Alexander Pashevich

I am a Ph.D. specializing in robotics, computer vision, and natural language processing. Over the last four years, I pioneered robot learning research in the team and developed methods to enable robots to learn visually- and language-guided behaviors from data. In the five publications at top-tier conferences, I showed advantages of my work over classical control algorithms. I also developed a method to transfer complex skills learned in simulation to real-world UR5 robots. I am now excited about the next challenge of applying my research knowledge to real-world products.

Email  /  Google Scholar  /  LinkedIn  /  Github  /  CV

My research interests include robotics, reinforcement and imitation learning, simulation-to-reality transfer, natural language processing, and vision-and-language navigation. During the Ph.D. studies, I was adviced by Cordelia Schmid and co-adviced by Ivan Laptev. I worked with Chen Sun during my internship at Google Research.

A multimodal transformer-based architecture for vision-and-language navigation (VLN) improving results on a challenging task by 74%.

An approach learning to build shapes by disassembly that combines learning in low-dimensional state space and high-dimensional observation space.

A reinforcement learning approach to task planning that learns to combine primitive skills learned from demonstrations.

An approach for transferring policies learned in simulation to real-world robots by exploiting parallel computations.

A hierarchical reinforcement learning approach for learning from sparse rewards.

An algorithm for unsupervised extraction of piecewise planar models from depth data using constrained Gaussian mixture models.

website template credit