Maks Sorokin
I am a Research Scientist at the RAI Institute, developing robot learning systems for whole-body manipulation. My work enables robots to have purposeful dynamic interactions with large objects and environments. I focus on fast and steerable policy learning - creating systems that can rapidly acquire new behaviors and generalize well.
Currently finishing my Robotics Ph.D. at Georgia Tech under Dr. Sehoon Ha and Dr. C. Karen Liu, where I've built expertise across vision-based learning, navigation, manipulation, and computational design.
My goal is to develop robotic systems capable of learning and executing complex physical tasks with elegance - at scale, and with superhuman speed and precision.
Latest
Combining Sampling and Learning for Dynamic Whole-Body Manipulation
Maks Sorokin*, Jan Brüdigam*, Brandon Hung*, Stephen Phillips, Dmitry Yershov, Farzad Niroui, Tong Zhao,
Leonor Fermoselle, Xinghao Zhu, Duy Ta, Tao Pang, Jiuguang Wang, Simon Le Cléac'h
We give Spot the ability to manipulate heavy objects (15kg tires) by using its entire body. We combine sampling-based optimization with reinforcement learning to enable forceful, multi-contact manipulation that discovers strategies on the fly. The system handles objects exceeding the robot's nominal payload at near-human speeds.
Featured
Jacta: A Versatile Planner for Learning Dexterous and Whole-body Manipulation
Jan Brüdigam, Ali Adeeb Abbas, Maks Sorokin, Kuan Fang, Brandon Hung, Maya Guru, Stefan Sosnowski, Jiuguang Wang, Sandra Hirche, Simon Le Cleac'h
IEEE Robotics and Automation Letters (RA-L) 2024
We combined reinforcement learning with sampling-based algorithms to solve contact-rich manipulation tasks. While sampling-based planners can quickly find successful trajectories for complex manipulation tasks, the solutions often lack robustness. We leveraged a reinforcement learning algorithm to enhance the robustness of a set of planner demonstrations, distilling them into a single policy that can handle variations and uncertainties in real-world scenarios.
On Designing a Learning Robot: Improving Morphology for Enhanced Task Performance and Learning
Maks Sorokin, Chuyuan Fu, Jie Tan, C. Karen Liu, Yunfei Bai, Wenlong Lu, Sehoon Ha, Mohi Khansari
International Conference on Intelligent Robots and Systems (IROS) 2023
We present a learning-oriented morphology optimization framework that accounts for the interplay between the robot's morphology, onboard perception abilities, and their interaction in different tasks. We find that morphologies optimized holistically improve the robot performance by 15-20% on various manipulation tasks, and require 25x less data to match human-expert made morphology performance.
Learning to Navigate Sidewalks in Outdoor Environments
Maks Sorokin, Jie Tan, C. Karen Liu, Sehoon Ha
IEEE Robotics and Automation Letters (RA-L) 2022
We design a system which enables zero-shot vision-based policy transfer to the real-world outdoor environments for sidewalk navigation task. Our approach is evaluated on a quadrupedal robot navigating sidewalks in the real world walking 3.2 kilometers with a limited number of human interventions.