstract }

      Conference Proceeding 2008
      • P. Djurdjevic and M. Huber. "Learning Task Decomposition and Exploration Shaping for Reinforcement Learning Agents," in Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (SMC'08) (Singapore, 2008).
        {Conference Proceeding }
      2008
      • A. Loganathan and M. Huber. "An Approach for Behavior Discovery Using Clustering of Dynamics," in Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (SMC'08) (Singapore, 2008).
        {Conference Proceeding }
      2008
      • M. Asadi and M. Huber. "Automatic Formation of Abstract State Space Representations for Reinforcement Learning Agents," in Proceedings of the International Conference on Security and Management (SAM 2008) (Las Vegas, NV, 2008).
        {Conference Proceeding }
      2008
      • B. Holbert and M. Huber. "Design and Evaluation of Haptic Effects for the Use in a Desktop for the Physically Disabled," in Proceedings of the International Conference on Pervasive Technologies Related to Assistive Environments (PETRA'08) (Athens, Greece, 2008).
        {Conference Proceeding }
      2008
      • B. Holbert and M. Huber. "Building a Haptically Enhanced Computer Desktop for the Physically Disabled Using a Force Feedback Mouse," in Proceedings of the IASTED International Conference on Assistive Technology (AT'08) (Baltimore, MD, 2008).
        {Conference Proceeding }

      Conference Proceeding 2007
      • H. Ryu and M. Huber. "A Particle Filter Approach for Multi-Target Tracking," in Proceedings of the IEEE/RJS International Conference on Intelligent Robots and Systems (IROS'07) (San Diego, CA, 2007).
        {Conference Proceeding }
      2007
      • R. Huang, G. V. Zaruba, and M. Huber. "Complexity and Error Propagation of Localization Using Interferometric Ranging," in IEEE International Conference on Communications (ICC'07) (Glasgow, Scotland, 2007).
        {Conference Proceeding }
      2007
      • "Learning Query Reformulations for Personalized Web Search Using a Probabilistic Inference Network," in AAAI 2007 Workshop on Intelligent Techniques for Web Personalization (Vancouver, BC, Canada, 2007).
        {Conference Proceeding }
      2007
      • "Effective Control Knowledge Transfer Through Learning Skill and Representation Hierarchies," in Proceedings of the Twentieth International Joint Conference on Artificial Intelligence (IJCAI'07) (Hyderabad, India, 2007).
        {Conference Proceeding }

      Journal Article 2007
      • G. V. Zaruba, M. Huber, F. Kamangar, and I. Chlamtac. "Location Tracking Using RSSI Reading from a Single Access Point," ACM/Kluwer Journal of Wireless Networks, vol. 13, no. 2, pp. 221-235, 2007.
        {Journal Article }

      Conference Proceeding 2006
      • E. Torres-Verdin and M. Huber. "Learning Personalized Query Modifications," in Proceedings of the 19th International FLAIRS Conference (Melbourne Beach, FL, 2006).
        {Conference Proceeding }
      2006
      • A. Sabbi and M. Huber. "Particle Filter Based Object Tracking in a Stereo Vision System," in Proceedings of the IEEE International Conference on Robotics and Automation (Orlando, FL, 2006).
        {Conference Proceeding }
      2006
      • M. Asadi, V. N. Papudesi, and M. Huber. "Learning Skill and Representation Hierarchies for Effective Control Knowledge Transfer," in ICML 2005 Workshop on Structural Knowledge Transfer for Machine Learning (Pittsburgh, PA, 2006).
        {Conference Proceeding }
      2006
      • V. N. Papudesi and M. Huber. "Learning Behaviorally Grounded State Representations for Reinforcement Learning Agents," in Proceedings of the Sixth International Conference on Epigenetic Robotics (Paris, France, 2006).
        {Conference Proceeding }

      Technical Report 2005
      • Asadi, M. & Huber, M. (2005). Learning State and Action Hierarchies for Reinforcement Learning Using Autonomous Subgoal Discovery and Action-Dependent State Space Partitioning. CSE@UTA Technical Report CSE-2005-12.
        {Technical Report }

      Journal Article 2005
      • G. Zaruba, F. Kamangar, M. Huber, and D. Levine. "Connect - A Personal Remote Messaging and Monitoring System to Aid People with Disabilities," IEEE Communications, vol. 43, no. 9, pp. 101-109, 2005.
        {Journal Article }

      Conference Paper 2005
      • Asadi, M. & Huber, M. (2005). Accelerating Action Dependent Hierarchical Reinforcement Learning Through Autonomous Subgoal Discovery. Paper presented at ICML 2005 Workshop on Rich Representations for Reinforcement Learning, Bonn, Germany.
        {Conference Paper }
      2005
      • Asadi, M. & Huber, M. (2005). Hierarchical State Abstraction with Subgoal Discovery Using Learned Policies. Paper presented at International Conference on Machine Learning; Models, Technologies and Applications, Las Vegas, NV.
        {Conference Paper }
      2005
      • Rajendran, S. & Huber, M. (2005). Learning Task-Specific Sensing, Control and Memory Policies. Paper presented at International Journal on Artificial Intelligence Tools,.
        {Conference Paper }
      2005
      • Elliott, F. & Huber, M. (2005). Learning Macros with an Enhanced LZ78 Algorithm. Paper presented at Prodeedings of the 18th International FLAIRS Conference, Clearwater Beach, FL.
        {Conference Paper }
      2005
      • Grupen, R. A. & Huber, M. (2005). A Framework for the Development of Robot Behavior. Paper presented at AAAI Spring Symposium on Developmental Robotics, Stanford, CA.
        {Conference Paper }
      2005
      • Seshadri, V., Zaruba, G. V., & Huber, M. (2005). A Bayesian Sampling Approach to In-door Localization of Wireless Devices Using Received Signal Strength Indication. Paper presented at Prodeedings of the 3rd IEEE International Conference on Pervasive Computing and Communications,.
        {Conference Paper }
      2005
      • Hannon, C. J., Burnell, L. J., & Huber, M. (2005). Research to Classroom: Experiences from a Multi-Institutional Course in Smart Home Technologies. Paper presented at SIGCSE Technical Symposium on Computer Science Education, St. Louis, MI.
        {Conference Paper }
      2005
      • Asadi, M. & Huber, M. (2005). Action Dependent State Space Abstraction for Hierarchical Learning Systems. Paper presented at Prodeedings of the IASTED International Conference on Artificial Intelligence and Applications, Insbruck, Austria.
        {Conference Paper }

