Nikhil Karnad's research page

Modeling Human Motion Patterns for Multi-Robot Planning
Nikhil Karnad and Volkan Isler



Accepted for publication: Nikhil Karnad and Volkan Isler. Modeling Human Motion Patterns for Multi-Robot Planning. In Proceedings of ICRA 2012. NOTE: To appear.

Energy-Optimal Velocity Profiles for Car-Like Robots
Pratap Tokekar, Nikhil Karnad, and Volkan Isler



Publication: P. Tokekar, N. Karnad, and V. Isler. Energy-Optimal Velocity Profiles for Car-Like Robots. In Proc. IEEE Int. Conf. on Robotics and Automation - ICRA 2011. pp. 1457-1462.

A Multi-Robot System for Unconfined Video-Conferencing
Nikhil Karnad and Volkan Isler

Telepresence or tele-immersion technologies allow people to attend a shared meeting without being physically present in the same location. Commercial telepresence solutions available in the market today have significant drawbacks - they are very expensive, and confine people to the area covered by stationary cameras. In this paper, we present a mobile tele-immersion platform that addresses these issues by using robots with embedded cameras. In our system, the users can move around freely because robots autonomously adjust their locations. We provide a geometric definition of what it means to get a good view of the user, and present control algorithms to maintain a good view. The algorithms are validated both in simulation and in real experiments.

Publication: Nikhil Karnad and Volkan Isler. A multi-robot system for unconfined video-conferencing. In Proceedings of ICRA 2010. pp.356-361. Link More details on our Wiki

Guarding a circular obstacle
Nikhil Karnad and Volkan Isler

We study a new version of the Lion and Man game played in a Euclidean environment with a circular obstacle. We present a complete characterization of the game: for each player, we derive necessary and sufficient conditions for winning the game. Their (continuous time) strategies are constructed using techniques from differential games and arguments from geometry. Our main result is a decision algorithm which takes arbitrary initial positions as input, declares one of the players as the winner of the game and outputs a winning strategy for that player. We extend our approach to explicitly construct, in closed form, the decision boundary that partitions the arena into win and lose regions.

Publication: N. Karnad and V. Isler. Lion and Man Game in the Presence of a Circular Obstacle. In Proceedings of the 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems at St. Louis, Missouri, USA. pp.5045-5050. 2009. Technical Report

Efficient Strategies for Collecting Data from Wireless Sensor Network Nodes using Mobile Robots
Onur Tekdas, Nikhil Karnad, Volkan Isler

This work focuses on systems where mobile robots periodically collect data from (static) wireless sensor network nodes. We present solutions to the following problems.

• From the static node's perspective: given the stochastic nature of the robot's arrival, what is an energy-efficient strategy to wake up and send/receive beacon messages? Such a strategy must simultaneously minimize the robot's waiting time and the number of beacon messages.
• From the robot's perspective: given the stochastic nature of the wireless link quality, what is an energy-efficient motion strategy to find a good pose (location and orientation) from where the data can be downloaded efficiently?

Publication: O. Tekdas, N. Karnad and V. Isler. Efficient Strategies for Collecting Data from Wireless Sensor Network Nodes using Mobile Robots. ISRR 2009: 14th International Symposium on Robotics Research. Lucerne, Switzerland. To appear. Link

Indoor Mobile Robot Localization with a Single Camera
Onur Tekdas and Nikhil Karnad

For a mobile robot navigating in an indoor environment, we use the Kalman Filter to fuse sensory data from the vision system and the wheel odometers to estimate the motion parameters of the robot. Motion parameters were extracted by first matching SIFT features over consecutive images, followed by RANSAC to find the best fit fundamental matrix. Using this approach, the rotation and translation of the camera attached to the robot frame can be extracted and then fused with the odometer readings for a combined estimate.

Submitted as a final project for CSci 5561: Computer Vision under the guidance of Dr. Paul Schrater. Other course projects include: 3-D reconstruction of facial images from illumination data, and Wide-baseline 3-D reconstruction of a house scene from two images.

Bearing-Only pursuit
We study a variant of the well-known Lion-and-Man game, motivated by mobile robots with monocular vision systems. We restrict the lion to a bearing-only sensing measurement and show that he can get to within the step-size distance (discrete-time) from the man. However, the man is able to avoid exact capture.

Publication: N. Karnad and V. Isler. Bearing-Only Pursuit. Proc. IEEE Int. Conf. on Robotics and Automation (ICRA). Pages 2665-2670. Pasadena, CA. May 2008. Link

Reduced visibility in the Cops and Robbers Game
We investigate the role of the information available to the players on the outcome of the cops and robbers game played in turns on a graph. On the positive side, we show that a cop with small or no visibility can capture the robber on any cop-win graph. On the negative side, we show that the reduction in cop’s visibility can result in an exponential increase in the capture time. We provide an analysis of the symmetric visibility case and present an algorithmic characterization for graphs on which greedy pursuit is sufficient for capture.

Publication: V. Isler and N. Karnad. The role of information in the cop-robber game. Theoretical Computer Science (Elsevier). Volume 399 (3). Pages 179-190. June 2008. Link

Nearest-neighbor search in higher dimensions
Research intern project at Microsoft Research, Bangalore, India (MSRI) with Dr. Manik Varma. Studied the applicability of k-D trees for nearest-neighbor search on data sets with applications in texture classification.

Self-Organization applied to Euclidean Steiner Minimal Trees
We used a self-organization approach with gradient descent to rearrange an initial tree to a Steiner tree. Further developed methods to generate good initial configurations, achieving an improvement from 1% up to 10% in tree length.

A. S. Mandal and N. Karnad. Generation of Euclidean Steiner Minimal Trees using Modified Neural Self-Organization Approach. Submitted to IEEE VLSI Design and Test Symposium (VDAT). India. 2008.