Inside Robotics

A new robotic navigation method: Multi-Policy Decision Making (MPDM)

In dynamic environments crowded with people, robot motion planning becomes difficult due to the complex and tightly-coupled interactions between agents. Trajectory planning methods, supported by models of typical human behavior and personal space, often produce reasonable behavior. However, they do not account for the future closed loop interactions of other agents with the trajectory being constructed. As a consequence, the trajectories are unable to anticipate cooperative interactions (such as a human yielding), or adverse interactions (such as the robot blocking the way). We propose a new method – Multi-Policy Decision Making (MPDM) for navigation amongst pedestrians in which the trajectory of the robot is not explicitly planned, but instead, a planning process selects one of a set of closed-loop behaviors whose utility can be predicted through forward simulation.

Read more.

Here is the MPDM presentation by Dhanvin Mehta, Gonzalo Ferrer and Edwin Olson, U-M, Ann Arbor.

Robotics Day 2017

Kevin French, a Ph.D. student in robotics, demonstrates a robotic arm, controlled with a Wii controller, that his group built for the Robotics Day technology showcase that took place Tuesday at the North Campus Research Complex. The event showcases state-of-the-art robotic technologies and educational efforts from universities, school districts, industry and government agencies across Michigan. (Photo by Akhil Kantipuly, College of Engineering)

U-M CSE Graduate Students present papers at ICAPS 2017

CSE graduate students Qi Zhang and Shun Zhang will present exciting research papers at ICAPS 2017, the 27th International Conference on Automated Planning and Scheduling, taking place this June at Carnegie Mellon University in Pittsburgh PA.

Here are the papers:

Minimizing Maximum Regret in Commitment Constrained Sequential Decision Making

Approximately-Optimal Queries for Planning in Reward-Uncertain Markov Decision Processes


Distinguished Leadership Awardee- Katie Skinner!

Congrats to current Ph.D student Katie Skinner on her Distinguished Leadership Award! 

This award is presented to the outstanding graduate students of the College of Engineering who have demonstrated outstanding leadership and service to the College, University, and community. Katie will be honored at the Leaders and Honors Brunch on March 19th. 

Congrats Katie!



A Shoutout to Two Michigan PhDs in Robotics

Science RoboticsThe research of Mechanical Engineering and Robotics alum Dr. Alireza Ramezani is featured on the February cover of Science Robotics. Dr. Ramezani defended his dissertation, “Feedback Control Design for MARLO, a 3D-Bipedal Robot,” in 2013. 

The U-M Mathematics Department has awarded Hamed Razavi with the 2016 Sumner B. Myers Prize, which honors the best PhD thesis in mathematics.  No award is made unless a thesis is judged to be truly distinguished:
Hamed Razavi, “Symmetry Method for Limit Cycle Walking of Legged Robots”, co-advised by Tony Bloch (Math) and Jessy Grizzle (EECS).
Michigan Daily 2/5/17 article 

RGSC End of Semester Celebtration

As a way to celebrate the end end of the semester and the holiday season and take a break from exam studies, RGSC held a White Elephant gift exchange party. Enthusiasm and the holiday spirit were high, and everybody had a relaxing and fun time, as we enjoyed food, socializing, presents, and a lot of laughs. This is likely to become an annual event for the robotics group.
Michigan Robotics students wish you a Happy New Year!

Take another look at robotic locomotion and morphology!

Selecting gaits for economical locomotion of legged robots

This paper explores the benefits of using multiple gaits in a single robot.

Weitao Xi, Yevgeniy Yseilevskiy, C. David Remy
Sage journals


Research on the simultaneous optimization of motion and morphology; comparing different actuators in legged robots:

A comparison of series and parallel elasticity in a Monoped hopper

Optimal configuration of series and parallel elasticity in a 2D Monoped

The video of the comparison:



Open-access Automated Cars Will Advance Driverless Research

New University of Michigan research vehicles will be open testbeds for academic and industry researchers to rapidly test self-driving and connected vehicle technologies at a world-class proving ground – Mcity.   

A roundabout at Mcity.
Mcity, a test site for autonomous vehicles that emulates the urban driving experience, is just half a mile from the Robotics Institute site.

Michigan Engineering article.