var bibbase_data = {"data":"\n\n
\n\n \n\n \n\n \n\n \n \n\n \n\n\n\n
\n\n \n\n\n
\n \n\n Excellent! Next, you can embed this page using\n one of several \n options.\n
\n\n
\n \n\n

To the site owner:

\n\n

Action required! Mendeley is changing its\n API. In order to keep using Mendeley with BibBase past April\n 14th, you need to:\n

    \n
  1. renew the authorization for BibBase on Mendeley, and
  2. \n
  3. update the BibBase URL\n in your page the same way you did when you initially set up\n this page.
  4. \n

\n\n

\n \n \n Fix it now\n

\n
\n\n
\n\n\n
\n \n \n
\n
\n \n \n\n \n \n \n \n PARCEL, A Planning and Adaptive Route Computation Engine for Logistics in India.\n \n\n\n \n Rajan, A.; Roy, S.; Chatterjee, A.; Gargay, V. V.; Sharma, V.; and Khandeparker, S.\n \n\n\n \n\n\n\n In . \n \n\n\n\n
\n\n\n \n \n\n \n\n bibtex \n \n \n \n  \n \n abstract \n \n\n \n\n \n\n \n \n \n \n \n \n \n \n\n\n
\n
@InProceedings{icaps16-demo-1,\r\n  author =   {Aruna Rajan and Sourav Roy and Abhranil Chatterjee and Vikas Veshishth Gargay and Varun Sharma and Shivram Khandeparker},\r\n  title =    {PARCEL, A Planning and Adaptive Route Computation Engine for Logistics in India},\r\n  abstract = {The recent boom of e-commerce in India has seen rapid growth of competing businesses that seek to provide better customer shopping experiences at affordable prices. A key component of an online shopping experience is the delivery experience, making last mile delivery one of the costliest and most crucial aspects of e-commerce. Many major ecommerce retailers, such as Flipkart, have developed in-house logistics services that aim to provide highly differentiated delivery at competitive costs. Today, no logistics provider or e-retailer is able to communicate reliable delivery time-windows to customers. To be able to plan for deliveries so accurately, yet cost-effectively, automated planning and scheduling solutions become indispensable. At Flipkart, we have built one such automated planning tool, PARCEL- combining mapping, search, optimisation, and scheduling techniques -, to give our customers superior delivery experience.}\r\n}\r\n\r\n
\n
\n\n\n
\n The recent boom of e-commerce in India has seen rapid growth of competing businesses that seek to provide better customer shopping experiences at affordable prices. A key component of an online shopping experience is the delivery experience, making last mile delivery one of the costliest and most crucial aspects of e-commerce. Many major ecommerce retailers, such as Flipkart, have developed in-house logistics services that aim to provide highly differentiated delivery at competitive costs. Today, no logistics provider or e-retailer is able to communicate reliable delivery time-windows to customers. To be able to plan for deliveries so accurately, yet cost-effectively, automated planning and scheduling solutions become indispensable. At Flipkart, we have built one such automated planning tool, PARCEL- combining mapping, search, optimisation, and scheduling techniques -, to give our customers superior delivery experience.\n
\n\n\n
\n\n
\n\n
\n
\n \n \n\n \n \n \n \n Future State Projection as Planning.\n \n\n\n \n Sohrabi, S.; Udrea, O.; and Riabov, A.\n \n\n\n \n\n\n\n In . \n \n\n\n\n
\n\n\n \n \n\n \n\n bibtex \n \n \n \n  \n \n abstract \n \n\n \n\n \n\n \n \n \n \n \n \n \n \n\n\n
\n
@InProceedings{icaps16-demo-2,\r\n  author =   {Shirin Sohrabi and Octavian Udrea and Anton Riabov},\r\n  title =    {Future State Projection as Planning},\r\n  abstract = {We extend the plan-recognition-as-planning technique to both explain the past and project the future. The Planning Projector helps users understand future possibilities in order to make better decisions.}\r\n}\r\n\r\n
\n
\n\n\n
\n We extend the plan-recognition-as-planning technique to both explain the past and project the future. The Planning Projector helps users understand future possibilities in order to make better decisions.\n
\n\n\n
\n\n
\n\n
\n
\n \n \n\n \n \n \n \n Planning.Domains.\n \n\n\n \n Muise, C.\n \n\n\n \n\n\n\n In . \n \n\n\n\n
\n\n\n \n \n\n \n\n bibtex \n \n \n \n  \n \n abstract \n \n\n \n\n \n\n \n \n \n \n \n \n \n \n\n\n
\n