      Conference Paper 2004
      • Gudla S, Huber M (2004), Learning Imitation Strategies Using Cost-Based Policy Mapping and Task Rewards, In Prodeedings of the 6th IASTED International Conference on Intelligent Systems and Control, Honolulu, HI. © 2004 IASTED
        {Conference Paper }
      2004
      • Asadi M, Huber M (2004), State Space Reduction For Hierarchical Reinforcement Learning, In Proceedings of the 17th International FLAIRS Conference, pp. 509 - 514, Miami Beach, FL. © 2004 AAAI
        {Conference Paper }
      2004
      • Rajendran S, Huber M (2004), Developing Task Specific Sensing Strategies Using Reinforcement Learning, In Proceedings of the 17th International FLAIRS Conference, pp. 738 - 743, Miami Beach, FL. © 2004 AAAI
        {Conference Paper }
      2004
      • Zaruba GV, Huber M, Kamangar, FA, Chlamtac A (2004), Monte Carlo Sampling Based In-Home Location Tracking With Minimal RF Infrastructure Requirements, In Prodeedings of the 47th GlobeCom Conference, Dallas, TX. © 2004 IEEE
        {Conference Paper }
      2004
      • Papudesi VN, Huber M (2004), Interactive Refinement of Control Policies for Autonomous Robots, In Prodeedings of the 10th IASTED International Conference on Robotics and Applications, Honolulu, HI. © 2004 IASTED
        {Conference Paper }
      2004
      • Rajendran S, Huber M (2004), Learning Task-Specific Memory Policies, In Prodeedings of the 6th IASTED International Conference on Intelligent Systems and Control, Honolulu, HI. © 2004 IASTED
        {Conference Paper }

      Journal Article 2004
      • Cook DJ, Huber M, Yerraballi R, Holder LB (2004), Enhancing Computer Science Education with a Wireless Intelligent Simulation Environment, Journal of Computing in Higher Education, Vol. 16, No. 1, pp. 106-127. © 2004 Carol B. MacKnight
        {Journal Article }

      Conference Paper 2003
      • Goel S, Huber M (2003), Subgoal Discovery for Hierarchical Reinforcement Learning Using Learned Policies, In Proceedings of the 16th International FLAIRS Conference, pp. 346-350, St. Augustine, FL. © 2003 AAAI
        {Conference Paper }
      2003
      • Gudla S, Huber M (2003), Cost-Based Policy Mapping for Imitation, In Proceedings of the 16th International FLAIRS Conference, pp. 17-21, St. Augustine, FL. © 2003 AAAI
        {Conference Paper }
      2003
      • Torres FJ, Huber M (2003), Learning a Causal Model from Household Survey Data Using a Bayesian Belief Network, Transportation Research Record, No. 1836, pp. 29 - 36, (Republication of previous TRB'03 conference paper) © 2003 TRB
        {Conference Paper }
      2003
      • Papudesi VN, Wang Y, Huber M, Cook DJ (2003), Integrating User Commands and Autonomous Task Performance in a Reinforcement Learning Framework, In the AAAI Spring Symposium on Human Interaction with Autonomous Systems in Complex Environments, Stanford Univ
        {Conference Paper }
      2003
      • Torres FJ, Huber M (2003), Learning a Causal Model from Household Survey Data Using a Bayesian Belief Network, In Proceedings of the 82nd Meeting of the Transportation Research Board, Washington D.C. © 2002 UTA
        {Conference Paper }
      2003
      • Wang Y, Huber M, Papudesi VN, Cook DJ (2003), User-Guided Reinforcement Learning of Robot Assistive Tasks for an Intelligent Environment, In Proceedings of the IEEE/RJS International Conference on Intelligent Robots and Systems, Las Vegas, NV, 2003. © 20
        {Conference Paper }
      2003
      • Platt R, Brock O, Fagg AH, Karupiah D, Rosenstein M, Coelho Jr. J, Huber M, Piater J, Wheeler D, Grupen RA (2003), A Framework For Humanoid Control and Intelligence, In Proceedings of the 2003 IEEE International Conference on Humanoid Robots, Karlsruhe &
        {Conference Paper }
      2003
      • Huang R, Zaruba GV, Huber M (2003), Link Longevity Kalman-Estimator for Ad Hoc Networks, In Proceedings of the 54th IEEE Vehicular Technology Conference. © 2003 IEEE
        {Conference Paper }
      2003
      • Khawaja F, Gjoni D, Huber M, Cook DJ, Youngblood M (2003), Achieving Faster Convergence to the Optimal Policy by Using Knowledge of the Unimodal Reward Structure, In Proceedings of the IASTED International Conference on AI and Applications, Spain. © 2003
        {Conference Paper }
      2003
      • Papudesi VN, Huber M (2003), Learning from Reinforcement and Advice Using Composite Reward Functions, In Proceedings of the 16th International FLAIRS Conference, pp. 361-365, St. Augustine, FL. © 2003 AAAI
        {Conference Paper }

