Visual servoing for Object Grasping

The projects defines implementation of visual servoing for object grasping. Visual servoing, also known as vision-based robot control, is a technique which uses feedback information extracted from a vision sensor (visual feedback) to control the motion of a robot. The proposed approach targets application domains from household to outer space.


  • Implement an efficient visual servoing algorithm on Franka Panda robot/Baxter robot and demonstrate successful object grasping.
  • Comparison with other object grasping algorithms.
  • How to consider robot uncertainties (Eg. Robot Sensor noise) into visual servoing methodology.
  • Implement and demonstrate moving object capture (If time permits)


  • In depth Understanding of Robot operating system (ROS).
  • Knowledge of Robot kinematics and Dynamics.
  • Vision Based control of Robots.
  • Hands on experience with Franka panda and Baxter Robots.


  • Good Programming skill Python/C++
  • Good Mathematical Background
  • Understanding of basic Image processing.



Dr Mithun Poozhiyil