From Virtual World to Reality: Designing an Autonomous ... virtual world to reality: designing an autonomous underwater robot Donald P. Brutzman Computer Science Department, Naval Postgraduate School

  • Published on

  • View

  • Download


  • From virtual world to reality:designing an autonomous underwater robot

    Donald P. BrutzmanComputer Science Department, Naval Postgraduate School

    Monterey California 93943-5000

    (408) 646-2149 work, (408) 646-2595 fax

    AbstractDesign of autonomous underwater robots is particularlydifficult due to the physical and sensor challenges ofthe underwater environment. Inaccessibility duringoperation and low probability of failure recovery makesrobot stability and reliability paramount. Building anaccurate and complete virtual world simulation isproposed as a necessary prerequisite for design of anautonomous underwater robot. A virtual world caninclude actual robot components and models for allother aspects of the world. Robot design can be fullytested using a virtual world and then verified using thereal world. Additional testing can be performed in thevirtual world that is not feasible in the real world.Visualization of robot interactions within a virtual worldpermits sophisticated analysis of robot performance thatis otherwise unavailable. All aspects of world modelingand robot design must be mastered and coordinated inorder to build an authentic virtual world and capableautonomous robot.

    1 ProblemsAutonomous underwater robot design is difficult.Unlike most other mobile robots, underwater robotsmust operate unattended and uncontrolled in a remoteand unforgiving environment. Inaccessibility duringoperation greatly complicates the design and evaluationof system software. In order to ensure completereliability, however, robot software and hardware needto be fully tested in a controlled environment beforeoperational deployment. Such comprehensive testingrequirements cannot be met using a standalonelaboratory robot due to the complexity andunpredictability of interactions that can occur in theactual remote environment. A different approach isneeded which can effectively support research on themany problems facing underwater robot designers.

    Underwater robots are normally termedautonomous underwater vehicles (AUVs), not becausethey are intended to carry people but rather becausethey are designed to intelligently convey sensors andpayloads. AUVs must accomplish complex tasks and

    Submitted to the AAAI Fall Symposium on Applications of ArtificialIntelligence to Real-World Autonomous Mobile Robots, Cambridge,Massachusetts, October 23-25, 1992.

    diverse missions while maintaining stable physicalcontrol with six spatial degrees of freedom. Little or nocommunication with distant human supervisors ispossible. When compared to indoor, ground, airborneor space environments, the underwater domain typicallyimposes the most restrictive physical control and sensorlimitations upon a robot. Underwater robot designrequirements therefore motivate this examination.Considerations and conclusions remain pertinent asworst-case examples in other environments.

    A large gap exists between the projections oftheory and the actual practice of underwater robotdesign. Despite a large number of remotely operatedsubmersibles and a rich field of autonomous robotresearch results (Iyengar and Elfes 1990a, 1990b), fewAUVs exist and their capabilities are limited. Cost,inaccessibility and scope of AUV design restrict thenumber and reach of players involved. Interactions andinterdependencies between hardware and softwarecomponent problems are poorly understood. Testing isdifficult, tedious, infrequent and potentially hazardous.Meaningful evaluation of results is hampered by overallproblem complexity, sensor inadequacies and humaninability to directly observe the robot in situ. Potentialloss of an autonomous underwater robot is generallyintolerable due to tremendous investment in time andresources, likelihood that any failure will becomecatastrophic and difficulty of recovery.

    Underwater robot progress has been slow andpainstaking for many reasons. By necessity mostresearch is performed piecemeal and incrementally. Forexample, a narrow problem might be identified assuitable for solution by a particular artificialintelligence (AI) paradigm and examined in great detail.Conjectures and theories are used to create animplementation which is tested by building a model orsimulation specifically suited to the problem inquestion. Test success or failure is used to interpretvalidity of conclusions. Unfortunately, integration ofthe design process or even final results into a workingrobot is often difficult or impossible. Lack ofintegrated testing prevents complete verification ofconclusions.

    AUV design must provide autonomy, stabilityand reliability with little tolerance for error. Controlsystems require particular attention since closed-form


    From: AAAI Technical Report FS-92-02. Copyright 1992, AAAI ( All rights reserved.

  • solutions for many hydrodynamics control issues areunknown. In addition, AI methodologies are essentialfor many critical robot software components, but theinteraction complexity and emergent behavior ofmultiple interacting AI processes is poorly understood,rarely tested and impossible to formally specify. Betterapproaches are needed to support coordinated research,design and implementation of underwater robots.