@InProceedings{icaps16-demo-3,\r\n  author =   {Christian Muise},\r\n  title =    {Planning.Domains},\r\n  abstract = {Commonly used resources for the field of automated planning, such as benchmarks, problem generators, etc., are widespread over the internet. With planning.domains, we aim to (a) collect these resources in a central location; and (b) enable creative possibilities through a consistent interface to the larger planning community. In this demo, we focus on the three main pillars of planning.domains: (1) api.planning.domains– a programmatic interface to all existing planning problems; (2) solver.planning. domains– an open (and extendable) interface to planning-in-the-cloud; and (3) editor.planning.domains– a fully featured editor for planning domains.}\r\n}\r\n\r\n
\n
\n\n\n
\n Commonly used resources for the field of automated planning, such as benchmarks, problem generators, etc., are widespread over the internet. With planning.domains, we aim to (a) collect these resources in a central location; and (b) enable creative possibilities through a consistent interface to the larger planning community. In this demo, we focus on the three main pillars of planning.domains: (1) api.planning.domains– a programmatic interface to all existing planning problems; (2) solver.planning. domains– an open (and extendable) interface to planning-in-the-cloud; and (3) editor.planning.domains– a fully featured editor for planning domains.\n
\n\n\n
\n\n
\n\n
\n
\n \n \n\n \n \n \n \n An AI Planning Tool for Region Wide Urban Traffic Control.\n \n\n\n \n McCluskey, T. L.; Vallati, M.; Chrpa, L.; Tachmazidis, I.; and Magazzeni, D.\n \n\n\n \n\n\n\n In . \n \n\n\n\n
\n\n\n \n \n\n \n\n bibtex \n \n \n \n  \n \n abstract \n \n\n \n\n \n\n \n \n \n \n \n \n \n \n\n\n
\n
@InProceedings{icaps16-demo-4,\r\n  author =   {Thomas L. McCluskey and Mauro Vallati and Lukas Chrpa and Ilias Tachmazidis and Daniele Magazzeni},\r\n  title =    {An AI Planning Tool for Region Wide Urban Traffic Control},\r\n  abstract = {The global growth in urbanisation increases the demand for services including road transport infrastructure, presenting challenges in terms of mobility. Optimising the exploitation of urban road network, while attempting to minimise the effects of traffic emissions, is a great challenge. SimplyfAI is a UK research council grant funded research project which is aimed towards solving air quality problems caused by road traffic emissions. Large cities such as Manchester struggle to meet air quality limits as the range of available traffic management devices is limited. In the study, we are investigating the application of linked data to enrich environmental and traffic data feeds, and we are using this with automated planning tools to enable traffic to be managed at a region level. The management will have the aim of avoiding air pollution problems before they occur. The first step in this project has been to create an automated planning tool which can reason with traffic flows within a large Urban Region, and will be the subject of the ICAPS demonstration.}\r\n}\r\n\r\n
\n
\n\n\n
\n The global growth in urbanisation increases the demand for services including road transport infrastructure, presenting challenges in terms of mobility. Optimising the exploitation of urban road network, while attempting to minimise the effects of traffic emissions, is a great challenge. SimplyfAI is a UK research council grant funded research project which is aimed towards solving air quality problems caused by road traffic emissions. Large cities such as Manchester struggle to meet air quality limits as the range of available traffic management devices is limited. In the study, we are investigating the application of linked data to enrich environmental and traffic data feeds, and we are using this with automated planning tools to enable traffic to be managed at a region level. The management will have the aim of avoiding air pollution problems before they occur. The first step in this project has been to create an automated planning tool which can reason with traffic flows within a large Urban Region, and will be the subject of the ICAPS demonstration.\n
\n\n\n
\n\n
\n\n
\n
\n \n \n\n \n \n \n \n KEWI: A Knowledge Engineering Tool for AI Planning.\n \n\n\n \n Mccluskey, L.; Chrpa, L.; and Wickler, G.\n \n\n\n \n\n\n\n In . \n \n\n\n\n
