Note: Majid Khadiv has transitioned from the institute (alumni).
Since September 2023 I am an assistant Professor at the Technical University of Munich.
From July 2022 to August 2023, I was a research scientist in the Empirical Inference department led by Prof. Dr. Bernhard Schölkopf.
My research focuses on both theoretical and empirical aspects of robotics, with a focus on locomotion and manipulation. I am mostly interested in generating complex motions for robots using machine learning and control theory and evaluating these behaviours on real robots.
From May 2018 to June 2022, I was a postdoctoral researcher in the Movement Generation and Control Group led by Prof. Dr. Ludovic Righetti. During my postdoc, I also contributed to the European Project MEMMO as well as the developement of the Open Dynamic Robot Initiative (ODRI).
Before joining Movement Generation and Control Group as a postdoc, I visited Autonomous Motion Department as a PhD visitor. During my one year visit, I worked on generating robust walking patterns for the humanoid robot Athena.
From 2012 to 2015, I was the head of dynamics and control group in the Iranian national humanoid robot project, SURENA III. I designed some novel motion planning and control algorithms for humanoid robots and implemented on humanoid robot SURENA III.
Please see my CV for more detail.
Humanoid robotics Locomotion
Step Timing Adjustment: A Step toward Generating Robust Gaits
Stepping simulation of the Sarcos humanoid robot Athena with passive ankles and prosthetic feet using a combination of step location and timing adjustment
Robust Humanoid Locomotion Using Trajectory Optimization and Sample-Efficient Learning
The main idea of this work is to use data from full-body simulation of humanoid robots to make the trajectory optimization stage robust by tuning the cost weights. We use Bayesian optimization to find the cost weights to use in the trajectory optimization that yields robust performance in the simulation/experiment, in the presence of different disturbance/uncertainties. In this video, we present two simulation scenarios of a 27 DoF humanoid robot. In the first scenario, we show through one practical example how the choice of cost in the trajectory optimization problem affects robustness and performance. Then, in the second scenario we apply Bayesian Optimization on the trajectory optimization problem with two cost weights and show how BO converges to the optimal set of cost weights.
Learning Variable Impedance Control for Contact Sensitive Tasks
The video presents extensive experiments in simulation of both floating and fixed-base systems in tasks involving contact uncertainties, as well as results for running the learned policies on a real system.
Variable Horizon MPC With Swing Foot Dynamics for Bipedal Walking Control
This video shows a set of new tests we performed on Bolt. Thanks to our feedback control based on Model Predictive Control, the robot can perform walking in the presence of different uncertainties. We conducted tests on 5 different scenarios, 1) walking forward/backward 2) uneven surface 3) soft surface 4) push recovery 5) slippage recovery.
Model-free RL for Robust Locomotion Using Trajectory Optimization for Exploration
In this work we present a general, two-stage reinforcement learning approach for going from a single demonstration trajectory to a robust policy that can be deployed on hardware without any additional training. The demonstration is used in the first stage as a starting point to facilitate initial exploration. In the second stage, the relevant task reward is optimized directly and a policy robust to environment uncertainties is computed. We demonstrate and examine in detail performance and robustness of our approach on highly dynamic hopping and bounding tasks on a real quadruped robot.
DeepQ Stepper: A framework for reactive dynamic walking on uneven terrain
We propose a novel 3D reactive stepper, The DeepQ stepper, that computes optimal step locations for walking at different velocities using the 3D capture regions approximated by the action-value function. The DeepQ stepper can handle non convex terrain with obstacles, walk on restricted surfaces like stepping stones and recover from external disturbances for a constant computational cost.
Introduction Video - Open Dynamic Robot Initiative
This video was submitted with our RAL paper "An Open Torque-Controlled Modular Robot Architecture for Legged Locomotion Research". https://arxiv.org/abs/1910.00093