Mohammad Khansari

I am a post-doc at the Department of Computer Science at Stanford University. I currently work with Prof. Oussama Khatib at Robotics Group at the Artificial Intelligence Laboratory. My research study lies at the intersection of two exciting fields: control theory and machine learning. More specifically, I use control theory to properly define dynamics of robots, and leverage on machine learning to endow them with the ability to perform a wide variety of tasks in complex unstructured environments. Guaranteed stability, adaptivity, reactivity, robustness, and compliancy are the five features that I always seek in my research.

I received my PhD in Robotics from EPFL (2012) and my MSc (2008) and BSc (2005) in Aerospace Engineering from Sharif University of Technology. I enjoy working with robots, creating things, developing new algorithms, and working on ideas that everyone says it does not work.


My research interest includes:
  - Whole-Body Robot Control under Uncertainty
  - Realtime Adaptive Motion Generation
  - Compliant Control
  - Variable Impedance control
  - Robot Learning
  - Imitation Learning
  - Bi-Manual Haptic Teleoperation
  - Dynamical Systems
  - Movement Primitives

Selected Publications

Contact Primitives

S.M. Khansari-Zadeh, E. Klingbeil, and and O. Khatib (2016), Adaptive Human-Inspired Compliant Contact Primitives to Perform Surface-Surface Contact under Uncertainty, The International Journal of Robotics Research.

Integrated Motion Generation and Variable Impedance Control

S.M. Khansari-Zadeh and O. Khatib (2015), Learning Potential Functions from Human Demonstrations with Encapsulated Dynamic and Compliant Behaviors, Autonomous Robots.

Stable Estimator of Dynamical Systems (SEDS)

S.M. Khansari-Zadeh and A. Billard (2011), Learning Stable Non-Linear Dynamical Systems with Gaussian Mixture Models, IEEE Transaction on Robotics, vol. 27, num 5, p. 943-957.

Learning Control Lyapunov Function

S.M. Khansari-Zadeh and A. Billard (2014), Learning Control Lyapunov Function to Ensure Stability of Dynamical System-based Robot Reaching Motions. Robotics and Autonomous Systems, vol. 62, num 6, p. 752-765.

Realtime Obstacle Avoidance

S.M. Khansari-Zadeh and A. Billard (2012), A Dynamical System Approach to Realtime Obstacle Avoidance, Autonomous Robots, vol. 32, num 4, p. 433-454.

Latest News

November 3, 2015: Co-organizing a workshop at the Humanoids 2015 with the title "Whole-Body Multi-Task Multi-Contact Humanoid Control".

October 1, 2015: Chaired the technical session on "Robot Learning I" at the IROS 2015 Whole-Body Multi-Task Multi-Contact Humanoid Control".

September 23, 2015: Invited to give a talk at KUKA robotics research center at Augsburg.

May 30, 2015: Co-organized a workshop at the ICRA 2015 with the title "Compliant and Versatile Robot Control in Human Environments: Bridging the Gap between Learning and Control".

May 13, 2015: Live demos to the executives of Boeing during their visit to the Stanford Robotics Lab.

April 28, 2015: Joined as Review Editor the Editorial Board of Robotic Control Systems, a specialty of Frontiers in Robotics and AI.

April 21, 2015: Hosted Mikael Damberg (the Minister of Enterprise and Innovation of Sweden) and Bjorn Lyrvall (Ambassador of Sweden to the USA) visit to the Stanford Robotics Lab.

April 20, 2015: Joined the SAILORS team, the Stanford AI outreach program for high-schoolers.

February 9, 2015: Invited to serve as an Associate Editor for the 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2015).

September-December, 2014: Co-organized the Stanford Robotics Seminar.