Perhaps it is because spring has already arrived and my energy levels go straight up. Perhaps it is because i will hopefully finish my PhD this year and i won’t have the chance to enroll to more courses any more.
Despite beeing extremely busy these days, I decided to enroll to three more university courses :
- Computre Graphics and Virtual Reality
- Autonomous Agents (AI + Machine vision)
- Algorithms for Robotic Problems
Although robotics are interesting from a Pattern Recognition/Machine Learning/Machine Perception view, I am also interested in viewing them from a Human computer interaction perspective, e.g. aibos have a very limited vocabulary speech recogntion. By using Distibuted Speech Recognition one can efficiently offload the speech recognition task and thus being able to use a much more rich speech interface. Other modalities such as gestures, face tracking may also be applied for human-robot communication. Emotion is also of high importance, refer to the Johnny Walker commercial.
Back on the more “pure” AI/robotics problems. One interesting issue is the localization and map building problem, e.g., how autonomous robots can identify their location in an unknown environment.
Although most solutions are based on machine vision it would be interesting to investigate how helpful it would be to exploit multi-modal information e.g., sensor information from vision, sonars, sounds. Another idea that came to me is to exploit the sensor information from more than one robots, to mitigate individual erroneous beliefs about location information a robot may have.
The robotics team in our university is really a great one, they came second place in the Florida RoboCup competition with the Kouretes team last year!
Coolness factor : 5.0!