A Mobile Vision System with Reconfigurable Intelligent Agents

Performing face detection and tracking on a mobile robot in a dynamic environment is a challenging task with the real-time constraints. To realize a natural reactive behavior of the mobile robot, some efficient algorithms are applied for face detection and tracking due to the limited onboard computation power. Instead of pushing the limit of software development and the computational resources by implementing these algorithms on a software platform, a reconfigurable System-on-Chip (SoC) platform is adopted to achieve the higher real-time performance. A BDI intelligent agent model is proposed as a unified structure for both hardware and software. The real-world experimental results on a mobile vision system for face detection and tracking demonstrate the feasibility and efficiency of the reconfigurable intelligent agent model.