Sustained Autonomy through Coupled Plan-based Control and World Modelling with Uncertainty

Lead Research Organisation: Heriot-Watt University
Department Name: Sch of Engineering and Physical Science

Abstract

Sustained autonomous behaviour requires a system that is robust to uncertainty, both at the low level of interactions between actuators and sensors and its environment, but also at the intermediate level of sensory perception and interpretation, action dispatch and execution monitoring and, at the highest level of planning, action selection, plan modification and world modelling. In this project we bring together a team of experts with complementary and linked skills and experience, from robotics and sensor data processing, from planning and from reasoning under uncertainty. Our goal is to combine these areas in order to build and demonstrate a robust approach to sustained autonomy, coupling plan-based control to the construction of world models under constraints on resources and under uncertainty.

We plan to demonstrate the approaches in an underwater environment, using Autonomous Underwater Vehicles (AUVs), performing inspection and investigation missions. These missions share many features with space exploration, the use of autonomous Unmanned Aerial Vehicles (UAVs) for track-and-target missions and investigation of terrestrial hazardous sites, such as nuclear waste storage sites. In all of these case, communication between a human supervisor and the autonomous system is often tightly constrained. This is particularly true of deep space missions (for example, Mars missions face transmission delays of about 15 minutes, but windows might consist of a just two 30 minute slots in 24 hours). However, in aerial observation missions involving multiple assets the need for rapid responses in the control of fast moving vehicles reacting to agile targets also leads to bandwidth constraints for a single human controller attempting to manage and coordinate the mission. Hazardous sites, particularly those subject to radiation emissions, often contain communication black-spots where vehicles must operate without human intervention over extended periods. The underwater setting also imposes limits on communication due to the physical difficulties in transmitting control signals over significant distances.

Many of these missions involve multiple assets, often mounting different capabilities. Space missions might combine orbital observing assets, ground-based landers or rovers, possibly aerial vehicles (in some settings) and even astronauts, each offering different subsets of capabilities. Aerial observation might combine slower but more agile vehicles with others that are fast but less manoeuverable, while mounted imaging systems might exploit different wavelengths (visible, infrared, radar) and vehicles might offer other capabilities. We intend to explore the use of multiple assets, including the coordination of AUVs mounting different sensors and actuators.

Uncertainty offers different challenges according to environment. Many space environments have relatively predictable dynamics (although Martian winds are one example of a highly dynamic and uncertain factor), but aerial observation missions operate in highly dynamic and unpredictable environments: both atmospheric conditions and target behaviours can be a source of dynamic uncertainty. The underwater environment is also highly dynamic: phenomena such as currents will act as useful proxies for similar dynamic sources of uncertainty in other execution environments. Other sources of uncertainty arise from the inherent limitations of sensors and actuators and our ability to process and interpret the data that can be recovered from these devices. One of the biggest challenges in achieving robust autonomy is in recognising that uncertainty about the state of the world and the state of execution of a plan is inevitable, but the form of that uncertainty is itself an unknown.

By combining techniques in modelling and reasoning about uncertainty, plan modification and sensor data perception and interpretation, we propose to build a robust approach to autonomous systems control.

Publications

10 25 50

publication icon
Baxter R (2015) Human behaviour recognition in data-scarce domains in Pattern Recognition

publication icon
De Carolis V (2018) Runtime Energy Estimation and Route Optimization for Autonomous Underwater Vehicles in IEEE Journal of Oceanic Engineering

publication icon
Francesco Maurelli (2014) Cognitive knowledge representation under uncertainty for autonomous underwater vehicles in ICRA'14 IEEE Hong Kong, Workshop on Persistent Autonomy for Underwater Robotics

publication icon
Houssineau J (2016) A Unified Approach for Multi-Object Triangulation, Tracking and Camera Calibration in IEEE Transactions on Signal Processing

publication icon
Lane D (2013) Marine Robot Autonomy

publication icon
Lee C (2013) SLAM With Dynamic Targets via Single-Cluster PHD Filtering in IEEE Journal of Selected Topics in Signal Processing