      Conference Paper 2002
      • Huber M, Grupen RA (2002), Robust Finger Gaits from Closed-Loop Controllers, Proceedings of the 2002 IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 1578-1584, Lausanne, Switzerland. © 2002 IEEE
        {Conference Paper }
      2002
      • Huber M (2002), Learning Hierarchical Control Policies Using Closed-Loop Actions , Proceedings of the 6th IASTED International Conference on Artificial Intelligence & Soft Computing, pp. 356-361, Banff, Alberta, Canada © 2002 IASTED
        {Conference Paper }

      Conference Paper 2000
      • Huber M (2000), A Hybrid Architecture for Hierarchical Reinforcement Learning , Proceedings of the 2000 IEEE International Conference on Robotics and Automation, pp. 3290-3295, San Francisco, CA. © 2000 IEEE
        {Conference Paper }

      Technical Report 2000
      • Huber M (2000), A Hybrid Architecture for Adaptive Robot Control, PhD thesis, University of Massachusetts at Amherst.
        {Technical Report }

      Journal Article 2000
      • Huber M, Grupen RA (2000), A Hybrid Architecture for Learning Robot Control Tasks, Robotics Today, Vol. 13, No. 4, RI/SME. © 2000 LPL
        {Journal Article }

      Conference Paper 1999
      • Huber M, Grupen RA (1999), A Hybrid Architecture for Learning Robot Control Tasks, AAAI 1999 Spring Symposium : Hybrid Systems and AI - Modeling, Analysis and Control of Discrete + Continuous Systems. Stanford University, CA.
        {Conference Paper }

      Conference Paper 1998
      • Huber M, Grupen RA (1998), Learning Robot Control - Using Control Policies as Abstract Actions, NIPS'98 Workshop : Abstraction and Hierarchy in Reinforcement Learning, Breckenridge, CO. © 1998 LPR
        {Conference Paper }
      1998
      • Coelho, Jr. JA, Araujo EG, Huber M, Grupen RA (1998), Dynamical Categories and Control Policy Selection, In Proceedings of the ISIC/CIRA/ISAS'98 Conference, Gaithersburg, MD. © 1998 IEEE
        {Conference Paper }
      1998
      • Coelho, Jr. JA, Araujo EG, Huber M, Grupen RA (1998), Contextual Control Policy Selection, Workshop on Robot Exploration and Learning/Conald'98, Pittsburgh, PA.
        {Conference Paper }
      1998
      • Huber M, Grupen RA (1998), A Control Structure for Learning Locomotion Gaits, Proceedings of the Seventh International Symposium on Robotic and Applications. © 1998 TSI Press
        {Conference Paper }
      1998
      • Huber M, MacDonald WS, Grupen RA (1996), A Control Basis for Multilegged Walking, Proceedings of the 1996 IEEE Conference on Robotics and Automation, pp. 2988-2993, Minneapolis, MN. © 1996 IEEE
        {Conference Paper }

      Conference Paper 1997
      • Huber M, Grupen RA (1997), A Feedback Control Structure for On-line Learning Tasks, Robots and Autonomous Systems, 22(3-4):303-315. © 1997 Elsevier
        {Conference Paper }
      1997
      • Huber M, Grupen RA (1997), Learning to Coordinate Controllers - Reinforcement Learning on a Control Basis , In Proceedings of the Fifteenth International Joint Conference on Artificial Intelligence, pp. 1366-1371, Nagoya, Japan. © 1997 IJCAII
        {Conference Paper }
      1997
      • Huber M, Grupen RA (1997), Prior Structure for On-line Learning , In Proceedings of CIRA'97, pp. 124-129, Monterey, CA. © 1997 IEEE
        {Conference Paper }

      Journal Article 1996
      • Huber M, Grupen RA (1996), A Hybrid Discrete Event Dynamic Systems Approach to Robot Control, UMass Computer Science technical report #96-43, October 1996.
        {Journal Article }

      Conference Paper 1995
      • raujo EG, Dakin GA, Huber M, Grupen RA (1995), Hierarchical Scheduling of Robotic Assembly Operations in a Flexible Manufacturing System, Proceedings of the 5th International Conference Flexible Automation & Intelligent Manufacturing '95, pp. 778-789, St
        {Conference Paper }

      Journal Article 1995
      • Araujo EG, Dakin GA, Huber M, Grupen RA (1995), Hierarchical Scheduling of Robotic Assembly Operations in a Flexible Manufacturing System, International Journal of Flexible Automation and Integrated Manufacturing, 3(3&4):301-316. (Republication of previo
        {Journal Article }
      1995
      • Grupen RA, Huber M, Coelho, Jr. JA , Souccar K (1995), Distributed Control of Manipulation Tasks, IEEE Expert, Special Track on Intelligent Robotic Systems, 10(2):9-14. © 1995 IEEE
        {Journal Article }

      Conference Paper 1994
      • Grupen RA, Coelho, Jr. JA, Connolly CI, Gullapalli V, Huber M, Souccar K (1994), Toward Physical Interaction and Manipulation: Screwing in a Light Bulb, AAAI 1994 Spring Symposium on Physical Interaction and Manipulation.
        {Conference Paper }

