I organized a relay along Seattle’s light rail line for UW CSE’s Race Condition Running club. Dozens of people ran, many a station was visited, and I can’t wait to do it again next year.
To appear as posters at the Conference on Robot Learning in November (virtually, I would guess):
- A paper describing how a robot can shape perceptions of its motion while doing a task. I’m happy that we were able to model this problem cleanly, and especially happy that our method works even with a tricky domain like coverage. iRobot, if you’re reading this, get in touch 😉
- Some new work describing how you can get a robot to make natural-seeming back-channels (nods, in this paper) based on human speech signals and a head-pose estimate. All it took was a fairly small amount of human-human interaction data, and the models are small enough that you can run them on real robots.
We have a new short paper summarizing our first experiments with modeling and controlling how a robot’s motion impacts the impressions formed by observers.
I helped put on UW’s undergrad robotics class this spring, working as one of several TAs to revamp the course projects for a fully virtual, simulation-only format. Thanks to the incredible platform and software work from the MuSHR team, we were able to create a buttery experience. I don’t know of any other educational stack that provides high-quality tests and scaffolding that can guide students in implementing a particle filter, controller and planner for a mobile robot—using ROS Noetic and Python 3, no less. All on top of a simulator that’s lightweight enough to run smoothly in an Ubuntu VM on just about any laptop. I think the materials and approach here should be the starting place for any class that’s trying to get students familiar with the important ideas in autonomous robotics and robot software.
Two RSS 2020 workshops I’ve been helping put together will be held next week. Check out the papers and come to the live sessions for discussions between our great panelists.
- Closing the Academia to Real-World Gap in Service Robotics: Researchers spend a lot of time thinking about service robots, but there aren’t many companies successfully fielding them. What can researchers do to help their work translate? We proposed this topic before the pandemic, but I’m looking forward to hearing thoughts on how things may change for service robots in a world where human-human contact is being minimized.
- Advances and Challenges in Imitation Learning for Robotics: Imitation learning remains as hot as ever. We’re looking forward to gathering leading researchers in the area to discuss what’s next.
Registration is required (but cheap!) to participate in the live events, but we’ll be posting recordings after.
Good news in a bad-news kind of time. By my count, there are 7 UW CSE awardees, and 3 of us are UTCS alum.