\n\n\n \n \n\n \n\n bibtex \n \n \n \n  \n \n abstract \n \n\n \n\n \n\n \n \n \n \n \n \n \n \n\n\n
\n
@InProceedings{icaps16-demo-5,\r\n  author =   {Lee Mccluskey and Lukas Chrpa and Gerhard Wickler},\r\n  title =    {KEWI: A Knowledge Engineering Tool for AI Planning},\r\n  abstract = {Hedlamp is one project of a UK-wide initiative into research and development of Autonomous Intelligent Systems, joint funded by the UK research council and a wide range of industries including aerospace, rail, and energy generation. Hedlamp aims to tackle challenges with knowledge engineering of automated planning techniques when applied to such real applications. Normally, successful deployment of planning technology relies on groups of planning experts encoding detailed domain models and investing large amounts of time maintaining them.\r\n  \r\nThe demonstration will be of KEWI, a product of the Hedlamp project. KEWI is a high level, application-oriented knowledge engineering framework usable by application developers who want to experiment with the potential of AI Planning, while encoding a precise domain model of some valuable application area. In the demonstration we will run the tools of the framework which support knowledge acquisition, validation and operationality of the domain model. These implement model translation, reformulation, and learning techniques to improve the model’s quality, and that of the planning function of which it is a part. The tool has been tested on benchmark problem domains as well as on a real industrial process.}\r\n}\r\n\r\n
\n
\n\n\n
\n Hedlamp is one project of a UK-wide initiative into research and development of Autonomous Intelligent Systems, joint funded by the UK research council and a wide range of industries including aerospace, rail, and energy generation. Hedlamp aims to tackle challenges with knowledge engineering of automated planning techniques when applied to such real applications. Normally, successful deployment of planning technology relies on groups of planning experts encoding detailed domain models and investing large amounts of time maintaining them. The demonstration will be of KEWI, a product of the Hedlamp project. KEWI is a high level, application-oriented knowledge engineering framework usable by application developers who want to experiment with the potential of AI Planning, while encoding a precise domain model of some valuable application area. In the demonstration we will run the tools of the framework which support knowledge acquisition, validation and operationality of the domain model. These implement model translation, reformulation, and learning techniques to improve the model’s quality, and that of the planning function of which it is a part. The tool has been tested on benchmark problem domains as well as on a real industrial process.\n
\n\n\n
\n\n
\n\n
\n
\n \n \n\n \n \n \n \n Risk-aware Planning in Hybrid Domains.\n \n\n\n \n Santana, P.; Vaquero, T.; Timmons, E.; Williams, B.; McGhan, C.; Murray, R.; and Toledo, C.\n \n\n\n \n\n\n\n In . \n \n\n\n\n
\n\n\n \n \n\n \n\n bibtex \n \n \n \n  \n \n abstract \n \n\n \n\n \n\n \n \n \n \n \n \n \n \n\n\n
\n
@InProceedings{icaps16-demo-6,\r\n  author =   {Pedro Santana and Tiago Vaquero and Eric Timmons and Brian Williams and Catharine McGhan and Richard Murray and Claudio Toledo},\r\n  title =    {Risk-aware Planning in Hybrid Domains},\r\n  abstract = {Expanding robotic space exploration beyond the immediate vicinity of Earth’s orbit can only be achieved by increasingly autonomous agents, given the sometimes insurmountable challenges of teleoperation over great distances. Among the numerous requirements that a fully autonomous robotic space explorer must meet, here we focus on three key mission-enabling technologies: (1) the ability to act under uncertainty and adapt to its environment; (2) the ability to optimize performance while offering hard bounds on the risk of mission failure; and (3) the ability to handle complex hybrid (discrete and continuous) mission planning problems in a provably correct and scalable fashion. In this demonstration, we showcase a novel hierarchical composition of three risk-aware planning elements (a conditional activity planner, a path planner, and a scheduler) and demonstrate its usefulness in the context of designing resilient science-gathering agents.}\r\n}\r\n\r\n