    Despite these many handicaps, the numerouschallenges of operating in the underwater environmentforce designers to build robots that are truly robust,autonomous, mobile and stable. This fits well with amotivating philosophy of Hans Moravec: ".. solvingthe day to day problems of developing a mobileorganism steers one in the direction of generalintelligence... Mobile robotics may or may not be thefastest way to arrive at general human competence inmachines, but I believe it is one of the surestroads." (Moravec 1983)

    2 Multiple Interacting ProcessesDesigning an AUV is complex. Many capabilities arerequired for an underwater mobile robot to act capablyand independently. Stable physical control, motioncontrol, sensing, motion planning, mission planning,replanning and failure recovery are example softwarecomponents that must be solved individually fortractability. The diversity and dissimilarity of thesemany component subproblems precludes use of a singlemonolithic AI paradigm.

    Distributed AI usually addresses specificationsand protocols between similar autonomous agentsworking cooperatively on global problems. Hybridreasoning often refers to novel combinations of two orthree techniques to improve overall performance whensolving a single problem type. Neither definitionappears suitable for general robot control. Multipledissimilar AI processes must interact in an intelligentmanner to achieve the robust capabilities and multiplebehaviors needed by a mobile robot (Elfes 1986). Avariety of robot architectures have been proposed anddeveloped to provide the control framework underwhich multiple AI processes can interact. A briefdiscussion of current robot architectures is thereforeuseful to clarify the scope of robot design issues.

    Robot architectures can be classified over aspectrum that ranges from hierarchical to reactive(Byrnes et al. 1992). Hierarchical architectures aredeliberative, symbolic, structured, "top down,"goal-driven, have explicit focus of attention and areoften implemented using backward inferencing.Hierarchical approaches typically contain world modelsand use planning and search techniques to achievestrictly defined goals. Hierarchical architectures tend tobe somewhat rigid, unresponsive in unpredictedsituations and computation-intensive, yet remain capableof highly sophisticated performance.

    Reactive architectures are subsumptive,"bottom up," sensor-driven, layered and may often becharacterized by forward inferencing. Reactivearchitectures attempt to combine robust subsumingbehaviors while avoiding dynamic planning and worldmodels. Reactive architectures appear to behavesomewhat randomly and achieve success withoutmassive computations by using well-consideredbehaviors that tend to lead to task completion(Brooks 1986). Scaling up to complex missions isdifficult. Stability and deterministic performance iselusive.

    It is interesting to note that numerous robotarchitecture researchers have recently proposed hybridcontrol architectures (Kwak et al. 1992) (Bonasso et al.1992) (Bellingham and Consi 1990) (Payton and Bihari1991) (Spector and Hendler 1991). A common themein these proposals is integrating the long-termdeliberation, planning and state information found inhierarchical approaches with the quick reaction andadaptability of subsumptive behaviors. Individualweaknesses of hierarchical and reactive architecturesappear to be well-balanced by their respective strengths.

    Stability and reliability deserve repeated mentionin the context of multiple interacting processes. Controlsystem considerations are often overlooked under theguise of simplifying assumptions that hide importantreal world restrictions and pitfalls. Robot survivabilitydictates that physical and logical behavior must alwaysconverge to a stable yet adaptive set of states.Divergence, deadlock, infinite loops and non-lineardynamic behavior must be detectable and controllable.Real-time operating constraints on sensing, processing,action and reaction must be similarly resolved.Stability prerequisites become similarly important forground robots as they progress from structured tounrestricted environments.

    3 Virtual WorldThe broad requirements of underwater robot designprovide a strong argument against piecemeal designverification. Individual component simulations are notadequate to develop effective AI-based systems orevaluate overall robot performance.

    Virtual world systems provide the capability tosee and interact with distant, expensive, hazardous ornon-existent three-dimensional environments (Zyda andPratt 1992). A virtual world is intended to providecomplete functionality of the target environment in thelaboratory. A virtual world can provide adequatesimulation scope and interaction capability to overcomethe inherent design handicaps imposed when building aremote robot to operate in a hazardous environment.Construction of a virtual world for robot developmentand evaluation is hereby proposed as a necessaryprerequisite for successful design of a complex remoterobot such as an AUV.


    From: AAAI Technical Report FS-92-02. Copyright 1992, AAAI ( All rights reserved.

  • A virtual world which is used to recreate everyaspect of the environment external to the robot mustalso include robot sensors and analog devices (such asthrusters and rudders) which are impossible torealistically operate in a laboratory. Interactionsbetween software processes, vehicle hardware and thereal world must all be comprehensively modeled andmutually consistent. Robot physical behavior andsensor interactions must be adequately simulated. Therobot itself is directly plugged into the virtual worldusing normal sensor and actuator connections. Thedifference between operation in a virtual world or anactual environment must be transparent to the robot inorder to be effective. Successful implementation of thevirtual world can be validated by identical robotperformance in each domain.

