Bio:

Mrinal Kalakrishnan graduated with a B.E. in Telecommunication from PESIT, Bangalore in 2004, and an M.S. in Computer Science from the University of Southern California in 2008. He is currently pursuing his doctoral degree at USC, advised by Prof. Stefan Schaal. His research focuses on the development of machine learning techniques to improve the performance of motion planners for autonomous robots in challenging domains such as rough terrain locomotion and autonomous grasping and manipulation. He is also interested in designing and learning controllers that use sensory and visual feedback loops to achieve compliant yet robust behavior.

Research Interests:

Machine Learning, Legged Locomotion, Motion Planning, Reinforcement Learning, Inverse Reinforcement Learning, Grasping and Manipulation, Force and Compliance Control

Journal Publications

Righetti, L. and Buchli, J. and Mistry, M. and Kalakrishnan, M. and Schaal, S. (2013). Optimal distribution of contact forces with inverse dynamics control, International Journal of Robotics Research, 32, 3, pp.280-298.
[Keywords: inverse dynamics; floating base; nonlinear control; legged robot]
[Detail] [BibTeX] [PDF]

Kalakrishnan, M.;Buchli, J.;Pastor, P.;Mistry, M.;Schaal, S. (2010). Learning, planning, and control for quadruped locomotion over challenging terrain, International Journal of Robotics Research, 30, 2, pp.236-258.
[Keywords: quadruped locomotion, locomotion planning and control, template learning, zmp optimization, floating base inverse dynamics]
[Detail] [BibTeX] [PDF]

Conference Publications

Kalakrishnan, M.; Pastor, P.; Righetti, L.; Schaal, S. (2013). Learning Objective Functions for Manipulation, IEEE International Conference on Robotics and Automation.
[Keywords: learning, inverse reinforcement learning, manipulation, grasping, inverse kinematics, motion planning, trajectory optimization]
[Detail] [BibTeX] [PDF]

Peter Pastor, Mrinal Kalakrishnan, Jonathan Binney, Jonathan Kelly, Ludovic Righetti, Gaurav Sukhatme, Stefan Schaal (2013). Learning Task Error Models for Manipulation, IEEE International Conference on Robotics and Automation.
[Detail] [BibTeX] [PDF]

Herzog, A.; Pastor, P.; Kalakrishnan, M.; Righetti, L.; Asfour, T.; Schaal, S. (2012). Template-Based Learning of Grasp Selection, IEEE International Conference on Robotics and Automation (ICRA).
[Keywords: grasping, manipulation, grasp selection]
[Detail] [BibTeX] [PDF]

Kalakrishnan, M.; Righetti, L.; Pastor, P.; Schaal, S. (2012). Learning Force Control Policies for Compliant Robotic Manipulation, International Conference on Machine Learning (ICML).
[Keywords: movement primitives, reinforcement learning, pi2, skill learning, force control]
[Detail] [BibTeX] [PDF]

Peter Pastor, Mrinal Kalakrishnan, Ludovic Righetti, Stefan Schaal (2012). Towards Associative Skill Memories, IEEE-RAS International Conference on Humanoid Robots.
[Detail] [BibTeX] [PDF]

Pastor, P.;Kalakrishnan, M.;Chitta, S.;Theodorou, E.;Schaal, S. (2011). Skill learning and task outcome prediction for manipulation, Robotics and Automation (ICRA), 2011 IEEE International Conference on.
[Keywords: movement primitives, reinforcement learning, sensory data mining, motor skills]
[Detail] [BibTeX] [PDF]

Kalakrishnan, M.;Chitta, S.;Theodorou, E.;Pastor, P.;Schaal, S. (2011). STOMP: Stochastic trajectory optimization for motion planning, Robotics and Automation (ICRA), 2011 IEEE International Conference on.
[Keywords: reinforcement learning, optimization, optimal motion planning]
[Detail] [BibTeX] [PDF]

Kalakrishnan, M.;Righetti, L.;Pastor, P.;Schaal, S. (2011). Learning force control policies for compliant manipulation, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011).
[Keywords: movement primitives, reinforcement learning, pi2, skill learning, force control]
[Detail] [BibTeX] [PDF]

