I am currently a Robotics Research Scientist at the Samsung AI Center in New York, where I work on deep learning for robotic manipulation.

I recently completed my Ph.D in Mechanical Engineering at the University of Pennsylvania with Mark Yim in ModLab, part of the GRASP Lab. During my Ph.D, I developed robots that can transform between different shapes (like a car, snake, or arm) and build structures. My research focused on hardware design and planning algorithms for transforming robots.

Tarik Tosun’s CV

Featured Research

Pixels to Plans

We present a novel method enabling robots to quickly learn to manipulate objects by leveraging a motion planner to generate “expert” training trajectories from a small amount of human-labeled data. In contrast to the traditional sense-plan-act cycle, we propose a deep learning architecture and training regimen called PtPNet that can ...
Read More

Autonomous Modular Robots

Science Robotics, 2018. The theoretical ability of modular robots to reconfigure in response to complex tasks in a priori unknown environments has frequently been cited as an advantage and remains a major motivator for work in the field. We present a modular robot system capable of autonomously completing high-level tasks by ...
Read More

Environment Augmentation with Modular Robots

Featured on IEEE Spectrum and TechCrunch! We present a system enabling a modular robot to autonomously build structures in order to accomplish high-level tasks.  Building structures allows the robot to surmount large obstacles, expanding the set of tasks it can perform. This addresses a common weakness of modular robot systems, ...
Read More

SMORES-EP

SMORES-EP is a modular robot designed and built at the University of Pennsylvania, and used by researchers at Penn and Cornell. SMORES stands for Self-Assembling MOdular Robot for Extreme Shapeshifting, and EP refers to the Electro-Permanent magnets the modules use to connect ...
Read More

All Research

Pixels to Plans

We present a novel method enabling robots to quickly learn to manipulate objects by leveraging a motion planner to generate ...
Read More

Autonomous Modular Robots

Science Robotics, 2018. The theoretical ability of modular robots to reconfigure in response to complex tasks in a priori unknown environments ...
Read More

Environment Augmentation with Modular Robots

Featured on IEEE Spectrum and TechCrunch! We present a system enabling a modular robot to autonomously build structures in order ...
Read More

PaintPots

The PaintPot manufacturing process is a new way to create low-cost, low-profile, highly customizable potentiometers for position sensing in robotic ...
Read More

The EP-Face Connector

Conference Highlight Talk. We present the EP-Face connector, a novel connector for hybrid chain-lattice type modular robots that is high- ...
Read More

An End-to-End System for Accomplishing Tasks with Modular Robots

Best Systems Paper, RSS 2016.  In this paper, we present an end-to-end system for addressing tasks with modular robots, and ...
Read More

SMORES-EP

SMORES-EP is a modular robot designed and built at the University of Pennsylvania, and used by researchers at Penn and ...
Read More

Computer-Aided Compositional Design and Verification for Modular Robots

To take full advantage of the flexibility of a modular robot system, users must be able to create and verify ...
Read More

Modular Robot Design Embedding

We have developed an algorithm that automatically detects embeddability of modular robot configurations. Simply put, a given design embeds another ...
Read More

Kinematic Retargeting

Kinematic Retargeting is a process by which a pose or motion may be translated from one platform (robot, human, or ...
Read More