Multi-sensor architecture development for intelligent systems

The philosophy of research at the University of Texas – Robotics Research Group (RRG) is towards creating a foundation for an open architecture, reconfigurable intelligent machines to meet wide breadth of operational needs. An intelligent system is the one which has complete knowledge of its operating characteristics at all times (updated in real-time) and it can make on-the-fly decisions to adapt itself to the different conditions or present the best possible options to the human decision maker under specified and ranked criteria. The reality of all complex system is that they are inherently non-linear with coupled parameters. The traditional approach dealing with such systems assumes linearized models, imposing conservative bounds on the operational domain and thus limiting performance capability of the system. Recent advancements in sensor technology and availability of computational resources (embedded processing) at low cost have made real-time intelligent control feasible for complex systems. The computational intelligence envisioned in modern intelligent machines will enhance the system performance and will provide capabilities such as criteria based control, identification of incipient faults, condition based maintenance, fault tolerance, and ability to monitor performance parameters in real-time. The first step in this process is to equip a system with a comprehensive suite of sensors. These sensors will provide real-time data and awareness about both, the internal system states and the external/environmental operating conditions. The aim of this work is to establish an argument in favor of using multiple sensors in all complex electro-mechanical systems. The report discusses numerous benefits of a multi-sensor environment with suitable examples and attempts to justify its pressing need in all the existing complex mechanical systems. Case studies for a multi-sensor environment in railroad freight cars and vehicle systems are presented. Sensing requirements in freight train and vehicle systems are evaluated and suitable sensor technology and commercial sensor options are suggested for decision makers. In addition to benefits, challenges in a multi-sensor environment such as sensor noise, cabling complexities, signal processing, communication, data validation and data management, sensor fusion, information integration, maintenance etc. are addressed and best practices to alleviate these complexities are discussed in the report. This effort lays out a foundation for developing a multi-sensor system and will enable computational intelligence and structured decision making in the system.