publication icon
Maurelli F. (2013) Probabilistic approaches in ontologies: Joining semantics and uncertainty for AUV persistent autonomy in OCEANS 2013 MTS/IEEE - San Diego: An Ocean in Common

publication icon
Maurelli F. (2013) Pose-based and velocity-based approaches to autonomous inspection of subsea structures in OCEANS 2013 MTS/IEEE - San Diego: An Ocean in Common

publication icon
Saigol Z.A. (2013) Facilitating cooperative AUV missions: Experimental results with an acoustic knowledge-sharing framework in OCEANS 2013 MTS/IEEE - San Diego: An Ocean in Common

 
Description Using new methods of storing information about a robot and its world in a semantic way that can be used to inform autonomous onboard planning

This give the robot the ability to re-plan its activities on the fly when unexpected events occur. Topical development in RAS
Exploitation Route Publication
Commercialisation
Outreach eg at science festivals
Follow on funding for further development, in particular ORCA Hub and follow on research with industrial sponsor Schlumberger
Sectors Aerospace, Defence and Marine,Agriculture, Food and Drink,Construction,Digital/Communication/Information Technologies (including Software),Education,Energy,Environment,Healthcare,Government, Democracy and Justice,Manufacturing, including Industrial Biotechology,Culture, Heritage, Museums and Collections,Retail,Security and Diplomacy,Transport

 
Description The project outputs have contributed to Govt policy in developing national strategy for RAS including Sector Deal to for BEIS They have further led to follow on funding from EU sources and £35M EPSRC ORCA Hub
Sector Aerospace, Defence and Marine,Education,Energy,Government, Democracy and Justice
Impact Types Policy & public services

 
Description CSA's Blackett Reviews of Robotics and Autonomous Systems
Geographic Reach National 
Policy Influence Type Gave evidence to a government review
Impact CCAV Set up in Dept Transport Increased EPSRC and iUK investments in RAS Increasing use of SBIR as smart procurement to develop the innovation pipeline in RAS £200M of Govt investment around RAS2020 Strategy
 
Description Gave evidence to House of Lords Inquiry on Autonomous Vehicles
Geographic Reach National 
Policy Influence Type Gave evidence to a government review
 
Description Jiangmen Science City Foundation and Scientific Advisor Invitation
Geographic Reach Multiple continents/international 
Policy Influence Type Participation in a advisory committee
 
Description Lead preparation of Lloyds Register Foundation Foresight Review in Robotics and Autonomous Systems
Geographic Reach Multiple continents/international 
Policy Influence Type Participation in a national consultation
 
Description Met with Cabinet Secretary and a variety of Civil Servants to inform and demonstrate about potential for Robotics
Geographic Reach Local/Municipal/Regional 
Policy Influence Type Gave evidence to a government review
 
Description Ministerial Round Table to Found UK Robotics and Autonomous Systems Sector Council
Geographic Reach National 
Policy Influence Type Participation in a national consultation
Impact Continuing strategy development from 2014 RAS2020 Strategy. This contributed to foundation of the industrial strategy challenge fund, £450m of Govt spend on RAS R&D, and over £1billion of industry investment including £250m of VC investment in 2016-2018.
 
Description Presentation and advice to Cabinet Secretary and Heads of Govt Dept Horizon Scanning on opportunities for Govt productivity with RAS and Smart Procurement
Geographic Reach National 
Policy Influence Type Gave evidence to a government review
 
Description RAS H2020 Strategy, Interaction with BIS and Treasury on RAS
Geographic Reach National 
Policy Influence Type Implementation circular/rapid advice/letter to e.g. Ministry of Health
URL https://connect.innovateuk.org/web/ras-sig
 
Description Submitted a Draft Sector Deal for RAS to Secretary of State
Geographic Reach National 
Policy Influence Type Gave evidence to a government review
 
