We recently conducted a research study with social robots at Fairfield hospital in Sydney.
We designed the experience and then implemented the intelligent distributed system. It combines a Softbank Pepper robot, a touch screen kiosk and several edge computing devices.
The robots alleviate stress and contribute to the welcoming atmosphere at the hospital.
From a technology perspective, the system included a number of novel features:
- Multi-lingual speech recognition, speech production and natural language processing
- Seamless multi-modal interaction using speech, gestures, video and touch (users can engage with the robot, the robot touch screen and/or the attached touch-screen kiosk)
- An intelligent "user engagement" subsystem that detects approaching people, maintains eye contact and responds through gestures
- A distributed system that offloads speech processing and image processing to nearby edge devices equipped with GPUs
- A visually appealing "organic" graphical interface that updates in real time (e.g., as partial speech recognition is performed)
- An web-based management interface that enables user-experience designers to update system behaviors while the system is running (i.e., without restarts/reboots and without writing code)
IT News wrote a good article about it.