Background Image

Opportunities

Opportunities for MIT UROPs, SuperUROPs and MEng (unfortunately it's likely we will not be able to offer RAs for MEng). If you are interested please send an email to the corresponding student.

Please note that you have to be an MIT student to apply.

Current Opportunities

// Visibility-Aware Motion Planning

About

We are interested in investigating practical formulations of and solutions to what we are calling "visibility-aware motion planning". In a traditional motion planning setting, a robot must plan a sequence of robot motions that avoid collision with known environment. In visibility-aware motion planning, the environment can contain un-modeled obstacles, and the robot must plan a sequence of moves and a sequence of "look" actions. The look actions ensure that if there are any unexpected obstacles, they will be seen before the robot causes a collision. At that moment, execution framework on the robot knows that the plan is invalid (since an unexpected obstacle was encountered). It adds the obstacle to the map, and the robot re-plans.

This problem arises from running navigation algorithms on actual robots. We have some information about the environment the robot is in (we know, for example, the floorplan). But we still need to move safely with respect to unknown and unexpected obstacles.

Contact

Take a look here to see if you are interested in this project and to learn about how to apply for this position.

Gustavo Goretkin
goretkin@csail.mit.edu

// Physical Understanding for Robotic Manipulation

About

Robotic manipulation tasks require robots to reason about how to use their end effectors, or hands, to grasp and move objects around the world. I am interested in tasks that require some physical understanding of the world. This includes tasks like balancing objects in specific arrangements, moving constrained mechanisms such as doors, and/or tool use problems. In the example of stacking objects, the physical understanding of an object's center of mass (COM) is important so that the objects don't fall. Other physical concepts such as friction are important, but for this assignment we will focus on COM and stability. The objective of this assignment is to familiarize you with a simple notion of object stability and to visualize solutions to finding stable arrangements of objects in a simulator.

Contact

If any part of this problem interests you, try out the assignment below. Please dedicate at most 8 hours to it, and turn in what you have completed in that time. I encourage you to reach out to me at carism (at) mit (dot) edu if you have any questions! Students applying and completing this assignment should have completed courses 6.006 and 6.009. If you feel that you are a good fit but have not completed these courses please email me and we can discuss. Link to assignment: https://github.com/carismoses/assessment

Caris Moses
carism@mit.edu