      Journal Article 1994
      • Huber M, Grupen RA (1994), 2D Contact Detection and Localization: Using Proprioceptive Information, IEEE Transactions on Robotics and Automation, 10(1):23-33. © 1994 IEEE
        {Journal Article }

      Conference Paper 1993
      • Grupen RA, Huber M (1993), 2D Contact Detection and Localization Using Proprioceptive Information, Proceedings of the 1993 IEEE Conference on Robotics and Automation, Vol.2, pp. 130-135, May 2-7, 1993.
        {Conference Paper }
      1993
      • Huber M, Grupen RA (1993), Contact Information from Proprioception, Proceedings of the Conference on Intelligent Autonomous Systems (IAS3), IOS Press, pp. 643-652, Feb. 1993.
        {Conference Paper }

      Journal Article 1992
      • Huber M, Grupen RA (1992), 2-D Contact Detection and Localization Using Proprioceptive Information, UMass Computer Science technical report #92-59, August 1992.
        {Journal Article }

Courses

      • CSE 4379-001 Unmanned Vehicle System Development

        Introduction to the technologies needed to create an UVS (Unmanned Vehicle System). Integration of these technologies (embodied as a set of sensors, actuators, computing and mobility platform sub-systems) into a functioning UVS through team work. UVS could be designed to compete in a student competition sponsored by various technical organizations or to support a specific mission or function defined by the instructors. Prerequisite: B or better in the Introduction to Unmanned Vehicle Systems course and admission to the UVS certificate program.

        Spring - Regular Academic Session - 2019 Download Syllabus Contact info & Office Hours
      • CSE 5384-001 Unmanned Vehicle System Development

        Introduction to the technologies needed to create an UVS (Unmanned Vehicle System). Integration of these technologies (embodied as a set of sensors, actuators, computing and mobility platform sub-systems) into a functioning UVS through team work. UVS could be designed to compete in a student competition sponsored by various technical organizations or to support a specific mission or function defined by the instructors. Prerequisite: B or better in the Introduction to Unmanned Vehicle Systems course and admission to the UVS certificate program.

        Spring - Regular Academic Session - 2019 Download Syllabus Contact info & Office Hours
      • CSE 6363-001 MACHINE LEARNING

        Machine learning techniques that allow computers to form representations, make predictions, or apply controls automatically from data have become increasingly prevalent in modern technologies and are opening up new approaches in a wide range of domains. This course provides an introduction to the field of Machine Learning and covers fundamental and state-of-the-art machine learning algorithms. It will cover unsupervised, supervised, semi-supervised, as well as reinforcement learning techniques with a focus on unsupervised and supervised learning. Students completing this course will gain an understanding of the area of machine learning and the ways in which different learning algorithms operate. They will also be able to apply the covered methods to real-world problems.

        Spring - Regular Academic Session - 2019 Download Syllabus Contact info & Office Hours
      • CSE 4360-001 Autonomous Robots

        This course is an introduction to Robotics from a computer science perspective and aimed at establishing the basis for the design and programming of autonomous robot systems. It covers basic kinematics, dynamics, and control as well as motion planning, sensors, and artificial intelligence techniques for robot applications. Emphasis is given to the application of these techniques to simulated and real robots. Throughout the course students will work individually and in groups to analyze robot control problems and to design hardware and software solutions. Students successfully completing this course will be able to write basic control programs for different robot platforms and to apply state-of-the-art artificial intelligence techniques to the control of robotic mechanisms.

        Fall - Regular Academic Session - 2018 Download Syllabus Contact info & Office Hours
      • CSE 4378-001 Introduction to Autonomous Vehicle Systems

        Introduction to UVS (Unmanned Vehicle Systems) such as UAS (Unmanned Aircraft Systems), UGS (Unmanned Ground System) and UMS (Unmanned Maritime System), their history, missions, capabilities, types, configurations, subsystems, and the disciplines needed for UVS development and operation. UVS missions could include student competitions sponsored by various technical organizations. This course is team-taught by engineering faculty. Prerequisite: Admission to a professional engineering or science program.

        Fall - Regular Academic Session - 2018 Download Syllabus Contact info & Office Hours
      • CSE 5383-001 Introduction to Autonomous Vehicle Systems

        Introduction to UVS (Unmanned Vehicle Systems) such as UAS (Unmanned Aircraft Systems), UGS (Unmanned Ground System) and UMS (Unmanned Maritime System), their history, missions, capabilities, types, configurations, subsystems, and the disciplines needed for UVS development and operation. UVS missions could include student competitions sponsored by various technical organizations. This course is team-taught by engineering faculty. Prerequisite: Admission to a professional engineering or science program.

        Fall - Regular Academic Session - 2018 Download Syllabus Contact info & Office Hours
      • CSE 4379-001 Unmanned Vehicle System Development

        Introduction to the technologies needed to create an UVS (Unmanned Vehicle System). Integration of these technologies (embodied as a set of sensors, actuators, computing and mobility platform sub-systems) into a functioning UVS through team work. UVS could be designed to compete in a student competition sponsored by various technical organizations or to support a specific mission or function defined by the instructors. Prerequisite: B or better in the Introduction to Unmanned Vehicle Systems course and admission to the UVS certificate program.

        Spring - Regular Academic Session - 2018 Download Syllabus Contact info & Office Hours
      • CSE 5384-001 Unmanned Vehicle System Development

        Introduction to the technologies needed to create an UVS (Unmanned Vehicle System). Integration of these technologies (embodied as a set of sensors, actuators, computing and mobility platform sub-systems) into a functioning UVS through team work. UVS could be designed to compete in a student competition sponsored by various technical organizations or to support a specific mission or function defined by the instructors. Prerequisite: B or better in the Introduction to Unmanned Vehicle Systems course and admission to the UVS certificate program.