Description invited by UK Government to stand up and lead a RAS Sector Council and to prepare a RAS Sector Deal as part of the Govt Industrial Strategy
Geographic Reach National 
Policy Influence Type Participation in a national consultation
URL https://www.gov.uk/government/consultations/building-our-industrial-strategy
 
Description Cooperative Control of Drilling Equipment
Amount £86,080 (GBP)
Organisation Schlumberger Limited 
Department Schlumberger Oilfield UK plc
Start 09/2015 
End 08/2021
 
Description EU Marine Robots
Amount € 5,000,000 (EUR)
Organisation European Commission 
Sector Public
Country European Union (EU)
Start 01/2018 
End 12/2021
 
Description EUMarineRobots
Amount € 4,998,736 (EUR)
Funding ID 731103 
Organisation European Commission H2020 
Sector Public
Country Belgium
Start 03/2018 
End 02/2021
 
Description Framework7
Amount £6,665,680 (GBP)
Organisation European Commission 
Department Seventh Framework Programme (FP7)
Sector Public
Country European Union (EU)
Start 01/2014 
End 12/2017
 
Description Framework7
Amount £348,160 (GBP)
Organisation European Commission 
Sector Public
Country European Union (EU)
Start 09/2012 
End 09/2015
 
Description H2020
Amount € 170,000 (EUR)
Organisation European Commission 
Sector Public
Country European Union (EU)
Start 01/2016 
End 12/2019
 
Description H2020
Amount € 150,000 (EUR)
Organisation EU-T0 
Sector Public
Country European Union (EU)
Start 03/2016 
End 12/2016
 
Description Interactive robotic inspection strategies using unstructured data
Amount £115,400 (GBP)
Organisation Renishaw PLC 
Sector Private
Country United Kingdom
Start 09/2015 
End 08/2019
 
Description STRONGMAR - STRengthening MARritime Technology Research Center
Amount € 999,203 (EUR)
Funding ID 692427 
Organisation European Commission 
Sector Public
Country European Union (EU)
Start 01/2016 
End 12/2018
 
Description The development of multi-sensor fusion algorithms for underwater pipeline position estimation by an AUV at close range
Amount £162,540 (GBP)
Organisation Kawasaki Heavy Industries, Ltd. 
Start 09/2015 
End 08/2019
 
Description Queensland University of Technology, Brisbane 
Organisation Queensland University of Technology (QUT)
Country Australia 
Sector Academic/University 
PI Contribution Research and training collaboration
Collaborator Contribution Research and training collaboration
Impact Nil.
Start Year 2018
 
Description State Key Laboratory in Robotics, Shenyang Institute of Automation, China 
Organisation Chinese Academy of Sciences
Country China 
Sector Public 
PI Contribution Research and training collaboration.
Collaborator Contribution Research and training collaboration.
Impact A collaboration Memorandum of Understanding has been signed with the Institute in March 2018.
Start Year 2018
 
Description University of New South Wales, Sydney 
Organisation University of New South Wales
Country Australia 
Sector Academic/University 
PI Contribution Research and training collaboration
Collaborator Contribution Research and training collaboration
Impact Nil.
Start Year 2017
 
Description University of Western Australia, Perth, Australia 
Organisation University of Western Australia
Country Australia 
Sector Academic/University 
PI Contribution Research and training collaboration
Collaborator Contribution Research and training collaboration
Impact Nil
Start Year 2017
 
Description Beijing Round Table with Major Chinese Companies 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Industry/Business
Results and Impact Round table developing Chinese links with major corporations to promote British prosperity and technology in RAS, the National ROBOTARIUM and seek sponsorship an inward investment
Year(s) Of Engagement Activity 2019
 
Description Presentation at Hong Kong Science and Technology Park 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Industry/Business
Results and Impact Round table and meetings with Hong Kong Science and Technology Park, developing collaborative links to National ROBOTARIUM and teaming discussions, learning from their business model and activities
Year(s) Of Engagement Activity 2019