Reconfigurable computing platform for small-scale resource-constrained robot.

Abstract

Specific applications often require robots of small size for reasons such as costs, access, and stealth. Small-scale robots impose constraints on resources such as power or space for modules, but they still require great functionality to do challenging tasks such as surveillance, urban search and rescue, application-specific sensing, robotic assembly, etc. This thesis develops a reconfigurable computing platform for small-scale resource-constrained robots that allows rapid deployment of available hardware and software for a specific task. Resource-adaptive control is introduced where control parameters can be changed with respect to the resource usage such as power consumption, area, or execution speed, as well as plant change. The use of a Field Programmable Gate Array (FPGA) is essential in providing the flexibility in hardware for both sensor interfacing and hardware-accelerated computation. In this study, reconfiguration is achieved by two steps; static reconfiguration and dynamic reconfiguration. This thesis utilizes reconfiguration technology in order to solve issues on resources and functionality. Prior to executing a task, a robot needs to be equipped with necessary sensors and actuators. This thesis introduces a new scheme of configuring a robot system before deploying a robot into a field, which is called static reconfiguration. Static reconfigurability of the hardware manifests itself in the form of a "morphing bus" architecture that permits the modular connection of various sensors. It is a novel sensor bus in the fact that no bus interface circuitry is required on a sensor side - the bus "morphs" to accommodate the signals of the sensor. Dynamic reconfiguration or run-time reconfiguration is performed in order to maximize the resource utilization in terms of power, area and speed while the robot is executing tasks. A software architecture for hardware/software dynamic reconfigurability is proposed and it provides for the reallocation of hardware and software resources at run time as the mobile, resource-constrained robots encounter unknown environmental conditions that render various sensors ineffective. A novel strategy to search a configuration tree is presented and metrics for cost functions in the tree are introduced. Resource-adaptive controller can modify control parameters, or change the order of a plant model, or even choose a different control algorithm by examining resource utilization during dynamic reconfiguration.