        Spring - Regular Academic Session - 2018 Download Syllabus Contact info & Office Hours
      • CSE 6369-002 Multiagent Systems

        Multiagent systems has emerged as an important research area with applications in many fields of computer science, including artificial intelligence, e-commerce, sensor networks, distributed computing and information retrieval, information security, and robotics. In multiagent systems, multiple autonomous entities with their own objectives have to interact and make decisions. This course explores techniques for the modeling, design, decision making, and communication in these systems. While the course will focus on frameworks, methodologies, and algorithms, it will investigate (and illustrate) them in the context of a wide range of application areas, including multi-robot systems, distributed scheduling and resource allocation, sensor networks, distributed information extraction, and network security.

        Spring - Regular Academic Session - 2018 Download Syllabus Contact info & Office Hours
      • CSE 4360-001 ROBOTICS

        This course is an introduction to Robotics from a computer science perspective and aimed at establishing the basis for the design and programming of autonomous robot systems. It covers basic kinematics, dynamics, and control as well as motion planning, sensors, and artificial intelligence techniques for robot applications. Emphasis is given to the application of these techniques to simulated and real robots. Throughout the course students will work individually and in groups to analyze robot control problems and to design hardware and software solutions. Students successfully completing this course will be able to write basic control programs for different robot platforms and to apply state-of-the-art artificial intelligence techniques to the control of robotic mechanisms.

        Fall - Regular Academic Session - 2017 Download Syllabus Contact info & Office Hours
      • CSE 5364-001 ROBOTICS

        This course is an introduction to Robotics from a computer science perspective and aimed at establishing the basis for the design and programming of autonomous robot systems. It covers basic kinematics, dynamics, and control as well as motion planning, sensors, and artificial intelligence techniques for robot applications. Emphasis is given to the application of these techniques to simulated and real robots. Throughout the course students will work individually and in groups to analyze robot control problems and to design hardware and software solutions. Students successfully completing this course will be able to write basic control programs for different robot platforms and to apply state-of-the-art artificial intelligence techniques to the control of robotic mechanisms.

        Fall - Regular Academic Session - 2017 Download Syllabus Contact info & Office Hours
      • CSE 4378-001 INTRODUCTION TO UNMANNED VEHICLE SYSTEMS

        Introduction to UVS (Unmanned Vehicle Systems) such as UAS (Unmanned Aircraft Systems), UGS (Unmanned Ground System) and UMS (Unmanned Maritime System), their history, missions, capabilities, types, configurations, subsystems, and the disciplines needed for UVS development and operation. UVS missions could include student competitions sponsored by various technical organizations. This course is team-taught by engineering faculty. Prerequisite: Admission to a professional engineering or science program.

        Fall - Regular Academic Session - 2017 Download Syllabus Contact info & Office Hours
      • CSE 5383-001 INTRODUCTION TO UNMANNED VEHICLE SYSTEMS

        Introduction to UVS (Unmanned Vehicle Systems) such as UAS (Unmanned Aircraft Systems), UGS (Unmanned Ground System) and UMS (Unmanned Maritime System), their history, missions, capabilities, types, configurations, subsystems, and the disciplines needed for UVS development and operation. UVS missions could include student competitions sponsored by various technical organizations. This course is team-taught by engineering faculty. Prerequisite: Admission to a professional engineering or science program.

        Fall - Regular Academic Session - 2017 Download Syllabus Contact info & Office Hours
      • CSE 4379-001 Unmanned Vehicle System Development

        Introduction to the technologies needed to create an UVS (Unmanned Vehicle System). Integration of these technologies (embodied as a set of sensors, actuators, computing and mobility platform sub-systems) into a functioning UVS through team work. UVS could be designed to compete in a student competition sponsored by various technical organizations or to support a specific mission or function defined by the instructors. Prerequisite: B or better in the Introduction to Unmanned Vehicle Systems course and admission to the UVS certificate program.

        Spring - Regular Academic Session - 2017 Download Syllabus Contact info & Office Hours
      • CSE 5384-001 Unmanned Vehicle System Development

        Introduction to the technologies needed to create an UVS (Unmanned Vehicle System). Integration of these technologies (embodied as a set of sensors, actuators, computing and mobility platform sub-systems) into a functioning UVS through team work. UVS could be designed to compete in a student competition sponsored by various technical organizations or to support a specific mission or function defined by the instructors. Prerequisite: B or better in the Introduction to Unmanned Vehicle Systems course and admission to the UVS certificate program.

        Spring - Regular Academic Session - 2017 Download Syllabus Contact info & Office Hours
      • CSE 5301-001 DATA ANALYSIS & MODELING TECHNIQUES

        With Computer Science moving into applications in the real world and involving large quantities of data, uncertainty and random variations become increasingly important aspects to be considered when designing algorithms, addressing large scale problems, modeling processes, or evaluating data. To do this, probabilistic methods for data analysis and modeling become essential tools within every branch of Computer Science.

