Qualification: 
M.Tech
aa_nippunkumaar@blr.amrita.edu

Nippun Kumaar A. A.  currently serves as Assistant Professor (Sr.Gr) at department of Computer Science,Amrita School of Engineering. He is currently pursuing his PhD in the area of Service Robotic in Amrita Robotic Research Center (ARRC). Doctoral thesis titled as "Navigation techniques for Mobile Service Robotics" in an indoor environment.

Qualification

YEAR DEGREE/PROGRAM INSTITUTION
2011 M. Tech Embedded Systems Amrita School of Engineeirng, Bengaluru
2009 B. E. Electronics and Communication Engineering Sona College of Technology, Salem
2006 Diploma in Electronics and Communication Engineering Thiagarajar Polytechnic College, Salem

Research Projects

  • Design and Development of Anthropomorphic arm
  • Design and Fabrication of Scara Based Universal Gripper Robot
  • Automatic Identification of Coffee White Stem Borer
  • Coordination of Industrial Manipulators
  • Design and Fabrication of Hexapod
  • State Based Obstacle Avoidance Algorithm
  • Mobile Robot Programming by Demonstration/li>
  • Unmanned Ground Vehicle using Neural Networks
  • Dynamic stability algorithm for a Hexapod Robot
  • Cloth Folding Manipulator
  • QR Code Based Indoor Mobile Robot Navigation
  • Autonomous Micro Quadcopter
  • Fast Detection of Produce for Harvesting
  • Smart Invigilation Assistant

Professional Activities

  • IEEE Member
  • IEEE RAS Bangalore Section, Execom Member
  • IEEE RAS Amrita School of Engineering, Bangalore, SBC, Mentor

Publications

Publication Type: Conference Paper

Year of Publication Title

2019

B. Reddy and Nippun Kumaar A A, “Indoor Mobile Robot Path Planning Using QR Code”, in International Conference on Communication, Computing and Electronics Systems, 2019, pp. 681-693.[Abstract]


Mobile robots are extensively used in service-based environments like warehouses, hotels, hospitals, restaurants etc. Path planning to reach destination from a source is a crucial task for any mobile robot. An idle path planning algorithm given a source and destination, should plan a shortest path with less computation time autonomously. In this work Quick Response (QR) code is used as via point/landmark in the environment. QR code is a 2D barcode which stores more data than a traditional barcode system. Path matrix which contains navigation in- formation to reach nearby via points or destinations is stored in QR code. These QR codes are placed on the floor strategically, such that given a destination, a mobile robot can navigate in a shortest route possible without any overall environment information. The proposed system is implemented and tested using an in-house built omni directional mobile robot powered by BeagleBone Black. The obtained results proves that the mobile robot is able to reach its destination point accurately.

More »»

2019

Sachin C., N. Manasa, Vicky Sharma, and Nippun Kumaar A A, “Vegetable Classification Using You Only Look Once Algorithm”, in 2019 International Conference on Cutting-edge Technologies in Engineering (ICon-CuTE), 2019.[Abstract]


Vegetable detection and classification is a challenging objective in daily production and use, and the complexity increases when other parameters such as shape, size and color are taken into consideration. In this paper, we define a methodology that will detect and classify three different green vegetables of different sizes. This method involves the use of Tensor Flow, Dark flow which is a Tensor flow version of You only look once (YOLO) algorithm, OpenCV. To train the desired network, several various vegetable images were fed into the network. The images were pre-processed before training by drawing bounding boxes around the vegetable manually using OpenCV. The main algorithm responsible for the detection and classification is YOLO. This method provides a faster and smarter way to identify an object in the given image or video. Once the network is trained, the test input is passed in to the network. Once the input is provided to the network, the output will display bounding boxes around the recognized vegetable and label it with its predicted class category with accuracy of 61.6 percent.

More »»

2018

P. R. Teja and Nippun Kumaar A A, “QR Code based Path Planning for Warehouse Management Robot”, in 2018 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2018.[Abstract]


Path planning is an essential part of a mobile robot controller. Autonomous path planning in a large space like warehouse is a challenging task. This work focuses on developing an efficient path planning algorithm for warehouse management robot using QR Code. Nowadays mobile robots play an important role in warehouse automation task such as navigating to a particular location, picking up the desired object and using it back to packing section. The proposed system uses QR Code sticker in the floor placed at strategic locations as via points to reach the desired destination and to pick the desired object. The proposed path planning algorithm is implemented and test in 3D Robotics simulator WEBOTS. The simulated results proves that the QR Code based path planning for the large environments is efficient and less computationally complex. More »»