\n
\n\n\n
\n Expanding robotic space exploration beyond the immediate vicinity of Earth’s orbit can only be achieved by increasingly autonomous agents, given the sometimes insurmountable challenges of teleoperation over great distances. Among the numerous requirements that a fully autonomous robotic space explorer must meet, here we focus on three key mission-enabling technologies: (1) the ability to act under uncertainty and adapt to its environment; (2) the ability to optimize performance while offering hard bounds on the risk of mission failure; and (3) the ability to handle complex hybrid (discrete and continuous) mission planning problems in a provably correct and scalable fashion. In this demonstration, we showcase a novel hierarchical composition of three risk-aware planning elements (a conditional activity planner, a path planner, and a scheduler) and demonstrate its usefulness in the context of designing resilient science-gathering agents.\n
\n\n\n
\n\n
\n\n
\n
\n \n \n\n \n \n \n \n Motion Planning for Fluid Manipulation.\n \n\n\n \n Pan, Z.; Park, C.; and Manocha, D.\n \n\n\n \n\n\n\n In . \n \n\n\n\n
\n\n\n \n \n\n \n\n bibtex \n \n \n \n  \n \n abstract \n \n\n \n\n \n\n \n \n \n \n \n \n \n \n\n\n
\n
@InProceedings{icaps16-demo-7,\r\n  author =   {Zherong Pan and Chonhyon Park and Dinesh Manocha},\r\n  title =    {Motion Planning for Fluid Manipulation},\r\n  abstract = {We present a new algorithm to compute a collision-free trajectory for a robot manipulator to pour liquid from one container to the other. Our formulation uses a physical fluid model to predicate its highly deformable motion. We present simulation guided and optimization based method to automatically compute the transferring trajectory. Instead of abstract or simplified liquid models, we use the full-featured and accurate Navier-Stokes model that provides the fine-grained information of velocity distribution inside the liquid body. Moreover, this information is used as an additional guiding energy term for the planner. One of our key contributions is the tight integration between the fine-grained fluid simulator, liquid transfer controller, and the optimization-based planner. We have implemented the method using hybrid particle-mesh fluid simulator (FLIP) and demonstrated its performance on 4 benchmarks, with different cup shapes and viscosity coefficients.}\r\n}\r\n\r\n
\n
\n\n\n
\n We present a new algorithm to compute a collision-free trajectory for a robot manipulator to pour liquid from one container to the other. Our formulation uses a physical fluid model to predicate its highly deformable motion. We present simulation guided and optimization based method to automatically compute the transferring trajectory. Instead of abstract or simplified liquid models, we use the full-featured and accurate Navier-Stokes model that provides the fine-grained information of velocity distribution inside the liquid body. Moreover, this information is used as an additional guiding energy term for the planner. One of our key contributions is the tight integration between the fine-grained fluid simulator, liquid transfer controller, and the optimization-based planner. We have implemented the method using hybrid particle-mesh fluid simulator (FLIP) and demonstrated its performance on 4 benchmarks, with different cup shapes and viscosity coefficients.\n
\n\n\n
\n\n
\n\n
\n
\n \n \n\n \n \n \n \n Planning for Sustainable and Reliable Robotic Part Handling in Manufacturing Automation.\n \n\n\n \n Rovida, F.; Krueger, V.; Toscano, C.; Veiga, G.; Crosby, M.; and Petrick, R.\n \n\n\n \n\n\n\n In . \n \n\n\n\n
\n\n\n \n \n\n \n\n bibtex \n \n \n \n  \n \n abstract \n \n\n \n\n \n\n \n \n \n \n \n \n \n \n\n\n
\n