        This course briefly covers basic statistics and probability concepts and introduces techniques to model and analyze probabilistic data. This includes basic representation such as Bayesian networks as well as hypothesis testing techniques for data analysis and interpretation. Further, it introduces modeling and analysis techniques for sequential processes, including Markov models, regression analysis, and basic queueing models. All of these techniques will be discussed in the context of common Computer Science problems from a wide range of fields, including Computer Networks, Artificial Intelligence, Machine Learning, Computer Vision, Data Mining, Bioinformatics, etc. In addition, the course will discus selected advanced topics and applications such as capacity planning and bottleneck analysis, clustering and classification

        Students successfully completing this course will have gained a solid understanding of probabilistic data modeling, interpretation, and analysis an thus have formed an important basis for more advanced courses in Computer Science as well as for the handling and analysis of data used in real-life applications and research.

        Spring - Regular Academic Session - 2017 Download Syllabus Contact info & Office Hours
      • CSE 4378-001 INTRODUCTION TO UNMANNED VEHICLE SYSTEMS

        Introduction to UVS (Unmanned Vehicle Systems) such as UAS (Unmanned Aircraft Systems), UGS (Unmanned Ground System) and UMS (Unmanned Maritime System), their history, missions, capabilities, types, configurations, subsystems, and the disciplines needed for UVS development and operation. UVS missions could include student competitions sponsored by various technical organizations. This course is team-taught by engineering faculty. Prerequisite: Admission to a professional engineering or science program.

        Fall - Regular Academic Session - 2016 Download Syllabus Contact info & Office Hours
      • CSE 5383-001 INTRODUCTION TO UNMANNED VEHICLE SYSTEMS

        Introduction to UVS (Unmanned Vehicle Systems) such as UAS (Unmanned Aircraft Systems), UGS (Unmanned Ground System) and UMS (Unmanned Maritime System), their history, missions, capabilities, types, configurations, subsystems, and the disciplines needed for UVS development and operation. UVS missions could include student competitions sponsored by various technical organizations. This course is team-taught by engineering faculty. Prerequisite: Admission to a professional engineering or science program.

        Fall - Regular Academic Session - 2016 Download Syllabus Contact info & Office Hours
      • CSE 4360-001 Autonomous Robots

        This course is an introduction to Robotics from a computer science perspective and aimed at establishing the basis for the design and programming of autonomous robot systems. It covers basic kinematics, dynamics, and control as well as motion planning, sensors, and artificial intelligence techniques for robot applications. Emphasis is given to the application of these techniques to simulated and real robots. Throughout the course students will work individually and in groups to analyze robot control problems and to design hardware and software solutions. Students successfully completing this course will be able to write basic control programs for different robot platforms and to apply state-of-the-art artificial intelligence techniques to the control of robotic mechanisms.

        Fall - Regular Academic Session - 2016 Download Syllabus Contact info & Office Hours
      • CSE 5364-001 Autonomous Robots

        This course is an introduction to Robotics from a computer science perspective and aimed at establishing the basis for the design and programming of autonomous robot systems. It covers basic kinematics, dynamics, and control as well as motion planning, sensors, and artificial intelligence techniques for robot applications. Emphasis is given to the application of these techniques to simulated and real robots. Throughout the course students will work individually and in groups to analyze robot control problems and to design hardware and software solutions. Students successfully completing this course will be able to write basic control programs for different robot platforms and to apply state-of-the-art artificial intelligence techniques to the control of robotic mechanisms.

        Fall - Regular Academic Session - 2016 Download Syllabus Contact info & Office Hours
      • CSE 4379-001 Unmanned Vehicle System Development

        Introduction to the technologies needed to create an UVS (Unmanned Vehicle System). Integration of these technologies (embodied as a set of sensors, actuators, computing and mobility platform sub-systems) into a functioning UVS through team work. UVS could be designed to compete in a student competition sponsored by various technical organizations or to support a specific mission or function defined by the instructors. Prerequisite: B or better in the Introduction to Unmanned Vehicle Systems course and admission to the UVS certificate program.

        Spring - Regular Academic Session - 2016 Download Syllabus Contact info & Office Hours
      • CSE 5384-001 Unmanned Vehicle System Development

        Introduction to the technologies needed to create an UVS (Unmanned Vehicle System). Integration of these technologies (embodied as a set of sensors, actuators, computing and mobility platform sub-systems) into a functioning UVS through team work. UVS could be designed to compete in a student competition sponsored by various technical organizations or to support a specific mission or function defined by the instructors. Prerequisite: B or better in the Introduction to Unmanned Vehicle Systems course and admission to the UVS certificate program.

        Spring - Regular Academic Session - 2016 Download Syllabus Contact info & Office Hours
      • CSE 4378-001 INTRODUCTION TO UNMANNED VEHICLE SYSTEMS

        Introduction to UVS (Unmanned Vehicle Systems) such as UAS (Unmanned Aircraft Systems), UGS (Unmanned Ground System) and UMS (Unmanned Maritime System), their history, missions, capabilities, types, configurations, subsystems, and the disciplines needed for UVS development and operation. UVS missions could include student competitions sponsored by various technical organizations. This course is team-taught by engineering faculty. Prerequisite: Admission to a professional engineering or science program.

        Fall - Regular Academic Session - 2015 Download Syllabus Contact info & Office Hours
      • CSE 5383-001 INTRODUCTION TO UNMANNED VEHICLE SYSTEMS

        Introduction to UVS (Unmanned Vehicle Systems) such as UAS (Unmanned Aircraft Systems), UGS (Unmanned Ground System) and UMS (Unmanned Maritime System), their history, missions, capabilities, types, configurations, subsystems, and the disciplines needed for UVS development and operation. UVS missions could include student competitions sponsored by various technical organizations. This course is team-taught by engineering faculty. Prerequisite: Admission to a professional engineering or science program.

