Walking robot

Team lead:

Shishir N. Y. Kolathaya
Bharadwaj AmruturRBCCPS/Electrical Communication Engineering (ECE)
Ashitava GhosalMechanical Engineering (ME)
Shalabh BhatnagarComputer Science and Automation (CSA)

RBCCPS has a custom built four legged robot (quadruped) called “Stoch”. The main goal is to explore deep-reinforcement learning algorithms to achieve a wide variety of walking behaviours. The quadruped must be able to plan and navigate over a diverse set of environments like flat plains, undulating and slippery surfaces, and also muddy terrains. Besides walking, we are also interested in exploring applications like:

  1. The quadruped must use vision, inertial measurements and other sensory information to read its surroundings, and then plan and execute its motion to a designated point.
  2. A traditional arm mechanism attached to the quadruped must be able to pick and place movable objects from one point to another.
The RBCCPS Walking Robot “STOCH”
Demo of the RBCCPS Walking Robot “STOCH” at the Shell Energy Transition Summit, 5 and 6 September 2018, Shell Technology Centre, Bangalore