Job Posting for 2021 SURE

Objective:

The Bio-Inspired Machine Intelligence (BIMI) lab (https://bimi.jrkwon.com) is looking for one undergraduate student who is interested in research funded by the 2021 Summer Undergraduate Research Experience (SURE) program.

Research Summary:

Driver Style Transfer for Autonomous Driving

People drive a vehicle differently. Yet, self-driving has a pre-defined style designed by manufacturers. It can be very uncomfortable for a driver who is aggressive in driving when a self-driving vehicle drives very cautiously. This can also be true vise versa. 

To provide an individualized autonomous driving experience, we will collect several driving styles from human drivers in a simulated environment. Then we will extract features from the driving data that can represent driving styles. 

To validate our approach, we will create a driving model from human driving data and the model will be deployed to a controller system of a simulated autonomous vehicle. 

Through this research, we will be able to provide an individualized autonomous driving experience for a driver who can feel the autonomous vehicle drives just like how the driver usually drives.

Responsibilities:

  • Read papers to understand the problems.
  • Participate in data collection, processing, and management.
  • Implement a neural network using Keras and/or PyTorch.
  • Prepare technical report.

Qualifications:

  • Required experiences:
    • Python Programming skill
    • Literacy in Linux commands
    • Machine learning toolkit: Keras and/or PyTorch
  • Preferred
    • Git and GitHub(or GitLab)
    • Robotic Operating Systems (ROS)
    • scikit-learn
    • pandas

Program Requirements:

  • The student must be a registered UM-Dearborn undergraduate student with an expected graduation date no sooner than December 2021.
  • The student will receive a stipend of $3,200 to be paid in installments throughout the project period (May-August). Students will receive payments of $1,000 the first week of June, July, and August, with a final payment of $200 after the Showcase in September.
    • Note, if the student receives financial aid, they should check with the Financial Aid Office to determine if this stipend will impact their financial aid package.
    • The student should not receive duplicate support while participating in this program; supplementing with external funding during the duration of the SURE program is NOT ALLOWED.
  • Student participants and faculty mentors must attend the SURE Kickoff on Tuesday, May 18th at 4 pm.
  • The student is required to attend the SURE Professional Development Seminars taking place on the following dates: 6/3, 6/17, 7/8, 7/22, 8/5, and 8/19 (all sessions run from 1:00 pm-2:00 pm; a schedule will be provided at the Kickoff event).
  • The student is expected to present their work at the SURE Project Showcase in the fall.

Contact Information

Please contact Prof. Jaerock Kwon at jrkwon@umich.edu.

DAIS 2020 Presentations

Sensorimotor Integration Learning for Autonomous Driving

By Mohamed Houssem Fehri

Latency Compensation in Autonomous Driving

By Sanjyot Thete

Autonomous Vehicle Research Platform

By Rohan Pradeepkumar Nair

Grant from IITP, Korea, 2020 – 2021

We have a new grant from the Institute for Information and Communications Technology Promotion (IITP) as a Korea-US International Joint Research Project. The project title is “Cooperative Perception and Navigation for Multiple Vehicles Using Deep Neural Network.” The project will complete by May 2021.

New Bimians 2020

Welcome to the BIMI Lab. You are a Bimian now.

  • Bharath Kumar Karre
  • Deepak Mysuru Heeranna
  • Meher Adheeth Hundi
  • Sanjyot Thete
  • Sumanth Pobala
  • Swathi Priya Soogoor

Development of Autonomous Vehicle Research Platform

A new project, “Development of Autonomous Vehicle Research Platform using Deep Learning and Robot Operating System” has been approved. This project is sponsored by the Institute for Information & Communication Technology Promotion (IITP), Korea.

This project is the 2nd phase of a project that was conducted at Kettering University from July 2019 to December 2019.

Research Initiation & Development Grant 2020

My research proposal, “Markerless 3D Human Motion Inference Framework from 2D Videos using Deep Learning,” has been selected for funding. This project is scheduled to start in May 2020 and end in December 2021.

https://umdearborn.edu/news/all-news/articles/update-office-research-april-2020

The project descriptions can be found at https://bimi.jrkwon.com/markerless-3d-human-motion-inference-framework-from-2d-videos-using-deep-learning/

Fig. 1. System overview. The proposed system has two sub-sections: 3D pose estimator from 2D video input (top) and gait feature extractor (bottom). (a) 2D input video, (b) 2D pose estimator, (c) extracted 2D joint points, (d) skeletal data of human pose, (e) skeletal model converter, (f) 2D joint points for 3D estimation, (g) 3D pose estimator, (h) 3D joint points, (i) feature extractor, (j) feature data, and (k) applications.