@InProceedings{icaps16-demo-8,\r\n  author =   {Francesco Rovida and Volker Krueger and César Toscano and Germano Veiga and Matthew Crosby and Ron Petrick},\r\n  title =    {Planning for Sustainable and Reliable Robotic Part Handling in Manufacturing Automation},\r\n  abstract = {Robots have been used effectively in factories for many years, however, it is only recently that they have begun to take on roles requiring large amounts of autonomy and high-level reasoning capabilities. Autonomy is becoming increasingly necessary due to greater variability in factory-generated products (e.g., end-user customisation) leading to assembly lines that must involve more than just simple repetitions of the same task with the same components. For example, in car manufacturing—the application domain for this work—each car is built to the specification of the user, meaning that the parts required for assembly may be different for each car on the line. Not only does this require more complex assembly line robots, but robots are starting to be used in preparing the parts for delivery to the assembly line.\r\n  \r\nThis system demonstration illustrates work that is being performed as part of the STAMINA1 project to address this latter task: using autonomous mobile robots with the ability to pick parts from around the factory to be delivered to the assembly line at the appropriate time (see Figure 1), a process called kitting. In particular, we focus on the high-level reasoning components in our framework consisting of a logistic planner, which acts as the central information provider in the system; a mission planner, which is tasked with creating and assigning initial high-level plans and goals to the robots in the fleet; and a task planner, which is responsible for managing planning activities for individual robots. Additionally, the robot fleet uses a skills framework which modularises robot capabilities into high-level, symbolic planning actions, meaning that the robots are pre-calibrated to use planning-like constructs. Plans are produced in a format that maps planned actions to skills to facilitate execution. This setup allows the technology to be quickly adapted to new situations when robot capabilities or the environment change, as happens when the factory floor is rearranged, new parts become available, or new robots are added to the fleet.}\r\n}\r\n\r\n
\n
\n\n\n
\n Robots have been used effectively in factories for many years, however, it is only recently that they have begun to take on roles requiring large amounts of autonomy and high-level reasoning capabilities. Autonomy is becoming increasingly necessary due to greater variability in factory-generated products (e.g., end-user customisation) leading to assembly lines that must involve more than just simple repetitions of the same task with the same components. For example, in car manufacturing—the application domain for this work—each car is built to the specification of the user, meaning that the parts required for assembly may be different for each car on the line. Not only does this require more complex assembly line robots, but robots are starting to be used in preparing the parts for delivery to the assembly line. This system demonstration illustrates work that is being performed as part of the STAMINA1 project to address this latter task: using autonomous mobile robots with the ability to pick parts from around the factory to be delivered to the assembly line at the appropriate time (see Figure 1), a process called kitting. In particular, we focus on the high-level reasoning components in our framework consisting of a logistic planner, which acts as the central information provider in the system; a mission planner, which is tasked with creating and assigning initial high-level plans and goals to the robots in the fleet; and a task planner, which is responsible for managing planning activities for individual robots. Additionally, the robot fleet uses a skills framework which modularises robot capabilities into high-level, symbolic planning actions, meaning that the robots are pre-calibrated to use planning-like constructs. Plans are produced in a format that maps planned actions to skills to facilitate execution. This setup allows the technology to be quickly adapted to new situations when robot capabilities or the environment change, as happens when the factory floor is rearranged, new parts become available, or new robots are added to the fleet.\n
\n\n\n
\n\n
\n\n
\n
\n \n \n\n \n \n \n \n Evaluating Scientific Coverage Strategies for A Heterogeneous Fleet of Marine Assets Using a Predictive Model of Ocean Currents.\n \n\n\n \n Branch, A.; Troesch, M.; Chien, S.; Chao, Y.; Farrara, J.; and Thompson, A.\n \n\n\n \n\n\n\n In . \n \n\n\n\n