2017

B. Veekshan Sree Sesha Sai, B. Akshay Kumar, B. Mani Rajesh Reddy, and Nippun Kumaar A A, “Dynamic stability algorithm for a Hexapod Robot”, in Recent Developments in Control, Automation Power Engineering (RDCAPE), 2017.[Abstract]


Navigation on different types of terrain has formed a barrier in usage of robots across various fields. Legged robots have more maneuverability compared to wheeled robots and can able to traverse on any kind of surface. Hexapod is a six-legged robot which is statically stable and can navigate on uneven surface. This work focuses on developing a stability algorithm using a closed loop control system with Inertial Measurement Unit as feedback sensor. Control system is used to calculate the motor angles in order to achieve stability over inclined surface. The proposed algorithm aims in selecting appropriate motors to control by moving it to the angle generated by the control system. The algorithm was implemented and tested on Amrita Hexapod Robot (AHR) platform.

More »»

2016

L. P. Amrita and Nippun Kumaar A A, “Bluetooth RSSI based collision avoidance in multirobot environment”, in 2016 International Conference on Advances in Computing, Communications and Informatics (ICACCI), 2016.[Abstract]


Multi-robot system is gaining its importance in robotic research. One critical issue in multi-robot system is collision among the mobile robots while sharing same workspace. This paper deals with the collision-free path planning for multiple mobile robots using Bluetooth RSSI value. In the proposed collision avoidance algorithm a decentralized approach with fixed priority level for robots is considered. A variable speed technique based on the RSSI value of robots is used and the obstacle avoidance is implemented based on State based Obstacle Avoidance Algorithm. Proposed algorithm is implemented and tested using Webots 3D simulator.

More »»

2015

B. A, Nippun Kumaar A A, and TSB, S., “3 axis SCARA robot with universal gripper”, in 2015 International Conference on Trends in Automation, Communications and Computing Technology (I-TACT-15), 2015.[Abstract]


The paper describes the design of pick and place 3-axis SCARA robot with a compact universal gripper. Pick and place an object is the predominant job of the robotic manipulators in the industry. The challenging task in designing such manipulators is to develop a universal gripping mechanism, which should possess the ability to pick unfamiliar objects irrespective of its shape within the given size range. The most commonly used technique to accomplish such challenge is multi-fingered approach, but it increases the complexities on both hardware and software for smaller objects. The gripping mechanism discussed in this paper uses the concept of granular jamming. The gripper consists of single mass of granules which conforms to the shape of the target objects when pressed onto it. On evacuating the air, granules contracts and hardens quickly to hold the object. This approach of gripping mechanism does not require any sensory feedback to pick an object.

More »»

2014

Nippun Kumaar A A and Sudarshan, T. S. B., “Path Mapping and Planning with Partially known Paths using Hierarchical State Machine for Service Robot”, in 3rd International Conference on Robot Intelligence Technology and Application 2014 (RiTA), FIRA 2014, Beijing, China, 2014.[Abstract]


Path mapping is a very essential part of a mobile robot navigation system. In this work, a novel technique to map and plan path for a mobile service robot without any vision aids in indoor environment using hierarchical state machine with partially known paths is proposed. The known paths are taught to a robot using Learning by Demonstration technique (LfD). The first phase of the algorithm is to map the paths as a hierarchical state machine using the partially known paths. Second phase is to plan the path given the source and destination. The algorithm is implemented and tested using a 2D simulation environment platform, Player/Stage.

More »»

2013

Nippun Kumaar A A and Dr. T.S.B. Sudarshan, “Learning from demonstration with state based obstacle avoidance for mobile service robots”, in International Conference on Mechatronics, Applied Mechanics and Energy Engineering, MAMEE 2013, American Applied Sciences Research Institute Singa- pore , 2013, vol. 394, pp. 448-455.[Abstract]


Learning from Demonstration (LfD) is a technique for teaching a system through demonstration. In areas like service robotics the robot should be user friendly in terms of coding, so LfD techniques will be of greater advantage in this domain. In this paper two novel approaches, counter based technique and encoder based technique is proposed for teaching a mobile service robot to navigate from one point to another with a novel state based obstacle avoidance technique. The main aim of the work is to develop an LfD Algorithm which is less complex in terms of hardware and software. Both the proposed methods along with obstacle avoidance have been implemented and tested using Player/Stage robotics simulator. © (2013) Trans Tech Publications, Switzerland.