    The potential value of general world simulatorshas been previously recognized (Moravec 1988).Certain underwater robots already benefit from theavailability of capable simulators (Pappas et al. 1991)(Brutzman 1992a) (Brutzman et al. 1992b). However,once simulation sophistication reaches that of a virtualworld, interesting things become possible. Emergentbehavior from interaction between multiple AIprocesses and the environment becomes evident.Sensor interactions can be repeated indefinitely in orderto develop new analysis algorithms and achievefine-tuned sensor performance. Machine learning basedon massive repetitive training becomes feasible and canbe conveniently monitored. Potentially fatal scenarioscan be attempted without risk to robot, human orenvironment.

    A plethora of interrelated requirements requiresmastering all aspects of world modeling and robotdesign in order to build both an authentic virtual worldand a capable autonomous robot. Traditionally onlycomponent software processes were integrated into therobot architecture; now corresponding validationsimulations must also be integrated into the virtualworld. Adequate simulation of a comprehensiveunderwater virtual world is possible since precisemodels are available for kinematics (Badler et al. 1991)(Zyda et al. 1991) (Zyda et al. 1990), hydrodynamics(Yuh 1990) (Abkowitz 1969), sonar response (Etter1991), and other objects in the underwater environment(Pentland 1990). Characteristics of the underwatervehicle physical components which require modelingcan be handled on a case basis (Pappas 1991).Depending upon planned missions and AUV hull form,interactive terrain modeling (Pratt et al. 1992) andprecise hydrodynamics modeling are areas likely torequire further investigation prior to implementation.Virtual world construction requires significantcoordination and cross-disciplinary efforts.

    From a design viewpoint, models replacefunctionality otherwise found only in the real world.Identical replication of every world characteristic is

    impossible but partial modeling of all pertinent worldaspects is necessary. Exact reproduction of real worldbehavior might even be undesirable in some cases. Forexample, a sonar model might provide perfect rangeand intensity values that can be augmented bystatistically adjustable noise and errors. Initial trainingor evaluation of a new sensor algorithm is bestperformed using the "perfect" error-free model. Furtheranalysis using quantifiable noise and errors will providenew insight into algorithm robustness and adaptability.Because it has been coupled with the robots ability tomove freely throughout a virtual world, overalleffectiveness of this example AI-based sensor processis likely to be superior to that obtainable by training inthe real world.

    Models in virtual worlds can be further studiedto examine the benefits of controllable error precision,addition of uncertainty, incorporation and extension ofactual sensor data, and maintaining internal worldconsistency throughout mutual interactions betweenindividual component models and the multifacetedautonomous robot. Such study also clarifiesunderstanding of robot design problems andspecifications.

    4 VisualizationA robot interacting within a virtual world permitscomplete visualization of all aspects of both robot andvirtual environment. Visualization of robotperformance is essential for evaluating both the precisedetails of low-level execution and the broad suitabilityof high-level behaviors. Visualization of robotinteractions permits sophisticated analysis that is notpossible using traditional test methods such asindividual software module evaluation, direct robotobservation or post-mission reconstruction.

    Human beings are visually oriented. Being ableto see and control location and time in a moving pictureallows us to quickly and intuitively understand data setsof much higher dimensionality than is otherwisepossible. Scientific visualization of a robot in itssurroundings can greatly improve our comprehension ofwhat is really going on. Being able to "look" over arobots shoulder or "see" through a robots sensorsprovides completely new perspectives. Addition ofaural cues provides a further order-of-magnitudeincrease in perceptual bandwidth. Visualizationtechniques greatly improve the effectiveness of complexAI process design and development, and can evenenable successful AI-based applications that mightotherwise be infeasible (Brutzman et al. 1992c).

    5 ImplementationConstructing a virtual world and designing anautonomous underwater robot are big jobs. This sectionoutlines some design considerations for implementingthem in combination.


    From: AAAI Technical Report FS-92-02. Copyright 1992, AAAI ( All rights reserved.

  • Youve got to get your arms around the world!A robot development team has to understand thefundamental basis of every virtual world componentand every robot component. All efforts must beconsidered in relation to the virtual world models andoverall robot architecture. Most research results arepartial and developed in isolation, which may be whycurrent autonomous robots rarely achieve a level ofperformance that can be considered intelligent. Themany details of world modeling and robot design mustbe addressed in a comprehensive, coordinated manneror the overall problem remains unbounded.

