It's been a while, so I guess it's time for an update ;)
Back in November I fixed a bunch of bugs and added some substantial features to Zaza's voiceServer. The module now has full support for Sable markup on input voice cues. This allowed reintroduction of the sound effects we used with the old VB version of Zaza's face.
I finally managed to squash a longstanding bug a few weeks ago in Zaza's tourguide code that would occasionally cause the robot to not notice that it had arrived at an exhibit destination. It's not an elegant solution, but works consistantly.
Last week I added initial back-end support to the poslib module for button interactivity during a tour. This will (eventually) allow visitors to press Zaza's three buttons when she is stopped at an exhibit to hear additional information about it (beyond the standard monolog), language selection, etc... It also announces the destinations the robot plans to visit when a button is pressed when in motion.
We have managed to max-out our offboard server during the Phase IV test runs. During previous tests the robot would inexplicably get lost from time to time. We had attributed this to a network or hardware glitch, but it appears that the machine would get I/O bound when running the web-based GUI locally and cause the localizer to miss critical updates from the base and laser servers. Running the web interface on an external laptop seems to improve reliability. Ideally we would have dedicated machines for the web interface, video server, and localizer/planner but a single-processor PIII 800 is all we have available at the moment.