• Enrollment Number
    rsi2018003
  • Name
    Aditya Kumar Singh
  • Thesis Topic
    Analysis on Integration of smart home devices with Household Robots
  • Supervisor's Name
    Prof. G.C. Nandi
  • Abstract
    As per advancement in technology, every thing becoming smart as smart city, smart phone, smart class, smart home, etc. If a robot is propose for some household purposes then it also needs to be smart enough to deal with the situation. I am working on the integration of smart devices like alexa enabled echo devices, google home and siri, with the robot according to complexity of house structure.
  • Email Addresses
  • Enrollment Number
    RSI2017503
  • Name
    Alok Ranjan Sahoo
  • Thesis Topic
    Synthesis, Kinematics and Dynamics of Soft Robots
  • Supervisor's Name
    Dr. Pavan Chakraborty
  • Email Addresses
  • Enrollment Number
    PRO2017001
  • Name
    Gaurav Kumar Yadav
  • Thesis Topic
    Biped Locomotion Control Using Reinforcement Learning
  • Supervisor's Name
    Prof. G.C. Nandi
  • Email Addresses
  • Enrollment Number
    RSI2016504
  • Name
    Lhilo Kenye
  • Supervisor's Name
    Dr. Rahul Kala
  • Enrollment Number
    RSI2017002
  • Name
    Mohammed Haider
  • Supervisor's Name
    Dr. Rahul Kala
  • Email Addresses
  • Enrollment Number
    RS175
  • Name
    Padmakar Pandey
  • Thesis Topic
    Cognitive Robotics
  • Supervisor's Name
    Prof. G.C.Nandi
  • Abstract
    Cognitive robotics is a new approach to robot programming based on high level primitives for perception and action. These primitives draw inspiration from ideas in cognitive science combined with state of the art robotics algorithms. Cognitive robotics is about doing robotics that deals with cognitive phenomena such as perception, attention, anticipation, planning, memory, learning, and reasoning. Some people may think that robotics already deals with these phenomena, and are therefore left wondering how cognitive robotics would be any different from robotics. However, despite what we see in the movies, most existing robots don't learn, have no memory to speak of, and don't reason. In fact, at this point most existing robots are used in industry, and most of them don't even have any perceptual abilities at all; they are programmed to do one thing, and one thing only. This kind of robotics we might call Industrial Robotics, and it can be characterized with the 3 D's of robotics: robots
  • Abstract Detail
    Cognitive robotics is a new approach to robot programming based on high level primitives for perception and action. These primitives draw inspiration from ideas in cognitive science combined with state of the art robotics algorithms. Cognitive robotics is about doing robotics that deals with cognitive phenomena such as perception, attention, anticipation, planning, memory, learning, and reasoning. Some people may think that robotics already deals with these phenomena, and are therefore left wondering how cognitive robotics would be any different from robotics. However, despite what we see in the movies, most existing robots don't learn, have no memory to speak of, and don't reason. In fact, at this point most existing robots are used in industry, and most of them don't even have any perceptual abilities at all; they are programmed to do one thing, and one thing only. This kind of robotics we might call Industrial Robotics, and it can be characterized with the 3 D's of robotics: robots that do dull, dangerous, or dirty work, that no human would or can do ... which is exactly why Industrial Robotics is important! However, it is not what we see as Cognitive Robotics. In Cognitive Robotics, we are interested in the kind of robots that are, well ... more cognitive. Robots with the kind of intelligence that humans have. Robots that reason, remember, learn, and that can communicate with humans and with each other. Robots that can be characterized by the 3 C's: Clever, Creative, and Charismatic.
  • Email Addresses
  • Enrollment Number
    PHC2015001
  • Name
    Priya Shukla
  • Thesis Topic
    Human Robot Interaction using Reinforcement Learning
  • Supervisor's Name
    Prof. G.C.Nandi
  • Abstract
    For training a robot we can use reinforcement learning in place of supervised/unsupervised learning as it understand the human behavior by defining reward and penalty for every instance of working. So that robot can decide it should learn or not particular behavior. But learning is never ending process we need to restrict at some point so it can decide best feasible reward function .It can be restrict by defining discounting with reward. But before using reinforcement we need to know which type of problem it can solve. Our motive to discuss these entire things because we need a friendly system which can do our daily life easy and risk free working and with reinforcement learning robot can learn without a supervisor. We find so many problems and their solution like how robot will interact with human, robot coordination with human teammates and robot assistance to human during task execution not in planning time. We studied modeling of human behavior and cognition so that robot can understand human uncertain behavior sometime but it is not possible to correct every time. So that it depends on learning of robot by training.
  • Email Addresses
  • Enrollment Number
    RSI2019001
  • Name
    Rohit Yadav
  • Thesis Topic
    Simultaneous Localization and Mapping in extreme weather conditions
  • Supervisor's Name
    Dr. Rahul Kala
  • Email Addresses
  • Enrollment Number
    RSI2016501
  • Name
    Shruti Jaiswal
  • Supervisor's Name
    Prof. G.C. Nandi
  • Email Addresses
  • Enrollment Number
    RSI2016001
  • Name
    Vaibhav Malviya
  • Supervisor's Name
    Dr. Rahul Kala
  • Email Addresses
  • Enrollment Number
    PRO2014002
  • Name
    Venkat B
  • Thesis Topic
    Temporal logic based Multi Robot Mission Planning
  • Supervisor's Name
    Prof. G C Nandi & Dr. Rahul Kala
  • Abstract
    The ambitious goals and several environmental conditions made robot to render in environment trace the given problem statement which may leads to move infinity without knowing the current assumptions towards goal. Robot motion planning involves moving of a Robot from a point A to Point B. Point A is referred as Start point while point B as the Goal point. Simple goal specifications are also tending towards more complex situations wherein the start point and the goal point are defined but there are numerous obstacles across the path. Or in other way, more complications are being added to the path such as visiting of various regions at least once or skipping a region for last iteration et al, which may change from perspective to perspective. Temporal logic list relation between the different entities as regions or goal points in a more formal approach. This would use the graphs, maps or the binary maps along with the temporal logic to generate the path. Temporal logic can be termed tense logic. In 1950’s Temporal logic was introduced by Arthur Prior as a particular modal logic-based system of temporal logic and important results were obtained by Hans Kamp.
  • Software used
    NuSMV, Triangle Package, Python, Matlab
  • Email Addresses
  • website
    http://theroboticistvenkat.webs.com/