Publications

  • Kumar V, Ha S , Liu C.K., "Learning a unified control policy for Safe Falling", IEEE/RSJ IROS,2017, Vancouver, CA.

  • Kumar V, Ha S, Yamane K, "Improving Model-Based Humanoid Balance Controllers using Reinforcement Learning and Adaptive Sampling", ICRA 2018, Australia.

  • Kumar V., Ha S, Liu C.K., "Expanding Motor Skills using Relay Networks", CORL, 2018, Zurich, Switzerland.

  • Yu, W., Kumar, V., Turk, G.,Liu, C.K., "Sim-2-Real transfer of Biped-locomotion", IROS, 2019, Macao China.

  • Kumar, V.,Ha, S., Sawicki, G.,Liu, C.K., "Learning a Control Policy for Fall-Prevention using an Assistive Device", ICRA 2020.

  • Kumar, V., Hermans, T., Fox, D., Birchfield, S. and Tremblay, J. "Contextual Reinforcement Learning of Visuo-Tactile Multi-Fingered Grasping Policies.", NeurIPS workshop 2020.

  • Kumar, V., Hoeller, D.,Sundaralingam ,B., Tremblay J, Birchfield, S. "Joint Space Control via Deep Reinforcement Learning", under review, ICRA 2021

  • Kumar V, Ha S , Liu C.K., Error-aware Policy Learning - Link coming soon

Manuscripts

  • "High performance pneumatics using Model Predictive Control", Vikash Kumar, Visak C V, Emanuel Torodov

  • "Precise Calibration of Robots with small link lengths using Kinematic Extensions", Visak C and Vikash Kumar