Pastor, P.;Righetti, L.;Kalakrishnan, M.;Schaal, S. (2011). Online movement adaptation based on previous sensor experiences, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011).
[Keywords: best overall paper award, movement primitives, force control, associative memeory, perception-action coupling]
[Detail] [BibTeX] [PDF]

Stulp, F.;Theodorou, E.;Kalakrishnan, M.;Pastor, P.;Righetti, L.;Schaal, S. (2011). Learning motion primitive goals for robust manipulation, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2011).
[Keywords: movement primitives, reinforcement learning, pi2, skill learning]
[Detail] [BibTeX] [PDF]

Sucan, I.; Kalakrishnan, M.; Chitta, S. (2010). Combining Planning Techniques for Manipulation Using Realtime Perception, IEEE International Conference on Robotics and Automation.
[Detail] [BibTeX] [PDF]

Kalakrishnan, M.;Buchli, J.;Pastor, P.;Mistry, M.;Schaal, S. (2010). Fast, robust quadruped locomotion over challenging terrain, Robotics and Automation (ICRA), 2010 IEEE International Conference on, pp.2665-2670.
[Keywords: best paper finalist, force control learning systems legged locomotion optimisation path planning stability criteria body trajectory optimizer challenging terrain control architecture control strategy fast robust quadruped locomotion floating-ba]
[Detail] [BibTeX] [PDF]

Kalakrishnan, M.;Buchli, J.;Pastor, P.;Schaal, S. (2009). Learning locomotion over rough terrain using terrain templates, Intelligent Robots and Systems, 2009. IROS 2009. IEEE/RSJ International Conference on, pp.167-172.
[Keywords: legged locomotion path planning littledog quadruped robot foot hand-hold selection foothold ranking function human rock-climbing robotic legged locomotion rough terrain terrain templates]
[Detail] [BibTeX] [PDF]

Buchli, J.;Kalakrishnan, M.;Mistry, M.;Pastor, P.;Schaal, S. (2009). Compliant quadruped locomotion over rough terrain, Intelligent Robots and Systems, 2009. IROS 2009. IEEE/RSJ International Conference on, pp.814-820.
[Keywords: force control gain control humanoid robots legged locomotion position control predictive control robot dynamics stability active balance control climbing rocks compliant quadruped locomotion floating-base inverse dynamics control littledog]
[Detail] [BibTeX] [PDF]

Ting, J.;Kalakrishnan, M.;Vijayakumar, S.;Schaal, S. (2008). Bayesian kernel shaping for learning control, in: Koller, D.;Bengio, Y.;Schuurmans, D.;Bottou, L.;Culotta, A. (eds.), Advances in Neural Information Processing Systems 21 (NIPS 2008), Cambridge, MA: MIT Press.
[Keywords: locally weighted learning, kernel regression, bayesian learning, nonstationary processes]
[Detail] [BibTeX] [PDF]

Google Scholar

Pre-CLMC Publications

Mehan, M.R.; Nunez-Iglesias, J.; Kalakrishnan, M.; Waterman, M.S.; Zhou, X.J (2008). An Integrative Network Approach to Map the Transcriptome to the Phenome, Research in Computational Molecular Biology.
[Detail] [BibTeX]

Liu, C.; Hu, J.; Kalakrishnan, M.; Huang, H.; Zhou, X.J. (2009). Integrative Disease Classification Based on Cross-platform Microarray Data, BMC Bioinformatics (APBC 2009).
[Detail] [BibTeX]

Videos:

Learning Force Control Policies for Compliant Manipulation:

Demos from the Autonomous Robotic Manipulation (ARM) project, Phase I:

Results from work on LittleDog, Phase III:

Summer internship at Willow Garage, 2010:

Summer internship at Willow Garage, 2009:

Email:

Address:

Ronald Tutor Hall, RTH-417
3710 S. Mc.Clintock Ave
Los Angeles, CA 90089

Phone:

(213) 821 6370

Fax:

(213) 740 1510