University of Michigan Robotics Department

Spring inside to what's been happening around Michigan Robotics, including: • making robot tour guides more engaging • measuring multitasking with robot assistance • a day in the life of an Engineering student In our latest newsletter, catch up with recent research, videos, and more! Read: https://lnkd.in/gbdpvAXs

The bionic leg with plans freely available for researchers to build gets a boost. A new $1M National Science Foundation (NSF) grant will help build out the ecosystem for the Open-Source Leg–a robotic lower-limb prosthesis. “This grant is a key step toward engaging the wider research community–developing the infrastructure for an open-source project is challenging both to fund and create, and we’re very thankful for the continued NSF POSE award,” said Elliott Rouse, professor of robotics and mechanical engineering at the University of Michigan College of Engineering. “Inspired by how the Linux Foundation democratized computing and sparked countless innovations, we want to democratize access to robotics research on a broader scale, fostering breakthroughs that can transform lives," adds Senthur Ayyappan, research engineer. Read: https://lnkd.in/gpCBGmSN

Awesome talk today by Dr. Robert Gregg at the University of Toronto Robotics Institute on robotic prosthetics and exoskeletons 🦾 Talk recording: https://lnkd.in/gW338EPM University of Michigan Robotics Department University of Toronto Engineering #robotics

“My advice for grad students at conferences is to have fun and enjoy their time. Conferences can be very large with thousands of attendees and multiple simultaneous sessions, so pay attention to the speakers and sessions you are interested in. You can’t fit everything in, and sometimes the most reward can come from a casual coffee conversation during a break from the conference. One of my favorite parts of conferences is meeting new people and catching up with former colleagues. In academia we have an amazing opportunity to connect with brilliant people, and you never know who you might cross paths with again in the future.” —Joey Wilson, Rackham Predoctoral Fellow, and University of Michigan Robotics Department Ph.D. student. Learn more about Joey’s research: myumi.ch/3Q9Zw What is your advice to first-time conference attendees? Tell us in the comments or email us at rack.social@umich.edu. #UMich #GradSchool #WeAreRackham Image description: Joey Wilson at the 2023 IEEE International Conference on Robotics and Automation (ICRA) in London, UK. There, he presented two papers on mapping for autonomous robots. ALT: Person wearing glasses and a conference badge smiles in front of a banner reading "ICRA London 2023 - Exhibition Hall" decorated with graphic designs of a robotic hand.

New faculty are key components to building our robotics program. This latest cohort are some pretty exceptional roboticists and collaborators. We're happy to have the following faculty join us over the next year as we define the discipline to meet the emerging needs of society and make robotics an inclusive field for aspiring experts. • Bernadette Bucher, Assistant Professor starting this fall • Steven Ceron, Assistant Professor starting January 2025 • Xiaoxiao Du, Lecturer starting this fall • Yulun Tian, Assistant Professor starting Fall 2025 Read more about each: https://lnkd.in/gjTs3brH

Overview paper of our ROB 204 class developed by Prof. Leia Stirling and colleagues from the University of Michigan Robotics Department. It was really fun to teach and to witness the maturity and analytical thinking of our talented robotics majors! Plus, it prepares the ground for our special topics grad class on computational HRI (https://lnkd.in/gmqfXuDs). 2nd iteration coming this Fall -- stay tuned 😎.

😆 I am attending #CVPR 2024 this week in Seattle, WA! I will be presenting our recent paper "CRKD: Enhanced Camera-Radar Object Detection with Cross-modality Knowledge Distillation". If you're curious about the work or just want to chat, feel free to stop by my poster session on Thursday from 5 p.m. to 6:30 p.m. PDT at location Arch 4A-E, Poster 83! In this work, we have developed a novel knowledge distillation framework that can transfer knowledge from a LiDAR-camera teacher to a camera-radar student to achieve enhanced perception capability for autonomous vehicles 🚗! The CRKD model has achieved notable improvement over non-distilled baseline network and demonstrated SOTA performance with camera-radar configuration. I am grateful for the unwavering help and support from my collaborator Lingjun Zhao and my PhD advisor Katherine A. Skinner from University of Michigan Robotics Department! Hope to see you there! Please check links below for more details! Code is also available. Project website: https://lnkd.in/embVxeNH Online poster: https://lnkd.in/ewdZg4mJ Video presentation: https://lnkd.in/e9dec_kF

Professor Katherine A. Skinner awarded a National Science Foundation (NSF) CAREER grant! The grant will support work "to provide new capabilities for marine robotic systems to map, visualize, and navigate underwater sites autonomously.” “These new capabilities will be achieved using innovative machine learning methods to simultaneously capture the robot’s surroundings and pinpoint the robot’s location by combining acoustic and visual information,” the award abstract states. “Project outcomes will be demonstrated for use in archaeology by mapping historically significant shipwreck sites. The results will also apply to tasks such as underwater construction, infrastructure maintenance, and emergency response.” Read more: https://lnkd.in/ghb_zJTm

“This is a massive result for the field of wearable robotics,” says Elliott Rouse. Researchers at North Carolina State University, led by Hao Su, have demonstrated a new method that leverages artificial intelligence (AI) and computer simulations to train robotic exoskeletons to autonomously help users save energy for versatile activities such as walking, running, and climbing stairs. The work was done in collaboration with the University of Michigan and other institutions. “This new approach leverages physics-informed modeling of the human, robot, and attachment, enabling the system to learn how to assist across activities, even when a human user is present,” Rouse continues. “Not only was the team able to demonstrate sim-to-real transfer for wearable robots, but the developed controllers have the most impressive metabolic reductions in the literature. Now, we want to see these results replicated.” https://lnkd.in/dX9yn9PZ