I was honored to give the Lockheed Martin Robotics Seminar at the University of Maryland last month. I talked about motivation dynamics, the framework I am developing to use dynamical systems tools for autonomous task management.
[Could not find the bibliography file(s)Much of the material I discussed can be found in various publications from my group, especially [?] and [?].
Giving talks over Zoom is an art I’m still learning. Showing videos poses a particular challenge because they’re often transmitted with a lag. For those who want to take a closer look at my videos from that talk, I post them here for reference.
A point robot using motivation dynamics to navigate in a sphere world, repeatedly patrolling two goal locations (red diamonds) while avoiding obstacles (black circles)
State trajectories for the two obstacles simulation. From top to bottom, the panels show navigation functions (normalized distance to goals), motivation state, and value state.
Simulation of the identical controller as in the two obstacle case, but now with one moving obstacle. The controller has no knowledge of the obstacle’s intent, just a perfect sensing of the obstacle’s current location.
State trajectories for the one moving obstacle simulation. From top to bottom, the panels show navigation functions (normalized distance to goals), motivation state, and value state.
Video for our recently-accepted T-RO paper on Motivation Dynamics [?].