        Fall - Regular Academic Session - 2015 Download Syllabus Contact info & Office Hours
      • CSE 6369-001 Special Topics in Advanced Intelligent Systems: Reasoning with Uncertainty

        This course explores modern reasoning techniques for the extraction of information from noisy data sources, for the integration of multiple information streams, and for decision-making in the presence of uncertainty. While this course will investigate these techniques often in the context of physical sensor applications and robotics, they are also applicable in a wide range of other fields including mobile networking, data mining, and control of physical processes. Students completing this course will gain an understanding of advanced methods to work with uncertain data and be able to apply them to real world problems.

        Fall - Regular Academic Session - 2015 Download Syllabus Contact info & Office Hours
      • CSE 6363-001 MACHINE LEARNING

        Machine learning techniques that allow computers to form representations, make predictions, or apply controls automatically from data have become increasingly prevalent in modern technologies and are opening up new approaches in a wide range of domains. This course provides an introduction to the field of Machine Learning and covers fundamental and state-of-the-art machine learning algorithms. It will cover unsupervised, supervised, semi-supervised, as well as reinforcement learning techniques with a focus on unsupervised and supervised learning. Students completing this course will gain an understanding of the area of machine learning and the ways in which different learning algorithms operate. They will also be able to apply the covered methods to real-world problems.

        Fall - Regular Academic Session - 2015 Download Syllabus Contact info & Office Hours
      • CSE 4317-003 Senior Design II

        This course is the second part of the two semester capstone class. The purpose of this class is to provide a "close to real world" experience in developing real products, the right way. Students in this course will learn a lot about the development process and discover some interesting things about themselves as a member of a development team along the way! This is the CSE capstone course, where many of the things learned in previous courses are put together before students tackle the real world. The course will study the product development environment used in the computer industry, and practice a phased system/software development process, often called the modified-Waterfall system development life cycle, as applied to computer hardware and software design projects. Throughout this course sequence, students will work on teams of 4-5 students. In this first course in the sequence (CSE 4316) students will identify their team and their project and start the planning process. Within this second semester, students will continue and complete, through demonstration of a working prototype, the project started in the previous semester in the same team.

        Spring - Regular Academic Session - 2015 Download Syllabus Contact info & Office Hours
      • CSE 4379-001 Unmanned Vehicle System Development

        Introduction to the technologies needed to create an UVS (Unmanned Vehicle System). Integration of these technologies (embodied as a set of sensors, actuators, computing and mobility platform sub-systems) into a functioning UVS through team work. UVS could be designed to compete in a student competition sponsored by various technical organizations or to support a specific mission or function defined by the instructors. Prerequisite: B or better in the Introduction to Unmanned Vehicle Systems course and admission to the UVS certificate program.

        Spring - Regular Academic Session - 2015 Download Syllabus Contact info & Office Hours
      • CSE 5384-001 Unmanned Vehicle System Development

        Introduction to the technologies needed to create an UVS (Unmanned Vehicle System). Integration of these technologies (embodied as a set of sensors, actuators, computing and mobility platform sub-systems) into a functioning UVS through team work. UVS could be designed to compete in a student competition sponsored by various technical organizations or to support a specific mission or function defined by the instructors. Prerequisite: B or better in the Introduction to Unmanned Vehicle Systems course and admission to the UVS certificate program.

        Spring - Regular Academic Session - 2015 Download Syllabus Contact info & Office Hours
      • CSE 4378-001 Introduction to Unmanned Vehicle Systems

        Introduction to UVS (Unmanned Vehicle Systems) such as UAS (Unmanned Aircraft Systems), UGS (Unmanned Ground System) and UMS (Unmanned Maritime System), their history, missions, capabilities, types, configurations, subsystems, and the disciplines needed for UVS development and operation. UVS missions could include student competitions sponsored by various technical organizations. This course is team-taught by engineering faculty. Prerequisite: Admission to a professional engineering or science program.

        Fall - Regular Academic Session - 2014 Download Syllabus Contact info & Office Hours
      • CSE 5383-001 Introduction to Unmanned Vehicle Systems

        Introduction to UVS (Unmanned Vehicle Systems) such as UAS (Unmanned Aircraft Systems), UGS (Unmanned Ground System) and UMS (Unmanned Maritime System), their history, missions, capabilities, types, configurations, subsystems, and the disciplines needed for UVS development and operation. UVS missions could include student competitions sponsored by various technical organizations. This course is team-taught by engineering faculty. Prerequisite: Admission to a professional engineering or science program.

        Fall - Regular Academic Session - 2014 Download Syllabus Contact info & Office Hours
      • CSE 4316-003 Senior Design I

        Analysis and design of an industry-type project that involves hardware and software components to meet desired needs within realistic constraints and standards. The project is to be completed in CSE 4317 the following semester. Multidisciplinary teams of CSE 4316 students are required to develop, review, and present problem definition, project planning, requirements formulation, and design specification. Corequisite: CSE 4314 Prerequisites: CSE 3310, CSE 3320, and for CpE Majors CSE 3442.

        Fall - Regular Academic Session - 2014 Download Syllabus Contact info & Office Hours
      • CSE 5364-001 Robotics

        This course is an introduction to Robotics from a computer science perspective and aimed at establishing the basis for the design and programming of autonomous robot systems. It covers basic kinematics, dynamics, and control as well as motion planning, sensors, and artificial intelligence techniques for robot applications. Emphasis is given to the application of these techniques to simulated and real robots. Throughout the course students will work individually and in groups to analyze robot control problems and to design hardware and software solutions. Students successfully completing this course will be able to write basic control programs for different robot platforms and to apply state-of-the-art artificial intelligence techniques to the control of robotic mechanisms.

