UROP Openings

Have a UROP opening you would like to submit?

Please fill out the form.

Submit your UROP opening

Prediction-aware planning for autonomous driving adsa


Term:

Spring

Department:

16: Aeronautics and Astronautics

Faculty Supervisor:

Brian Williams

Faculty email:

williams@csail.mit.edu

Apply by:

ASAP

Contact:

Cyrus Huang: xhuang@csail.mit.edu

Project Description

The Model Based Embedded and Robotic Systems Group (MERS) is attempting to deploy a prediction-aware planner for automated driving on a real world system, which includes two RC cars that can be controlled by either a joystick or a software script. Their positions can be tracked by an accurate motion capture system. The goal of this UROP project is to contribute to both algorithmic development and real-world deployment. The project details depend on the interests of the student, and some possibilities are: 1) Inferring the recognition of a human-operated RC car 2) Planning a collision-free path for an autonomous car in the presence of other stochastic agents 3) Controlling an RC car to follow a pre-defined path as fast as possible without colliding with other stochastic agents 4) Generating plans for a multi-agent system to improve driving efficiency in congested driving scenarios such as intersections We are looking for students with interests in robotics and autonomous driving, and those who are self-motivated to identify their own research interests. For those who are interested in PhD programs, many topics are likely to culminate in conference publications.

Pre-requisites

Pre-requisites: ROS, Python, basic linux background Desirable: Hardware skills (e.g., soldering, laser cutting), machine Learning, planning, interested in entering a PhD program, interested in long-term projects