Kartik Talamadupula
Homepage

 

Current Work

 

My current work centers around a human-robot interaction scenario. In specific, we are trying to solve the problem of having a high-level task-planner that performs reasoning based on the closed-world assumption (CWA) control and plan for a robot that has to act in an open world. The robot that we plan for is a rescue robot that goes into buildings that are deemed unsafe for human actors and reports the locations of valuable assets (e.g. injured humans).


I have also been working on an unrelated project in temporal planning. The problem at hand has to do with finding a suitably informed heuristic for temporally expressive planning (as defined over the past few years in the planning community). My interest in temporally expressive planning stems from my early work as an undergraduate (alongwith William Cushing) on required concurrency.

 

Publications

 

Integrating a Closed World Planner with an Open World Robot: A Case Study
[pdf] [slideshow] (MS Office 2007+ only)

K. Talamadupula, J. Benton, P. Schermerhorn, S. Kambhampati, M. Scheutz.

ICAPS 2009 Workshop on Bridging the Gap Between Task and Motion Planning.

Also accepted to the ICAPS 2009 Doctoral Consortium [pdf]

 

Finding and Exploiting Goal Opportunities in Real-time during Plan Execution [pdf]

P. Schermerhorn, J. Benton, M. Scheutz, K. Talamadupula, S. Kambhampati.

In the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Presented by Paul Schermerhorn.

 

A Heuristic for Soft Deadline Goals

J. Benton, Kartik Talamadupula, Subbarao Kambhampati.

In the ICAPS 2008 Doctoral Consortium. Presented by J. Benton.

 

Evaluating Temporal Planning Domains [pdf]

William Cushing, Daniel S. Weld, Mausam, Subbarao Kambhampati, Kartik Talamadupula.

In Proceedings of the 17th International Conference on Automated Planning & Scheduling.

Presented by William Cushing.

Also in the ICAPS 2007 Workshop on the International Planning Competition.

 

Erdös Number

 

My Erdös Number is 5 (as far as MathSciNet is accurate and recently updated). If you think it should be lower, please let me know. If you know how to make it lower, I'll contact you.

 

Subbarao Kambhampati -> Dana Nau -> George Markowsky -> Daniel Kleitman -> Paul Erdös