More »»

2011

Nippun Kumaar A A and Sudarshan, T. S. B., “Mobile Robot Programming By Demonstration”, in International Conference on Emerging Trends in Engineering and Technology – ICETET, Le Meridien  Mauritius, 2011, pp. 206-209.[Abstract]


Programming by demonstration is an End-user development technique for teaching a computer or a robot new behavior by demonstrating the task to transfer directly instead of programming it through machine commands. In this paper we propose two new techniques to obtain the control code for a mobile robot through "programming by demonstration". Initially, a robot is controlled by a human operator who manually guides the robot through a desired path this is called teaching phase, and then the robot will navigate autonomously with taught information this is called execution phase. In contrast to traditional robot programming techniques, these methods does not require specialized technical or programming skills, but translates demonstrated behavior immediately into executable code. This has obvious implications for the widespread use of personal service robots.

More »»

Publication Type: Conference Proceedings

Year of Publication Title

2017

B. Sannapaneni, Shaswat, M., and Nippun Kumaar A A, “Learning from demonstration algorithm for cloth folding manipulator”, 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI), vol. 2017-January. pp. 1339-1398, 2017.[Abstract]


The aging population and high labor cost have accelerated the need for service robots for household activities. The household activity being diverse robot training over dynamic environments is required. Our work aims in developing an algorithm for teaching a manipulator to perform a task. Teaching pendant simplifies the process of teaching for the end user and also trains manipulator to a user specific problem. In this work, we present an approach to teaching a manipulator using Learning from Demonstration technique. Folding a cloth is taken as activity to teach the robot. Amrita Dual Anthropomorphic Manipulator (ADAM) is used to test the proposed algorithm.

More »»

2011

Nippun Kumaar A A and Sudarshan, T. S. B., “Sensor Counter Approach for a Mobile Robot to Navigate a Path Using Programming by Demonstration”, International Conference on Communication Technology and System Design – ICCTSD, vol. 30. Elsevier, Amrita School of Engineering at Ettimadai , pp. 554–561, 2011.[Abstract]


This paper presents a sensor counter approach for a mobile robot to navigate a path using programming by demonstration. In this paper a hybrid method which uses sensor values and counter values as path variables has been proposed, in order to avoid the dynamic obstacle in the environment we propose an obstacle avoidance algorithm (OAA) which is merged with hybrid method. Proposed method has been implemented and tested in a mobile robot platform AAMoR-1. Experiments has been done in an real time test environment to find the accuracy of the robot, the robot has been taught a particular trajectory by a human operator and later changing the robot to autonomous mode where in it moves in the same trajectory as taught, obstacle avoidance algorithm has also been tested by adding an obstacle in the taught path. Good test results have been obtained.

More »»

Publication Type: Journal Article

Year of Publication Title

2014

S. Sanju, Nippun Kumaar A A, and Sudarshan, T. S. B., “Autonomous Robotic Arm With Enhanced Intelligence”, International Journal of Advanced Computational Engineering and Networking, vol. 2, pp. 12–17, 2014.[Abstract]


In robotics for accomplishing simple and complex tasks, manipulation is a very important aspect. For maximizing the robustness and minimizing the cost there is no ideal solution for manipulation. Service robot systems have long been a goal of robotics research. This proposed work deals with the design and development of an autonomous robotic arm with enhanced intelligence. Amrita Articulated Robotic Manipulator, AARM-II is designed and fabricated, and is used for the realization of the proposed algorithm. Servomotors are used as actuators. A computer through a serial port interface using Flash Magic terminal controls the arm. The arm will be capable of picking and placing the objects in the sequence given by the user through PC terminal; if the arm is ideal it enters into random pick and place mode. Object’s source and destination order is entered in the user interface application. The trajectory planning is done with the help of Inverse Kinematics (IK). Geometric approach is followed to obtain inverse kinematic solutions. The work also aims at addressing the user interrupts instantly while the robot is in random pick and place mode and arrange the object in the sequence provided by the user in an efficient manner. The Microcontroller used is ARM7 based Blueboard LPC2148.

More »»

2010

Nippun Kumaar A A, TSB, S., and , “Intelligent lighting system using wireless sensor networks”, International Journal of Ad hoc, Sensor & Ubiquitous Computing (IJASUC) , vol. 1, 2010.[Abstract]


This paper examines the use of Wireless Sensor Networks interfaced with light fittings to allow for daylight substitution techniques to reduce energy usage in existing buildings. This creates a wire free system for existing buildings with minimal disruption and cost.

More »»