Intelligent Real-time Navigation and Cooperation of Multiple Autonomous Surface and Underwater Robotic Systems

点击翻译按钮获取中文摘要

Unmanned surface and underwater vehicles have many important applications such as security surveillance, environmental monitoring and exploration in rivers, lakes, and seas, particularly in unstructured and hazardous environments. A team of unmanned vehicles could work together to accomplish an assigned task rapidly and efficiently. A multi-robotic system has obvious advantages such as faster operation, higher efficiency, and better reliability than a single robot. The key challenges are the real-time collision-free navigation and efficient cooperation of multiple surface and underwater robots in changing complex environments subject to uncertainties, disturbances and noises, for successful completion of designated tasks. The proposed 5-year research program aims to make significant original and innovative contributions in real-time collision-free navigation and cooperation of multiple autonomous surface and underwater robotic systems, using novel biologically inspired intelligent approaches. To address the key challenge, the proposed research program will focus on: (1) Real-time collision-free intelligent navigation of autonomous surface and underwater robots, including real-time multi-sensor fusion with time synchronization of acquired information from onboard sensors and other available sensed information, and real-time path planning, tracking and control of the robots; (2) Intelligent communication and cooperation of the multiple surface and underwater robots to accomplish a task that is usually multi-objective, including dynamic task assignment subject to uncertainties and disturbances, and efficient communication and cooperation to achieve an overall optimal performance; (3) Extensive theoretical analysis and experimental studies on real robots to evaluate and validate the newly developed approaches in comparison to existing solutions. The proposed research has been motivated by the fact that biological systems, such as fishes and insects, can efficiently sense the dynamic environments and take effective actions using very simple mechanisms; and biological species exhibit collective behaviours and can cooperatively accomplish many complex tasks that are beyond the capabilities of an individual under limited implicit communications. The novelty and anticipated significance of the proposed research will be the provision of new knowledge to the respective research fields and the development of new bioinspired intelligent techniques for real-time multi-sensor fusion, path planning, control, communication, and cooperation of multiple autonomous surface and underwater robots. In addition, it will offer some insights into biologically inspired methodologies for other research areas such as multiple unmanned cars. Furthermore, this research program will provide many opportunities for the training of highly qualified personnel in the areas of robotics and artificial intelligence, and lead to great knowledge transfer and commercial applications.