Our lab's research spans across various domains, ranging from hardware development to the creation of controllers utilizing Optimal Controls, learning-based controls, and safety-critical controls. The following projects serve as a testament to this diverse spectrum of work.
Design and Control of a low cost bipedal robot
A highly dynamic, torque controllable manipulator for quadruped robots.
Control Barrier Functions for Kinematic Obstacle Avoidance :A Collision Cone Approach
A framework for designing controllers to achieve robust blind quadrupedal walking using force control thorugh learnt linear policies.
A new class of CBFs for robotic systems that augment kinetic energy with the traditional forms.
Policy gradient theorem for average reward criteria with deterministic policy.
A framework for utilizing experience for generating predictive simulations and learning from them.
A framework for sythesizing controllers to achieve blind bipedal walking on challenging terrains thorugh learnt linear policies.
This paper presents a linear policy approach to achieve walking on sloped terrains
A complete description of the hardware design and control architecture of our custom built quadruped robot, called the Stoch
Learning Active Spine Behaviors for Dynamic and Efficient Locomotion
Trajectory based Deep Policy Search for Quadrupedal Walking
Reinforcement Learning using ARS (Augmented random Search)to generate Gaits