
"Robots in Montreal," eh? Sounds like the title of a Steven Moffat Doctor Who episode. But it's really ICRA 2019 - the IEEE Conference on Robotics and Automation, and, yes, there are quite a few robots!

My team presented our work on evolutionary learning of rewards for deep reinforcement learning, AutoRL, on Monday. In an hour or so, I'll be giving a keynote on "Systematizing Robot Navigation with AutoRL":

Keynote: Dr. Anthony Francis
Systematizing Robot Navigation with AutoRL: Evolving Better Policies with Better Evaluation
Abstract: Rigorous scientific evaluation of robot control methods helps the field progress towards better solutions, but deploying methods on robots requires its own kind of rigor. A systematic approach to deployment can do more than just make robots safer, more reliable, and more debuggable; with appropriate machine learning support, it can also improve robot control algorithms themselves. In this talk, we describe our evolutionary reward learning framework AutoRL and our evaluation framework for navigation tasks, and show how improving evaluation of navigation systems can measurably improve the performance of both our evolutionary learner and the navigation policies that it produces. We hope that this starts a conversation about how robotic deployment and scientific advancement can become better mutually reinforcing partners.
Bio: Dr. Anthony G. Francis, Jr. is a Senior Software Engineer at Google Brain Robotics specializing in reinforcement learning for robot navigation. Previously, he worked on emotional long-term memory for robot pets at Georgia Tech's PEPE robot pet project, on models of human memory for information retrieval at Enkia Corporation, and on large-scale metadata search and 3D object visualization at Google. He earned his B.S. (1991), M.S. (1996) and Ph.D. (2000) in Computer Science from Georgia Tech, along with a Certificate in Cognitive Science (1999). He and his colleagues won the ICRA 2018 Best Paper Award for Service Robotics for their paper "PRM-RL: Long-range Robotic Navigation Tasks by Combining Reinforcement Learning and Sampling-based Planning". He's the author of over a dozen peer-reviewed publications and is an inventor on over a half-dozen patents. He's published over a dozen short stories and four novels, including the EPIC eBook Award-winning Frost Moon; his popular writing on robotics includes articles in the books Star Trek Psychology and Westworld Psychology. as well as a Google AI blog article titled Maybe your computer just needs a hug. He lives in San Jose with his wife and cats, but his heart will always belong in Atlanta. You can find out more about his writing at his website.
Looks like I'm on in 15 minutes! Wish me luck.
-the Centaur



























Well, the Nano climb is starting off great, for a switch! Fourth of July, and I'm already 800 words ahead of what my goal is for this time of the month.
Not bad, but then, I am on vacation. :-) An excerpt:

Well, so insanely busy, I haven't posted in a while. But not for want of working on things that I want to post about! Most pressingly, my Camp Nano project for the July Camp of 2018, and what I hope is the last major chunk of the third book in the Cinnamon Frost series ...
Well, Gabby had his stitches out and his collar off for all of twelve hours before we were back in the emergency room. He was cleared for activity, but then re-opened the wound.
The lesson: I should have said something. I knew we were taking the stitches out and returning him to activity too soon; they doctor gave us a window of 10-14 days, but the technician scheduled us for a 10-day return. That day, I was a bit iffy about the stitches, but they went ahead and removed them. I clarified: is he ready for activity? Can he go out? They said yes.
Well, they were wrong, and I should have said something at the day of the original appointment scheduling, at least putting it off until Monday. Failing that, I should have said something before the stitches came out. Failing that, I should have used my own discretion and left the collar on for a few more days.
Failing that, I failed my cat.
The late-night emergency doc didn't think the cut had reopened the underlying wound and that it didn't warrant stitches ... but it looks worse today. I kept him inside overnight and today; let's see how he's doing and whether I should exercise my discretion and take him back in.
-the Centaur
Pictured: Cancer cat, abscess cat, aka Lenora and Gabby.