Milad Shafiee

I'm a PhD candidate in BioRobotics Lab at the EPFL under the supervision of Prof. Auke Ijspeert. I am a robotics/ML researcher intrested on the use of Reinforcement Learning and Optimization algorithms for agile movement generation of legged robots. We use robots as tools to investigate scientific hypotheses about animal motor-control, iteratively taking inspiration from animals to improve the robots’ performance.

Email  /  Linkedin  /  Google Scholar  /  Twitter  /  Github

profile photo
Previous Research Experiences

In 2020-2021, I had been a Researcher in Dynamic Locomotion Group at the Max Planck Institute for Intelligent Systems under the supervision of Dr. Alexander Badri-Sprowitz. In 2019-2020, I had been a Research Fellow in Artificial and Mechanical Intelligence lab at the Italian Institute of Technology (IIT) under the supervision of Dr. Daniele Pucci.

I received my master degree in Mechanical engineering from University of Tehran in 2017. In 2017-2018, I had been the leader of the Dynamic and Control group of SURENA humanoid robot projects at CAST, University of Tehran, where I used the SURENA and Surena Mini as research platforms.

Research
ManyQuadrupeds: Learning a Single Locomotion Policy for Diverse Quadruped Robots
Milad Shafiee, Guillaume Bellegarda, Auke Ijspeert,
International Conference on Robotics and Automation (ICRA), 2024  
project page / arXiv / Code (Coming Soon)

DeepTransition: Viability Leads to the Emergence of Gait Transitions in Learning Anticipatory Quadrupedal Locomotion Skills
Milad Shafiee, Guillaume Bellegarda, Auke Ijspeert,
Pre-Print, 2023,   Accepted at Nature Communications
project page / arXiv / Code (Coming Soon)

Identifying important sensory feedback for learning locomotion skills
Wanming Yu, Chuanyu Yang, Christopher McGreavy, Eleftherios Triantafyllidis, Guillaume Bellegarda, Milad Shafiee, Auke Ijspeert, Zhibin Li
Nature Machine Intelligence, 2023,  COVER
paper / arXiv / Code

ExoRecovery: Push Recovery with a Lower-Limb Exoskeleton based on Stepping Strategy
Zeynep Ozge Orhan, Milad Shafiee, Vincent Juillard, Joel Coelho Oliveira, Auke Ijspeert, Mohamed Bouri,
International Conference on Robotics and Automation (ICRA), 2024  
arXiv

Puppeteer and Marionette: Learning Anticipatory Quadrupedal Locomotion Based on Interactions of a Central Pattern Generator and Supraspinal Drive
Milad Shafiee, Guillaume Bellegarda, Auke Ijspeert,
International Conference on Robotics and Automation (ICRA), 2023  
project page / arXiv / gallery

Online Bipedal Locomotion Adaptation for Stepping on Obstacles Using a Novel Foot Sensor
Pezhman Abdolahnezhad, Aghil Yousefi-Koma, Amirhosein Vedadi, Kasra Sinaei, Behnam Maleki, Milad Shafiee
Humanoids, 2022
project page / video / IEEE / arXiv

Hybrid leg compliance enables robots to operate with sensorimotor delays and low control update frequencies
Milad Shafiee, Alborz Sarvestani, Alexander Sprowitz,
Frontiers in Robotics and AI, 2021  
project page / arXiv / gallery

Online DCM Trajectory Generation for Push Recovery of Torque-Controlled Humanoid Robots
Milad Shafiee, Giulio Romualdi, Stefano Dafarra, Francisco Chavez, Daniele Pucci
Humanoids, 2019
project page / video / arXiv

Surena IV: Towards a cost-effective full-size humanoid robot for real-world scenarios
Aghil Yousefi-Koma,, Behnam Maleki,, Hessam Maleki, Amin Amani, Ali Bazrafshani, Hossein Keshavarz, Ala Iranmanesh, Alireza Yazdanpanah, Hamidreza Alai, Sahel Salehi, Mahyar Ashkvari, Milad Mousavi, Milad Shafiee
Humanoids, 2020
project page / video / IEEE / arXiv

Push Recovery of a Position-Controlled Humanoid Robot Based on Capture Point Feedback Control
Milad Shafiee, Aghil Yousefi-Koma, Reihaneh Mirjalili, Hessam Maleki, Mojtaba Karimi
ICRoM, 2018
project page / video / arXiv


Design and source code from Jon Barron's website.