Towards More Autonomy for Unmanned Vehicles: Situational Awareness and Decision Making under Uncertainty
Lead Research Organisation:
Loughborough University
Department Name: Aeronautical and Automotive Engineering
Abstract
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.
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.
Planned Impact
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.
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.
Organisations
- Loughborough University (Lead Research Organisation)
- Defence Science and Technology Laboratory (Co-funder)
- Sellafield (United Kingdom) (Co-funder)
- Schlumberger (United Kingdom) (Co-funder)
- United Kingdom Space Agency (Co-funder)
- BAE Systems (United Kingdom) (Co-funder, Collaboration)
- Network Rail (Co-funder)
Publications
Hunt S
(2014)
A Consensus-Based Grouping Algorithm for Multi-agent Cooperative Task Allocation with Complex Requirements.
in Cognitive computation
Hyondong Oh
(2015)
Coordinated standoff tracking of moving target groups using multiple UAVs
in IEEE Transactions on Aerospace and Electronic Systems
Hyondong Oh
(2015)
Road-map-assisted standoff tracking of moving ground vehicle using nonlinear model predictive control
in IEEE Transactions on Aerospace and Electronic Systems
Katrakazas C
(2018)
A Simulation Study of Predicting Real-Time Conflict-Prone Traffic Conditions
in IEEE Transactions on Intelligent Transportation Systems
Katrakazas C
(2019)
A new integrated collision risk assessment methodology for autonomous vehicles.
in Accident; analysis and prevention
Katrakazas C
(2015)
Real-time motion planning methods for autonomous on-road driving: State-of-the-art and future research directions
in Transportation Research Part C: Emerging Technologies
Ladosz P
(2017)
Trajectory Planning for Communication Relay Unmanned Aerial Vehicles in Urban Dynamic Environments
in Journal of Intelligent & Robotic Systems
Description | A framework based on Bayesian inference has been developed for situation awareness of unmanned vehicles. It is able to incorporate priori information such as maps, geological information systems and traffic rules into onboard sensor measurement to support the safe operation of unmanned vehicles in a complicated uncertain and dynamic environment. The framework is implemented through newly developed particle filtering algorithms. In addition to making a good use of priori information and other knowledge, a distinct feature of the propsoed framewrok is the uncertainty of the provided information is quantified so this leads to decision making with uncertainty awareness. By working with BAE Systems, the proposal framework has been applied to develop two key autonomous functions for unmanned aircraft operation: forced landing for unmanned aircraft, and autonomous taxiing in aerodrome. After the algorithms are designed and implemented, these functions have been first tested in a synthetic simulation environment and then part of the functions have been demonstrated through small scale UAV flight tests. |
Exploitation Route | It is our intention to carry on working with BAE Systems to further refine and develop these important autonomous functions to enable UAV safety operation in civilian airspace. We are also exploring opportunities to bring our findings of the general framework about situation awareness and decision making under uncertainty into intelligent or driverless vehicle area. We have discussed with a few companies including JLR, AVL, LOTUS and Nissan. We are also invited to present our framework on several workshops in autonomous vehicles area to attract possible partners to take the work forward. We have now worked with SMEs in developing autonomous agriculture robots using the navigation and safety functions developed in this project. |
Sectors | Aerospace Defence and Marine Digital/Communication/Information Technologies (including Software) Healthcare Transport |
Description | This was the first major grant we have received from Research Councils which opened opportunities for a number of major funded grants and helped us to build up a significant research profile internationally in autonomous vehicles and generated impact in a wide range of ways. The PI was also awarded the EPSRC Established Career Fellowship in control of robotics and autonomous systems. One area is some research outcome enable us to develop remote sensing capability for precision agriculture based on unmanned areal vehicles. We developed path planning software for ground control stations for agriculture survey which was now implemented by a company and in the trial. We also contributed to a white paper "Agriculture robotics: The future of Robotic Agriculture" (Duckett T, Pearson S, Blackmore S, Grieve B, Chen WH, Cielniak G, Cleaversmith J, Dai J, Davis S, Fox C, From P. Agricultural robotics: the future of robotic agriculture. arXiv preprint arXiv:1806.06762. 2018 Jun 18.) It aimed to reflect our thinking of future UK agriculture sector and influence the UK policy. Significant investment on agriculture technology including robotics and autonomous systems has been made by the UK agencies particularly Innovate UK since, though difficult to know how much influence our white paper had. |
First Year Of Impact | 2018 |
Sector | Agriculture, Food and Drink |
Impact Types | Economic Policy & public services |
Description | ASUR |
Amount | £40,000 (GBP) |
Funding ID | 1014_C1_PH1_028 |
Organisation | Defence Science & Technology Laboratory (DSTL) |
Sector | Public |
Country | United Kingdom |
Start | 03/2015 |
End | 09/2015 |
Description | Autonomous Bayesian search for hazardous sources. CDE Autonomy in hazardous scene assessment competition |
