– To make a mobile robot with real-time vision system adapt to the highly dynamic environments and emergencies under the real-time constraints, a significant account of processing power is needed. Instead of pushing the limit of software development and computational resources, and to reduce the system computation time and improve system faulttolerance, this paper presents an embedded platform which can dynamically reconfigure a mobile robot system on the fly by integrating Field Programmable Gate Arrays (FPGA) and embedded processors in a system-on-chip (SOC) environment. The BDI agent model is adopted as the unified agent structure, which significantly simplify the HW/SW partitioning and communication. A self-reconfigurable platform is also proposed to improve the hardware flexibility. This proposed embedded framework has been applied to a real-world mobile robot, and the experimental results demonstrate its feasibility and efficiency.