\n\n\n \n \n\n \n\n bibtex \n \n \n \n  \n \n abstract \n \n\n \n\n \n\n \n \n \n \n \n \n \n \n\n\n
\n
@InProceedings{icaps16-demo-9,\r\n  author =   {Andrew Branch and Martina Troesch and Steve Chien and Yi Chao and John Farrara and Andrew Thompson},\r\n  title =    {Evaluating Scientific Coverage Strategies for A Heterogeneous Fleet of Marine Assets Using a Predictive Model of Ocean Currents},\r\n  abstract = {Planning for marine asset deployments is a challenging task. Determining the location to where the assets will be deployed involves considerations of (1) location, extent, and evolution of the science phenomena being studied; (2) deployment logistics (distances and costs), and (3) ability of the available vehicles to acquire the measurements desired by science.\r\n  \r\nThis paper describes the use of mission planning tools to evaluate science coverage capability for planned deployments. In this approach, designed coverage strategies are evaluated against ocean model data to see how they would perform in a range of locations. Feedback from these runs is then used to refine the coverage strategies to perform more robustly in the presence of a wider range of ocean current settings.}\r\n}\r\n\r\n
\n
\n\n\n
\n Planning for marine asset deployments is a challenging task. Determining the location to where the assets will be deployed involves considerations of (1) location, extent, and evolution of the science phenomena being studied; (2) deployment logistics (distances and costs), and (3) ability of the available vehicles to acquire the measurements desired by science. This paper describes the use of mission planning tools to evaluate science coverage capability for planned deployments. In this approach, designed coverage strategies are evaluated against ocean model data to see how they would perform in a range of locations. Feedback from these runs is then used to refine the coverage strategies to perform more robustly in the presence of a wider range of ocean current settings.\n
\n\n\n
\n\n
\n\n
\n
\n \n \n\n \n \n \n \n Using Operations Scheduling to Optimize Constellation Design.\n \n\n\n \n Schaffer, S.; Branch, A.; Chien, S.; Broschart, S.; Hernandez, S.; Belov, K.; Lazio, J.; Clare, L.; Tsao, P.; Castillo-Rogez, J.; and Wyatt, E. J.\n \n\n\n \n\n\n\n In . \n \n\n\n\n
\n\n\n \n \n\n \n\n bibtex \n \n \n \n  \n \n abstract \n \n\n \n\n \n\n \n \n \n \n \n \n \n \n\n\n
\n
@InProceedings{icaps16-demo-10,\r\n  author =   {Steve Schaffer and Andrew Branch and Steve Chien and Stephen Broschart and Sonia Hernandez and Konstantin Belov and Joseph Lazio and Loren Clare and Philip Tsao and Julie Castillo-Rogez and E. Jay Wyatt},\r\n  title =    {Using Operations Scheduling to Optimize Constellation Design},\r\n  abstract = {Space mission design is a challenging task. Many factors combine to influence overall mission return, and it is extremely difficult a priori to predict which factors in concert will most influence mission return. These challenges are even greater for constellation missions, in which a potentially large number of spacecraft are used in concert to achieve mission goals, because constellations have additional design choices of number of spacecraft, orbit combinations, and constellation topology.\r\n  \r\nWe describe efforts to use automated operations scheduling to assist in the design and analysis of a family of radio science constellation missions. Specifically we work to produce a model-based approach to evaluating mission return based on key design variables of: target catalogue selection, constellation topology, size of the science constellation, size of the relay support network, orbit mix, communications capability, communications strategy, ground station configuration, onboard processing and compression, onboard storage, and other elements of operations concept.\r\n\r\nIn our design methodology, choices on the design dimensions are evaluated by producing mission plans using automated scheduling technology and these resultant plans are evaluated for science return. By this approach we intend to enable evaluation of large numbers of mission configurations (literally 106 configurations) with manual assessment of only a small number of the best of these configurations.}\r\n}\r\n\r\n
\n
\n\n\n