Amount | £50,000 (GBP) |
Funding ID | ACC 101517 |
Organisation | Defence Science & Technology Laboratory (DSTL) |
Sector | Public |
Country | United Kingdom |
Start | 01/2017 |
End | 06/2017 |
Description | Autonomous Search for Chemical Release with a pocket-sized Drone; Phase II Autonomy in Hazardous Scene Assessment |
Amount | £375,000 (GBP) |
Organisation | Defence Science & Technology Laboratory (DSTL) |
Sector | Public |
Country | United Kingdom |
Start | 09/2017 |
End | 09/2018 |
Description | Autonomous landing of a helicopter at sea: advanced control in adverse conditions (AC2) |
Amount | £100,000 (GBP) |
Funding ID | EP/P012868/1 |
Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
Sector | Public |
Country | United Kingdom |
Start | 03/2017 |
End | 06/2018 |
Description | EPSRC/Dstl UDRC |
Amount | £437,908 (GBP) |
Funding ID | EP/K014307/1 |
Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
Sector | Public |
Country | United Kingdom |
Start | 03/2013 |
End | 03/2018 |
Description | Enabling wide area persistent remote sensing for agriculture applications through developing and coordinating heterogenous platforms |
Amount | £1,000,000 (GBP) |
Funding ID | ST/N006852/1 |
Organisation | Science and Technologies Facilities Council (STFC) |
Sector | Public |
Country | United Kingdom |
Start | 04/2016 |
End | 04/2019 |
Description | FollowPV |
Amount | £354,810 (GBP) |
Funding ID | 98378 |
Organisation | Innovate UK |
Sector | Public |
Country | United Kingdom |
Start | 03/2021 |
End | 03/2022 |
Description | Goal-Oriented Control Systems (GOCS): Disturbance, Uncertainty and Constraints |
Amount | £1,599,964 (GBP) |
Funding ID | EP/T005734/1 |
Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
Sector | Public |
Country | United Kingdom |
Start | 02/2020 |
End | 10/2025 |
Description | Innovate UK: Jiangsu-UK Industrial Challenge Programme; AgriRobot: Autonomous agricultural robot system for precision spraying |
Amount | £840,000 (GBP) |
Funding ID | Project Number 104016 |
Organisation | Innovate UK |
Sector | Public |
Country | United Kingdom |
Start | 03/2018 |
End | 02/2020 |
Description | Persistence through Reliable Perching |
Amount | £200,000 (GBP) |
Funding ID | EP/R005494/1 |
Organisation | Engineering and Physical Sciences Research Council (EPSRC) |
Sector | Public |
Country | United Kingdom |
Start | 03/2017 |
End | 02/2018 |
Description | BAE Systems AISP |
Organisation | BAE Systems |
Department | BAE Systems Military Air & Information |
Country | United Kingdom |
Sector | Private |
PI Contribution | Based on the informaiton provided by the BAE Systems, we have defined autonomous taxiing and terminal area operation for unmaned aircraft systems. After fully reviewing the problems and related work, a number of new methods have been developed including predicting the location of other aircraft with specified level of confidence and combing maps and other informaiton with camera observation for nagivation and safety assessment in autonomous taxiing. |
Collaborator Contribution | BAE Systems has regular meetings with the Team working at Loughborough and has appointed two technical officers working with us. Guidance on the problem formulation and real operation constraints have been provided. Assessment and feedback of the research progress have regularly made by BSE Systems. BAE Systems also helped to set up the research link with Virtual Engineering Centre at Liverpool for research colalborations in this area. Several data sets using virtual simulation environment have been collected and provided to Loughboorugh Team for algorithm development. In the summer of 2015, BAE Systems has conducted various filed tests and collected data from an airfield for the project. |
Impact | New situational awareness algorithms for terminal area operation of unmanned aircraft systems have been developed and the corresponding simulator has been developed. These algorithms have been implemented in the simulator and demonstrated to BAE Systems. This lays out the further work in this area for improving the accuracy and reducing uncertainty of the predicting the behaviours of other airspace users. The work is of multidisciplinary nature and is the combinations of aerospace and computer science. |
Start Year | 2012 |
Description | 3rd Intelligent Robots and Automation(Germany) |
Form Of Engagement Activity | A talk or presentation |
Part Of Official Scheme? | No |
Geographic Reach | International |
Primary Audience | Professional Practitioners |
Results and Impact | Given a plenarytalk on 3rd Symposium on Intelligent Robots and Automation, Germany, about autonomous search of sources of airborne hazard substance release using robotics and unmanned aerial vehicles. |
Year(s) Of Engagement Activity | 2020 |
Description | Autonomous systems theme meeting |
Form Of Engagement Activity | Participation in an activity, workshop or similar |
Part Of Official Scheme? | No |
Geographic Reach | National |
Primary Audience | Professional Practitioners |
Results and Impact | This event is open for all the industrial companies particularly Defenec sectors for improving their awareness of and understanding progess in autonomous system related technologies. As a Co-Chair, I was involved in organising the theme meeting and gave a presentation. It triggers a good level of discussion. Industrial companies and technical officers and advisors in Defence Science and Technology Laboratory (Dstl) have a better understanding of the recent progress in autonomous system technologies cross a number of sectors (air, land, naval). |
Year(s) Of Engagement Activity | 2014 |