        Spring - Regular Academic Session - 2014 Download Syllabus Contact info & Office Hours
      • CSE 6369-001 Reinforcement Learning

        Machine learning techniques are increasingly employed in a wide range of areas to model and analyze data as well as to facilitate decision support and autonomous decision making by computer systems. Reinforcement learning is an important machine learning paradigm in particular in the context of decision support and decision making, but also in the context of modeling when only limited feedback is available. This course will introduce the Reinforcement Learning paradigm and its underlying formalisms, and will cover a wide range of basic and advanced Reinforcement Learning algorithms as well as aspects of model learning, hierarchy and abstraction, and reward modeling. Throughout, this course will study these techniques in the context of a wide range of application areas, including robotics, computer vision, security, control, scheduling, and data analysis. Students completing this course will gain an understanding of the field and be able to apply modern, state-of-the-art Reinforcement Learning techniques to a wide range of problems and applications.

        Spring - Regular Academic Session - 2014 Download Syllabus Contact info & Office Hours
      • CSE 4360-001 AUTONOMOUS ROBOT DESIGN AND PROGRAMMING

        This course is an introduction to Robotics from a computer science perspective and aimed at establishing the basis for the design and programming of autonomous robot systems. It covers basic kinematics, dynamics, and control as well as motion planning, sensors, and artificial intelligence techniques for robot applications. Emphasis is given to the application of these techniques to simulated and real robots. Throughout the course students will work individually and in groups to analyze robot control problems and to design hardware and software solutions. Students successfully completing this course will be able to write basic control programs for different robot platforms and to apply state-of-the-art artificial intelligence techniques to the control of robotic mechanisms.

        Spring - Regular Academic Session - 2014 Download Syllabus Contact info & Office Hours
      • CSE 4308-001 Cse 4308-001

        This course gives an introduction to the philosophies and techniques of Artificial Intelligence. AI techniques have become an essential element in modern computer software and are thus essential for a successful career and advanced studies in computer science. Students successfully completing this course will be able to apply a variety of techniques for the design of efficient algorithms for complex problems. Topics covered in this course include search algorithms (such as breadth-first, depth-first, A*), game-playing algorithms (such as Minimax), knowledge and logic reasoning, planning methods (such as STRIPS and Partially Ordered Planner), probabilistic reasoning, and machine learning.

        Fall - Regular Academic Session - 2013 Download Syllabus Contact info & Office Hours
      • CSE 5360-001 Cse 5360-001

        This course gives an introduction to the philosophies and techniques of Artificial Intelligence. AI techniques have become an essential element in modern computer software and are thus essential for a successful career and advanced studies in computer science. Students successfully completing this course will be able to apply a variety of techniques for the design of efficient algorithms for complex problems. Topics covered in this course include search algorithms (such as breadth-first, depth-first, A*), game-playing algorithms (such as Minimax), knowledge and logic reasoning, planning methods (such as STRIPS and Partially Ordered Planner), probabilistic reasoning, and machine learning.

        Fall - Regular Academic Session - 2013 Download Syllabus Contact info & Office Hours
      • CSE 5364-001 ROBOTICS
        This course is an introduction to Robotics from a computer science perspective and aimed at establishing the basis for the design and programming of autonomous robot systems. It covers basic kinematics, dynamics, and control as well as motion planning, sensors, and artificial intelligence techniques for robot applications. Emphasis is given to the application of these techniques to simulated and real robots. Throughout the course students will work individually and in groups to analyze robot control problems and to design hardware and software solutions. Students successfully completing this course will be able to write basic control programs for different robot platforms and to apply state-of-the-art artificial intelligence techniques to the control of robotic mechanisms.
        Spring - Regular Academic Session - 2013 Download Syllabus 1 Link
      • CSE 4309-001 ARTIFICIAL INTELLIGENCE II
        This course introduces and applies the AI techniques necessary for an agent to act intelligently in the ``real'' world. Techniques include uncertainty reasoning, learning, natural language processing, vision and speech processing. Basic AI techniques will be reviewed in the context of the Java programming language which will be used for implementing the more advanced techniques. Emphasis will be on implementation and experimentation with the goal of building robust intelligent agents.
        Spring - Regular Academic Session - 20131 Link
      • CSE 4360-001 AUTONOMOUS ROBOT DESIGN AND PROGRAMMING
        This course is an introduction to Robotics from a computer science perspective and aimed at establishing the basis for the design and programming of autonomous robot systems. It covers basic kinematics, dynamics, and control as well as motion planning, sensors, and artificial intelligence techniques for robot applications. Emphasis is given to the application of these techniques to simulated and real robots. Throughout the course students will work individually and in groups to analyze robot control problems and to design hardware and software solutions. Students successfully completing this course will be able to write basic control programs for different robot platforms and to apply state-of-the-art artificial intelligence techniques to the control of robotic mechanisms.
        Spring - Regular Academic Session - 2013 Download Syllabus 1 Link
      • CSE 5361-001 ARTIFICIAL INTELLIGENCE II
        This course introduces and applies the AI techniques necessary for an agent to act intelligently in the ``real'' world. Techniques include uncertainty reasoning, learning, natural language processing, vision and speech processing. Basic AI techniques will be reviewed in the context of the Java programming language which will be used for implementing the more advanced techniques. Emphasis will be on implementation and experimentation with the goal of building robust intelligent agents.
        Spring - Regular Academic Session - 20131 Link