\n Space mission design is a challenging task. Many factors combine to influence overall mission return, and it is extremely difficult a priori to predict which factors in concert will most influence mission return. These challenges are even greater for constellation missions, in which a potentially large number of spacecraft are used in concert to achieve mission goals, because constellations have additional design choices of number of spacecraft, orbit combinations, and constellation topology. We describe efforts to use automated operations scheduling to assist in the design and analysis of a family of radio science constellation missions. Specifically we work to produce a model-based approach to evaluating mission return based on key design variables of: target catalogue selection, constellation topology, size of the science constellation, size of the relay support network, orbit mix, communications capability, communications strategy, ground station configuration, onboard processing and compression, onboard storage, and other elements of operations concept. In our design methodology, choices on the design dimensions are evaluated by producing mission plans using automated scheduling technology and these resultant plans are evaluated for science return. By this approach we intend to enable evaluation of large numbers of mission configurations (literally 106 configurations) with manual assessment of only a small number of the best of these configurations.\n
\n\n\n
\n\n
\n\n
\n
\n \n \n\n \n \n \n \n Leveraging Probabilistic Reasoning in Deterministic Planning for Large-Scale Autonomous Search-and-Tracking.\n \n\n\n \n Bernardini, S.; Fox, M.; Long, D.; and Piacentini, C.\n \n\n\n \n\n\n\n In . \n \n\n\n\n
\n\n\n \n \n\n \n\n bibtex \n \n \n \n  \n \n abstract \n \n\n \n\n \n\n \n \n \n \n \n \n \n \n\n\n
\n
@InProceedings{icaps16-demo-11,\r\n  author =   {Sara Bernardini and Maria Fox and Derek Long and Chiara Piacentini},\r\n  title =    {Leveraging Probabilistic Reasoning in Deterministic Planning for Large-Scale Autonomous Search-and-Tracking},\r\n  abstract = {Search-And-Tracking (SaT) is the problem of searching for a mobile target and tracking it once it is found. Since SaT platforms face many sources of uncertainty and operational constraints, progress in the field has been restricted to simple and unrealistic scenarios. In this paper, we propose a new hybrid approach to SaT that allows us to successfully address large-scale and complex SaT missions. The probabilistic structure of SaT is compiled into a deterministic planning model and Bayesian inference is directly incorporated in the planning mechanism. Thanks to this tight integration between automated planning and probabilistic reasoning, we are able to exploit the power of both approaches. Planning provides the tools to efficiently explore big search spaces, while Bayesian inference, by readily combining prior knowledge with observable data, allows the planner to make more informed and effective decisions. We offer experimental evidence of the potential of our approach.}\r\n}\r\n\r\n
\n
\n\n\n
\n Search-And-Tracking (SaT) is the problem of searching for a mobile target and tracking it once it is found. Since SaT platforms face many sources of uncertainty and operational constraints, progress in the field has been restricted to simple and unrealistic scenarios. In this paper, we propose a new hybrid approach to SaT that allows us to successfully address large-scale and complex SaT missions. The probabilistic structure of SaT is compiled into a deterministic planning model and Bayesian inference is directly incorporated in the planning mechanism. Thanks to this tight integration between automated planning and probabilistic reasoning, we are able to exploit the power of both approaches. Planning provides the tools to efficiently explore big search spaces, while Bayesian inference, by readily combining prior knowledge with observable data, allows the planner to make more informed and effective decisions. We offer experimental evidence of the potential of our approach.\n
\n\n\n
\n\n
\n\n
\n
\n \n \n\n \n \n \n \n REACT!: An Interactive Educational Tool for AI Planning for Robotics.\n \n\n\n \n Dogmus, Z.; Erdem, E.; and Patoglu, V.\n \n\n\n \n\n\n\n In . \n \n\n\n\n
