Towards More Autonomy for Unmanned Vehicles: Situational Awareness and Decision Making under Uncertainty

It is anticipated that unmanned vehicles will be widely used within military and civilian operations and have a profound influence in our daily life in near future. Before fully realising the potential that unmanned vehicles bring, it is reasonably expected that to make unmanned vehicles accepted by users, the public and regulatory authorities, they shall achieve a similar level of safety as human operated systems. Among many others, a fundamental requirement for an unmanned vehicle is the capability to respond to internal and external changes in a safe, timely and appropriate manner. Therefore, situational awareness and decision making are two of the most important enabling technologies for safe operation of unmanned vehicles. To a large extent, they determine the level of autonomy and intelligence of an unmanned vehicle. Compared with a human driver or pilot residing in the vehicle, a major safety concern is the inevitable reduction in situational awareness of the unmanned vehicle operator remotely located in a control station.

Unmanned vehicles operate in a dynamic, unpredictable environment with incomplete (or inaccurate) sensory information, which creates many challenges in situational awareness and decision making. Probabilistic and bounded approaches are widely used to represent uncertainty with a known distribution or with a known upper and lower bounds respectively. Situational awareness includes the perception of the objects in the environment within a volume of time and space, the comprehension of their meaning and the projection of their status in the near future. For example, in projection of the near status of moving objects of interest, any initial uncertainty associated with perception and comprehension will expand exponentially with the increase of the projection time span. However, it is possible to significantly reduce the uncertainty by utilising the information in the world model such as the operation environment, the Rules of the Road (or of the Air) and the properties of an identified object. For probabilistic uncertainty, this makes the Gaussian distribution assumption invalid, which is fundamental for most of the current statistical approaches such as Kalman filtering. Under the Gaussian distribution assumption, the estimated state about a moving object can be presented by its mean with a variance, and a symmetric uncertain region can be defined with the mean located at the centre (under a specified confidence level such as 99%). The introduction of knowledge (e.g. constraints due to the roadway layout) makes this not true anymore. To address the challenge of non-Gaussian distributions imposed by making use of information from the world model, a rigorous Bayesian learning framework will be developed for pooling all the knowledge from the world model and measurement data to provide a better estimate of the environment, and to propagate the uncertain regions with projection time. Reachability analysis will be developed for bounded uncertainty for worst case analysis, where the uncertainty will be reduced using constraints from the world model. Hazard analysis will be carried out to identify any potential risk. The key idea is to take a proactive approach to prevent any emergent situation through improving situational awareness reasoning and decision making. The estimates and associated uncertain region provided by the situational awareness will be fed to novel decision making and planning tools. The research activities will be strongly supported and verified by experimental tests on small scale ground and aerial vehicles. This project aims to significantly improve the level of safety of unmanned vehicle operation and to bridge the gap between the development and deployment of unmanned vehicles in real world applications, which is a strategically important area for new business growth.

Although unmanned vehicles have the potential to provide huge benefit to the economy, end users and the society, they do impose unprecedented challenges as they are in an uncharted area. Among other concerns such as legal issues and ethics, safety is a paramount consideration for a wide application of unmanned vehicles. In Afghanistan, on 13th Sept., 2009, the American Air Force was forced to shoot down one of its own MQ-9 Reaper aircraft that did not go into failsafe mode after the service lost remote control of the aircraft, and license for patrolling along the Mexico border was suspended by the Federation Aviation Authority (FAA) for a short time due to safety issues.

This Autonomous and Intelligent Systems Programme is to respond to the imperative needs of fundamental research in this emerging business area, backed by an industrial consortium consisting of companies that share the same vision but may have different business interests. Although there is a wide spectrum of unmanned vehicles, each with different operational environments/needs, all the unmanned vehicles face the same challenge, i.e. operating in a dynamic and unpredictable environment. This project aims to tackle the fundamental issues faced by the industrials by improving situational awareness and decision making in a dynamic and uncertain environment so to improve the safety in operating unmanned vehicles. Therefore, all the UK industrials with business interests in unmanned vehicles, in particular the partners, will directly benefit from this project.

The outcomes of this proposed project will assist regulatory authorities to formulate their policies for the operation of unmanned vehicles, helping them to understand the behaviour of unmanned vehicles and the risks and safety issues caused by increasing the level of autonomy. The situational awareness and hazard analysis functions developed in this project will help end users and unmanned vehicles operators to determine proper levels of autonomy in response to the change of real operation scenarios. The public will benefit from a better understanding about the true risk involved in using unmanned vehicles, and the reduced risk due to better onboard situational awareness and decision making functions (e.g. unmanned vehicles will less likely become a hazard to the public). In the long term, the situational awareness and decision making techniques developed in this proposal will help to develop other autonomous systems such as domestic support, health care or other service robots. This would improve quality of life and health care by providing domestic support for society and providing health care for disabled and elderly people living at home.

The academic community will be able to take the results generated by this project to identify new research directions. This project identifies and addresses a number of new academic challenges, for example, non-Gaussian distributions arising from situational awareness in autonomous and intelligent systems, and comprehension, projection and hazard analysis for unmanned vehicles. This project takes a true multi-disciplinary effort in tackling these challenges, which will promote interdisciplinary collaboration and cross-fertilise in a number of areas, e.g. mathematics/statistics, autonomous/intelligent systems, transport, computational intelligence and safety engineering. It supports and contributes to the wider academic community of unmanned vehicles in the UK and worldwide, where further academic research in the relevant areas will ultimately lead a pathway towards economic/societal impact as highlighted above. The public and other interested parties (non-academic) will be informed about the results of this project via the project web site, newsletters and media reports through Lougborough University's Public Relations Office.