Lokesh Krishna

I am a senior undergraduate at the Indian Institute of Technology (BHU) Varanasi, pursuing my bachelor's in Electronics Engineering. Currently, I am a guest researcher at the Movement Generation and Control Group, Max Planck Institute for Intelligent Systems, working on control strategies for agile and dynamic bipedal locomotion under the supervision of Majid Khadiv. I am also a student researcher at the Stochastic Robotics Lab, Indian Institute of Science, jointly advised by Shishir Kolathaya and Ayonga Hereid. Here I work towards the development of a lightweight control framework for robust proprioceptive bipedal walking. In my prior works, I have also worked on trajectory optimisation and control for quadrupedal robots.

Apart from my research activities, I also co-found and lead the student research group, RoboReG at my home institute. As the technical lead of this group, I have successfully mentored several student-driven research projects and led student teams in events/competitions of national significance. As an avid proponent of student mentorship, I had conducted various robotics workshops, summer camps and events to promote robotics research and foster the student's intrest and skillset in robotics. I am always happy to learn and open to network.

Email  /  CV  /  LinkedIn  /  Google Scholar  /  Twitter  /  GitHub

profile photo

My research intrest lies in extending the athletic intelligence in robots and thereby leveraging their motor skills. I am interested in adopting formal methods from optimization, reinforcement learning to control hybrid and underactuated robotic systems. In future, I look forward to working towards the development of algorithms with the optimal balance of performance, reliability and guarantees of safety that are key to real-world robotic applications. Representative works are highlighted.

Linear Policies are Sufficient to Realize Robust Bipedal Walking on Challenging Terrains
Lokesh Krishna*, Guillermo Castillo*, Utkarsh Mishra, Ayonga Hereid, Shishir Kolathaya
Submitted to IEEE RA-L (journal) + ICRA 2022
arXiv(to be updated soon) / video

To make bipeds walk blindly on arbitary slopes, outdoors and stairs aswell as have a direct sim-to-real transfer, we find linear policies to be sufficient.

Learning Linear Policies for Robust Bipedal Locomotion on Terrains with Varying Slopes
Lokesh Krishna, Utkarsh Mishra, Guillermo Castillo, Ayonga Hereid, Shishir Kolathaya
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2021)
arXiv / project page / video

In this paper, we view toward deployment of robust and light-weight control frameworks for bipedal walking robots.

Robust Quadrupedal Locomotion on Sloped Terrains: A Linear Policy Approach
Kartik Paigwar, Lokesh Krishna, Sashank Tirumala, Naman khetan, Aditya Sagi, Ashish Joglekar, Shalabh Bhatnagar, Ashitava Ghosal, Bharadwaj Amrutur, Shishir Kolathaya
4th Conference on Robot Learning (CoRL 2020), MIT, USA
arXiv / project page / GitHub / video / slides

What is the minimum possible control framework that can be deployed to realize stable locomotion behaviors on slopped terrains in medium-size low-cost quadruped robots?

Ongoing Work(s)
Learning Agile Bipedal Locomotion Through Trajectory Driven
Multi Stage Learning

Lokesh Krishna , Miroslav Bogdanovic , Majid Khadiv , Ludovic Righetti

GitHub / video (to be added soon)
AADOpt: A Framework for Antenna Array Design and Synthesis through Optimisation
Lokesh Krishna, Prityush Chandra, Prajwal Nair, MK Meshram

GitHub / preprint

Completed Work(s)
Intelligent Picking: An end to end solution for ware house automation
Yash Sahijwani, Raghav Soni, Ayush Kumar Shaw, Niranth Sai, Lokesh Krishna

National Finalists, Flipkart Grid 2.0 Robotics Challenge

Slides / GitHub / video
Jerbot: a biomimetic bipedal robot
Lokesh Krishna, Nishant Kumar, Niranth Sai

GitHub / video
TOWRpy: a simulation test bed for TOWR trajectories in Pybullet
Lokesh Krishna, Shishir Kolathaya

Mini Projects

MiniCheetahEnv: A modular pybullet environment for mini-cheetah with an MPC controller
GitHub / Video

ArduinoMLP: A NN netowrk library for Arduino
GitHub / Report / Video

RaisimStoch2: a simulation environment for Stoch2 in RAISIM

LudoBot: An autonmous ludo solving robot
GitHub / Video

GestureBot: A mobile manpualtion platform for gesture controlled teleoperation
GitHub / Video

GAMCA: Genetic Algorithm to solve Maze like Cellular Automata
GitHub /

cs188 Technical Head, 2020-21

Founder, 2020

Coordinator, Robotics Summer Camp 2021

Mentor, Robotics Summer Camp 2020

Panel Member, 2020-21

Mentor, 2019-20

I am a Roboticist, I dont make cool websites. He does.