\n\n\n \n \n\n \n\n bibtex \n \n \n \n  \n \n abstract \n \n\n \n\n \n\n \n \n \n \n \n \n \n \n\n\n
\n
@InProceedings{icaps16-demo-12,\r\n  author =   {Zeynep Dogmus and Esra Erdem and Volkan Patoglu},\r\n  title =    {REACT!: An Interactive Educational Tool for AI Planning for Robotics},\r\n  abstract = {This paper presents REACT!, an interactive educational tool for artificial intelligence (AI) planning for robotics. REACT! enables students to describe robots’ actions and change in dynamic domains without first having to know about the syntactic and semantic details of the underlying formalism, and to solve planning problems using state-of-the-art reasoners without having to know about their input/output language or usage. In particular, REACT! can be used to represent sophisticated dynamic domains that feature concurrency, indirect effects of actions, and state/transition constraints. REACT! also allows the embedding of externally defined calculations (e.g., checking for collision-free continuous trajectories) into domain representations of hybrid domains that require a tight integration of (discrete) high-level reasoning with (continuous) geometric reasoning. REACT! also allows students to solve planning problems that involve complex temporal goals. This broad applicability, and the intelligent interactive user interface, mean that students can work on interesting and challenging domains, ranging from service robotics to cognitive factories, leading to hands-on robotic applications. The efficacy of REACT! was evaluated from three different points of view: 1) the course outcomes that demonstrate its utility in achieving the learning objectives of a research-oriented cognitive robotics course; 2) the user friendliness and usefulness of REACT! for students, as evaluated by quantitative student surveys; and 3) instructors’ experience of teaching the course either with or without REACT!.}\r\n}\r\n\r\n
\n
\n\n\n
\n This paper presents REACT!, an interactive educational tool for artificial intelligence (AI) planning for robotics. REACT! enables students to describe robots’ actions and change in dynamic domains without first having to know about the syntactic and semantic details of the underlying formalism, and to solve planning problems using state-of-the-art reasoners without having to know about their input/output language or usage. In particular, REACT! can be used to represent sophisticated dynamic domains that feature concurrency, indirect effects of actions, and state/transition constraints. REACT! also allows the embedding of externally defined calculations (e.g., checking for collision-free continuous trajectories) into domain representations of hybrid domains that require a tight integration of (discrete) high-level reasoning with (continuous) geometric reasoning. REACT! also allows students to solve planning problems that involve complex temporal goals. This broad applicability, and the intelligent interactive user interface, mean that students can work on interesting and challenging domains, ranging from service robotics to cognitive factories, leading to hands-on robotic applications. The efficacy of REACT! was evaluated from three different points of view: 1) the course outcomes that demonstrate its utility in achieving the learning objectives of a research-oriented cognitive robotics course; 2) the user friendliness and usefulness of REACT! for students, as evaluated by quantitative student surveys; and 3) instructors’ experience of teaching the course either with or without REACT!.\n
\n\n\n
\n\n
\n\n\n\n\n
\n\n\n \n
\n
\n \n

Embedding in another Page

\n
\n
\n\n

\n Copy&paste any of the following snippets into an existing\n page to embed this page. For more details see the\n documention.\n

\n\n JavaScript\n (Easiest)\n
\n \n <script src=\"https://bibbase.org/show?bib=icaps16.icaps-conference.org/demos.bib&jsonp=1&groupby=&jsonp=1\"></script>\n \n
\n\n PHP\n
\n \n <?php\n $contents = file_get_contents(\"https://bibbase.org/show?bib=icaps16.icaps-conference.org/demos.bib&jsonp=1&groupby=\");\n print_r($contents);\n ?>\n \n
\n\n iFrame\n
\n \n <iframe src=\"https://bibbase.org/show?bib=icaps16.icaps-conference.org/demos.bib&jsonp=1&groupby=\"></iframe>\n \n
\n\n \n
\n
\n \n
\n
\n\n \n \n \n \n\n
\n\n"}; document.write(bibbase_data.data);