    A virtual world ought to include interfaces forthe actual robot or have duplicate robot processinghardware directly connected. As mentioned previously,which environment is active should not be evident tothe robot. If robot behavior is affected by substitutionof a virtual world for the actual world then laboratoryresults become suspect. Reverification of laboratoryresults in the real world due to inadequacies in thevirtual world will be time-consuming, ambiguous andpossibly contradictory. Identical robot performance ineach domain allows development of a single version ofrobot software, a valuable software engineeringconsideration.

    Virtual world simulation and visualizationgraphics rendering are computationally expensive. Adistributed implementation can solve real-timeprocessing bottlenecks by exploiting the implicitparallelism that is available over networkedworkstations. A distributed approach also permits rapidaccess to multiple versions of robot control softwareand addition of an indefinite number of virtual robotsinto the virtual world. A side benefit of a networkedimplementation is accessibility for remote research.The theoretical basis and construction of virtual worldsremains an area of active investigation (Rheingold1991).

    Theory will continue to outstrip the practice ofautonomous underwater robotics unless improveddesign methodologies are employed. Overall problemcomplexity and the importance of emergent behaviordictate that actual robot implementations need to beused to confirm broad theoretical conclusions.

    Many of the conclusions reached in this paperare based on work accomplished with the NavalPostgraduate School AUV (Healey et al. 1992)(Brutzman and Compton 1991). Using an actual robotwith measurable performance greatly clarifies researchconclusions. Building a virtual world that matches theenvironment used by an actual robot is expected toaccelerate robotic research progress and providecredible, verifiable results.

    6 ConclusionsUse of a virtual world can greatly improve developmentof multiple interacting AI-based processes that are thecritical components of autonomous underwater robots.Construction of an underwater virtual world is feasible.Scientific visualization of robot interactions in a virtualworld can improve our perceptual capabilities byseveral orders of magnitude, enabling more effectiveresearch progress. Every aspect of virtual world andautonomous robot design must be considered andimplemented in a coordinated manner.

    AcknowledgmentsI thank Michael J. Zyda, Yutaka Kanayama, Robert B.McGhee, Anthony J. Healey and David R. Pratt fortheir contributions.

    ReferencesAbkowitz, M.A. 1969. Stability and Motion of OceanVehicles, MIT Press, Cambridge, Massachusetts.

    Badler, Norman I., Barsky, Brian A. and Zeltzner, David, ed.1991. Making Them Move: Mechanics, Control andAnimation of Articulated Figures, Morgan KaufmannPublishers Inc., San Mateo, California.

    Bellingham, J.G. and Consi, T.R. 1990. "State ConfiguredLayered Control," Proceedings of the First IARP Workshopon Mobile Robots for Subsea Environments, Monterey,California, October 23-26, 1990, pp. 75-80.

    Bonasso, R. Peter, Yoerger, Dana R. and Stewart,W. Kenneth. 1992. "Semi-Autonomous Underwater Vehiclesfor Shallow Water Mine Clearing," IEEE OceanicEngineering Society Symposium on Autonomous UnderwaterVehicles, Washington DC, June 2-3, 1992, pp. 22-28.

    Brooks, Rodney A. 1986. "A Robust Layered Control Systemfor a Mobile Robot," IEEE Journal of Robotics andAutomation, vol. RA-2 no. 1, March 1986, pp. 14-23.

    Brutzman, Donald P. 1992a. NPS AUV Integrated Simulator,Masters Thesis, Naval Postgraduate School, Monterey,California, March 1992.

    Brutzman, Donald P., Kanayama, Yutaka, and Zyda,Michael J. 1992b. "Integrated Simulation for RapidDevelopment of Autonomous Underwater Vehicles",Proceedings of the IEEE Oceanic Engineering SocietyConference AUV 92, Washington DC, June 2-3, 1992,pp. 3-10.

    Brutzman, Donald P., Compton, Mark A. and Kanayama,Yutaka. 1992c. "Autonomous Sonar Classification usingExpert Systems," Proceedings of the IEEE OceanicEngineering Society Conference OCEANS 92, Newport,Rhode Island, October 26-29, 1992.


    From: AAAI Technical Report FS-92-02. Copyright 1992, AAAI ( All rights reserved.

  • Brutzman, Donald P. and Compton, Mark A. 1991. "AUVResearch at the Naval Postgraduate School," Sea Technology,vol. 32 no. 12, December 1991, pp. 35-40.

