Mobile Robotics

The first part of this research work is to develop methods for building scaled 2D and 3D maps (free space maps) using single two point perspective (2PP) or three point perspective (3PP) images. 3D reconstruction was shown possible using the methods proposed in this work. The novelty of this method is that the proposed methods utilizes single images taken using monocular cameras and no calibration is needed.
Although the methods are initially developed for robotic applications to implement planning algorithms to plan a path for navigation tasks, due to the flexibility of the approach, it can also be implemented for the more general single view metrology problems.
A new path planning algorithm, introduced as Multi-Bug Path Planning (MBPP), was covered as the second part of the research, which finds all the possible optimal paths in a given environment.

Conference publications

• Bhanu Chander V., Asokan Thondiyath and Ravindran Balaraman, “Recovering Free Space from a Single Two-Point Perspective Image for Mobile Robot Navigation for Indoor Applications,” in Proceedings of 3rd International and 18th National Conference on Machines and Mechanisms (iNaCoMM), Badodkar D., Dwarakanath T. Eds. in Machines, Mechanism and Robotics, Lecture Notes in Mechanical Engineering, August 2018, pp. 15--26, doi: 10.1007/978-981-10-8597-0_2.
• Bhanu Chander V., Asokan Thondiyath and Ravindran Balaraman, "A new Multi-Bug Path Planning algorithm for robot navigation in known environments," in IEEE Region 10 Conference (TENCON), Singapore, 2016, pp. 3363--3367, doi: 10.1109/TENCON.2016.7848676.

Faculty in-charge: Prof. Asokan Thondiyath

Students: Mr. Bhanu Chander V.