1. Rajendran S., Huber M., Developing Task-Specific Sensing Strategies Using Reinforcement Learning,In Proceedings of the 17th International FLAIRS Conference, Miami Beach, FL, pp 738-743, © 2004 AAAI Press.
   
   Abstract:Robots that can adapt and perform multiple tasks promise to be a powerful tool with many applications. In order to achieve such robots, control systems have to be constructed that have the capability to handle real world situations. Robots use sensors to interact with the world. Processing the raw data from these sensors becomes computationally intractable in real time. This problem can be tackled by learning mechanisms for focus of attention. This paper presents an approach that considers focus of attention as a problem of selecting controller and feature pairs to be processed at any given point of time in order to optimize system performance. The result is a control and sensing policy that is task specific and can adapt to real world situations using feedback from the world. The approach is illustrated using a number of different tasks in a blocks world domain. Download : (,)
   
   
2. Rajendran S., Huber M., Learning Task-Specific Memory Policies, In Proceedings of the 6th IASTED International Conference on Intelligent Systems and Control, Honolulu, Hawaii, pp 238-243. © 2004 IASTED.
   
   Abstract:Effective AI agents and robots require the ability to adapt to real world situations and perform multiple tasks. This requires them to take into account the important sensory information. Extraction of this information can be made tractable using mechanisms of focus of attention that select perceptual features that have to be processed. This mechanism alone however is inadequate for tasks in real world situations since it still requires the robot to maintain all past information, rendering decision making computationally intractable. This requires the robots and AI agents to have the capability to remember only the past events that are required for successful completion of a task. Here we present an approach (illustrated using block stacking and block copying tasks) that extends a previous focus of attention mechanism by incorporating short term memory to remember past events. The result is a task-specific control, sensing, and memory policy. Download : (,)
   
   

Journal Papers:

1. Rajendran S., Huber M., Learning Task-Specific Sensing, Control and Memory Policies, In International Journal on Artificial Intelligence Tools, Vol 14, No 1-2 (2005), pp 303-327. © 2005 World Scientific Publishing.
   

   Abstract: AI agents and robots that can adapt and handle multiple tasks in real time promise to be a powerful tool. To address the control challenges involved in such systems, the underlying control approach has to take into account the important sensory information. Modern sensors, however,can generate huge amounts of data, rendering the processing and representation of all sensor data in real time computationally intractable. This issue can be addressed by developing task-specific focus of attention strategies that limit the sensory data that is processed at any point in time to the data relevant for the given task. Alone, however, this mechanism is not adequate for solving complex tasks since the robot also has to maintain selected pieces of past information. This necessitates AI agents and robots to have the capability to remember significant past events that are required for task completion. This paper presents an approach that considers focus of attention as a problem of selecting controller and feature pairs to be processed at a given point in time to optimize the system performance. This approach is further extended by incorporating short term memory and a learned memory management policy. The result is a system that learns control, sensing, and memory policies that are task-specific and adaptable to real world situations using the feedback from the world in a reinforcement learning framework. The approach is illustrated using table cleaning, sorting, stacking, and copying tasks in the blocks world domain. Download - Not final version : (,)

Masters Thesis:

1. Rajendran S., Developing Focus of Attention Strategies using Reinforcement Learning, M.S. Thesis (UTA-CSE Technical Report No. CSE-2003-32), © 2003 Computer Science and Engineering, University of Texas at Arlington. ADVISOR: Dr. Manfred Huber
   
   Abstract:Robot and AI agents that can adapt and handle multiple tasks are the need of today. This requires them to have the capability to handle real world situations. Robots use sensors to interact with the world. Processing the raw data from these sensors becomes computationally intractable in real time. This problem can be addressed by learning strategies of focus of attention. This thesis presents an approach that considers focus of attention as a reinforcement learning problem of selecting controller and feature pairs to be processed at any given point in time. The result is a sensing and control policy that is task specific and can adapt to real world situations using the feedback from the world.

   Handling all the information of the world for the successful completion of a task is computationally intractable. In order to resolve this, the current approach is further augmented with short term memory. This enables the agent to learn a memory policy. The memory policy tells the agent what to remember and when to remember in order to successfully complete a task. The approach is illustrated using a number of tasks in the blocks world domain. Download : ( , )
   

Posters:

1. A visually presented extension of the DRM paradigm: Incidence of false memories in truth or lie conditions with observer judgments of participant responses. © 2005 Department of Psychology, University of Texas at Arlington.(Presented for the class of Theories of Human Learning and Memory -Spring 2005).

   ADVISOR:Dr.Valerie F. Reyna

   Authors: Srividhya Rajendran, Matthew Banks, Heather Bassuk, Mike Blevins, Shannon Blevins, Kyle Bryan, Edie Jauregui,Trang Le, Marie Oum, Phuong Phan, Neelam Rawal, Kristi Rhodes,Cres Salazar, Demetrius Salter, and Roger Wesson. (I would like to thank Dr.Timothy Odegard who extended his help whenever we needed it.)

   Abstract:This experiment was designed to measure the mean proportion of test words accepted as "seen" in truth and lie conditions of recognition testing. This was lowest for unrelated distractors, and highest for targets and criticallures. There was no significant effect of order of presented words, gender, or age on participants' memoryrecognition. The experiment was an extension of Deese, Roedgier, and McDermott's (1995) paradigm to measure false memory. A truth or lie condition was added to the recognition test in which subjects were instructed to tell the truth in indicated "truth" sessions or convincingly lie during "lie" sessions testing recognition of previously studied words. We found that observers were more likely to judge the participants as telling the truth than telling a lie or experiencing a false memory for target words and critical lures. Results and implication of this study will be discussed and future research directions will be highlighted. Download : ( , ) ( Photo of the people in the group)
   

Resume : ( )

Personal Info, Blogs, Ph.D. Milestones Completed, Research Related Papers

No of Visitors :

© 2007 Srividhya Rajendran