    Byrnes, R.B., MacPherson, D.L., Kwak, S.H., McGhee, R.B.and Nelson, M.L. 1992. "An Experimental Comparison ofHierarchical and Subsumption Software Architectures forControl of an Autonomous Underwater Vehicle," IEEEOceanic Engineering Society Symposium on AutonomousUnderwater Vehicles, Washington DC, June 2-3, 1992,pp. 135-141.

    Elfes, Alberto. 1986. "A distributed control architecture for anautonomous mobile robot," Artificial Intelligence,vol. 1 no. 2.

    Etter, Paul C. 1991. Underwater Acoustic Modeling:Principles, Techniques and Applications, Elsevier AppliedScience, London, England.

    Healey, A.J., McGhee, R.B., Cristi, F., Papoulias, F.A.,Kwak, S.H., Kanayama, Y., Lee, Y., Shukla, S. and Zaky, A.1992. "Research on Autonomous Underwater Vehicles at theNaval Postgraduate School," Naval Research Reviews, NavalResearch Laboratory, Washington DC, vol. XLIV no. 3.

    Iyengar, S. Sitharama and Elfes, Alberto, ed. 1991.Autonomous Underwater Robots: Perception, Mapping andNavigation, volume 1, IEEE Computer Society Press,Los Alamitos, California.

    Iyengar, S. Sitharama and Elfes, Alberto, ed. 1991.Autonomous Underwater Robots: Control, Planning andArchitecture, volume 2, IEEE Computer Society Press,Los Alamitos, California.

    Kwak, S.H., McGhee, R.B. and Bihari, T.E. 1992. "RationalBehavior Model: A Tri-level Multiple Paradigm Architecturefor Robot Vehicle Control Software," technical reportNPS-CS-92-003, Naval Postgraduate School, Monterey,California, March 1992.

    Moravec, Hans. 1983. "The Stanford Cart and the CMURover," Proceedings of the IEEE, vol. 71 no. 7, July 1983,pp. 872-884.

    Moravec, Hans. 1988. Mind Children, Harvard UniversityPress, Cambridge Massachusetts, p. 48.

    Pappas, George, Shotts, William, OBrien, Mack and Wyman,William. 1991. "The DARPA/Navy Unmanned UnderseaVehicle Program," Unmanned Systems, vol. 9 no. 2,Spring 1991, pp. 24-30.

    Payton, David W. and Bihari, Thomas E. 1991. "IntelligentReal-Time Control of Robotic Vehicles," Communications ofthe ACM, vol. 34 no. 8, August 1991, pp. 49-63.

    Pentland, Alex P. 1990. "Computational Complexity VersusSimulated Environments," Computer Graphics Special Issue:1990 Symposium on Interactive 3D Graphics, Snowbird, Utah,March 25-28, 1990, ACM Press, New York.

    Pratt, David R., Zyda, Michael J., Mackey, Randall L. andFalby, John S. 1992. "NPSNET: A Networked VehicleSimulation with Hierarchical Data Structures," Proceedings ofthe Image VI Conference, Image Society Inc., Scottsdale,Arizona, July 14-17, 1992, pp. 216-225.

    Rheingold, Howard. 1991. Virtual Reality, Summit Books,New York.

    Spector, Lee and Hendler, James. 1991. "The SupervenienceArchitecture," AAAI Fall Symposium on Sensory Aspects ofRobotic Intelligence, Asilomar Conference Center, PacificGrove, California, November 15-17, 1991, pp. 93-100.

    Yuh, J. 1990. "Modeling and Control of Underwater RoboticVehicles," IEEE Transactions on Systems, Man andCybernetics, vol. 20 no. 6, November/December 1990,pp. 1475-1483.

    Zyda, M.J., McGhee, R.B., Kwak, S.H., Nordman, D.B.,Rogers, R.C. and Marco, D. 1990. "Three-DimensionalVisualization of Mission Planning and Control for the NPSAutonomous Underwater Vehicle," IEEE Journal of OceanicEngineering, vol. 15 no. 3, July 1990, pp. 217-221.

    Zyda, Michael J., Jurewicz, Thomas A., Floyd, Charles A.and McGhee, Robert B. 1991. "Physically Based Modeling ofRigid Body Motion in a Real-Time Graphical Simulator,"unpublished paper, Naval Postgraduate School, Monterey,California, September 1991.

    Zyda, Michael J. and Pratt, David R. 1992. "NPSNET Digest:A Look at a 3D Visual Simulator for Virtual WorldExploration and Experimentation," Proceedings of the 1992EFDPMA Conference on Virtual Reality, Washington DC,June 1-2, 1992.


    From: AAAI Technical Report FS-92-02. Copyright 1992, AAAI ( All rights reserved.


View more >