As the presence of robots in our every day life continues to increase, it will be critical to ensure that they can safely and efficiently interact with humans in an uncontrolled environment. Students on the Honda project will develop algorithms to find feasible, collision-free paths for a Clearpath Jackal robot with a Zed2 camera operating in a crowd of pedestrians.
Abstract:
Honda is working comprehensively to address challenges in the areas of the environment and safety. At the same time, for the future, Honda will strive to lead advancements, which will be made, in the areas of mobility, the power unit, energy and robotics. A key area of this is micro-mobility, and another key trend in the mobility industry is autonomy. As robots become more integrated into society, it is critical that they can path plan and interact with humans in an open environment. Students on the Honda project will utilize simultaneous localization and mapping (SLAM) and develop motion planning algorithms to find feasible, collision-free paths for robots operating in a crowd of pedestrians. Honda Automobile Technology Research Group will provide a Clearpath Jackal robot with a Zed2 camara for use in their Ann Arbor, MI R&D offices.
Impact:
This project will advance the strategic research within the Honda Research Institute and prepare for complex, multi-agent autonomous unit interaction with humans. It is important to investigate how robots should properly interact with humans in order to achieve a harmonious robot & human society.
Scope:
Minimum Viable Product Deliverable (Minimum level of success)
- Background review of hardware, SLAM, and robot social navigation including: academic literature, industrial best practices, and optimal algorithms.
- Background review of best practices for social interactions of robots with humans.
- A functioning baseline SLAM system build from available open-source libraries
- Implementation of social navigation algorithms onto the Jackal robot
Expected Final Deliverable (Expected level of success)
- Integration of social navigation algorithms onto the Jackal robot that allows the robot to navigate around pedestrians while performing SLAM.
- Ideation of robot to human interaction best practices including but not limited to:
- Sounds
- Visuals
- Actions
- Down selection of top idea and integration into system
Stretch Goal Opportunities: (High level of success)
- Integration of a second robot into the environment
- Integration of additional robot-human interaction methods with user testing
- Operation in a more complex environment such as outdoors, in low light, in poor visibility, etc.
Hardware Prototyping and Sensor Integration (2-3 Students)
Specific Skills: Hardware instrumentation, electrical system development, system integration
Likely Majors: EE, CE, ME, ROB
AI Reasoning and Path Planning (2-3 Students)
Specific Skills: Algorithm development and testing methods, understanding of localization
Prior SLAM experience is a plus
Must have completed EECS 281 or equivalent
Likely Majors: CS, ROB, ECE, EE, CE, DATA
General Programming (2-3 Students)
Specific Skills: General programming experience
Development and analysis will be performed in C++
Must have completed EECS 281 or equivalent
Likely Majors: CS
Additional Desired Skills/Knowledge/Experience
- Ability to come up with unique ideas to solve technical challenges
- Honda has a strong consensus culture – we highly value effective teamwork
- We highly value practical experience on team-based engineering projects
- Specific knowledge of C/C++ coding language
- Experience in coding in ROS (Robot Operating System) framework
Sponsor Mentor
Tyler Naes
After Receiving his Bachelor’s and Master’s Degree from Georgia Southern University, Tyler joined Honda as a research engineer. His research focuses on autonomous vehicle and micro-mobility applications. This is his third year participating in the Multidisciplinary Design Program.
Faculty Mentor
Alex Gorodetsky
Aerospace Engineering Department
Alex Gorodetsky is an Assistant Professor of Aerospace Engineering. His research interests include using applied mathematics and computational science to enhance autonomous decision making under uncertainty. He is especially interested in controlling systems, like autonomous aircraft, that must act in complex environments which are often represented by expensive computational simulations. Toward this goal, he pursues research in wide-ranging areas, including uncertainty quantification, statistical inference, machine learning, numerical analysis, function approximation, control, and optimization.
Alex completed his Ph.D. (2016) and S.M. (2012) in the Department of Aeronautics and Astronautics at the Massachusetts Institute of Technology, where he worked on algorithms for stochastic optimal control and estimation in dynamical systems. He received his B.S.E (2010) in Aerospace Engineering from the University of Michigan.
Project Meetings: During the winter 2024 semester, the Honda Robot team will meet at Honda Research Institute in Ann Arbor on Fridays from 3:00 – 5:00 PM. (MDP will provide transportation)
Work Location: Honda has an R&D Center located in Ann Arbor. Students will be provided with lab space and hardware within the Honda R&D Center. (MDP will provide transportation to the facility)
Course Substitutions: CE MDE, ChE Elective, CS Capstone/MDE, DS Capstone, EE MDE, CoE Honors, IOE Senior Design, ROB 490, ROB 590, SI Elective/Cognate
Citizenship Requirements: This project is open to all students. Note: International students on an F-1 visa will be required to declare part time CPT during winter 2024 and fall 2024 terms.
IP/NDA: Students will sign standard University of Michigan IP/NDA documents.
Summer Project Activities: Students will be guaranteed an interview for a 2024 internship. The interviews will take place before the end of February of 2024. Note: You must have the right to work in the U.S.A indefinitely, without sponsorship, to participate in the summer internship program.
Learn more about the expectations for this type of MDP project