Rich Levinson - Academia.edu (original) (raw)
Papers by Rich Levinson
Proceedings of the International Conference on Automated Planning and Scheduling, Jun 13, 2022
We compare two planner solutions for a challenging Earth science application to plan coordinated ... more We compare two planner solutions for a challenging Earth science application to plan coordinated measurements (observations) for a constellation of satellites. This problem is combinatorically explosive, involving many degrees of freedom for planner choices. Each satellite carries two different sensors and is maneuverable to 61 pointing angle options. The sensors collect data to update the predictions made by a high-fidelity global soil moisture prediction model. Soil moisture is an important geophysical variable whose knowledge is used in applications such as crop health monitoring and predictions of floods, droughts, and fires. The global soil-moisture model produces soil-moisture predictions with associated prediction errors over the globe represented by a grid of 1.67 million Ground Positions (GPs). The prediction error varies over space and time and can change drastically with events like rain/fire. The planner's goal is to select measurements which reduce prediction errors to improve future predictions. This is done by targeting high-quality observations at locations of high prediction-error. Observations can be made in multiple ways, such as by using one or more instruments or different pointing angles; the planner seeks to select the way with the least measurement-error (higher observation quality). In this paper we compare two planning approaches to this problem: Dynamic Constraint Processing (DCP) and Mixed Integer Linear Programming (MILP). We match inputs and metrics for both DCP and MILP algorithms to enable a direct apples-to-apples comparison. DCP uses domain heuristics to find solutions within a reasonable time for our application but cannot be proven optimal, while the MILP produces provably optimal solutions. We demonstrate and discuss the trades between DCP flexibility and performance vs. MILP's promise of provable optimality. Science Problem and Application Soil moisture is an important geophysical variable that can forewarn of impending drought or flood conditions before other more standard indicators are triggered (NIDIS, 2021). Other soil moisture applications include wildfire
I. INTRODUCTION Writing autonomous software is complex, requiring the coordination of functionall... more I. INTRODUCTION Writing autonomous software is complex, requiring the coordination of functionally and technologically diverse software modules [Bonasso et al. 9"/] [Currie & Tate 91] [Firby 89] [Georgeff & Lanskey 89] [McDermott 92] [Musliner et al. 93] [Simmons 92]. System and mission engineers must rely on specialists familiar with the different software modules to translate requirements into application software. Also, each module often encodes the same requirement in different forms. The results are high costs and reduced reliability due to the difficulty of tracking discrepancies in these encodings. In this paper we describe a unified approach to planning and execution that we believe provides a unified representational and computational framework for an autonomous agent. We identify the four main components whose interplay provides the basis for the agent's autonomous behavior: the domain model, the plan database, the plan running module, and the planner modules. This representational and problem solving approach can be applied at all levels of the architecture of a complex agent, such as Remote Agent. In the rest of the paper we briefly describe the Remote Agent architecture. The new agent architecture proposed here aims at achieving the full Remote Agent functionality. We then give the fundamental ideas behind the new agent architecture and point out some implication of the structure of the architecture, mainly in the area of reactivity and interaction between reactive and deliberative decision making. We conclude with related work and current status. transition the system to a specified state for a specified period of time. We define robust as the ability to overcome
Proceedings of 9th IEEE Conference on Artificial Intelligence for Applications
ABSTRACT The authors describe an autonomous system that performs closed loop control of a differe... more ABSTRACT The authors describe an autonomous system that performs closed loop control of a differential thermal analyzer (DTA) and a gas chromatograph (GC) to identify minerals and organics in soil samples. The system is presented as an instantiation of an integrated agent architecture designed to autonomously control scientific equipment in remote locations. The motivational context and general requirements of the application are described, followed by a description of the DTA-GC problem in terms of specific requirements for integrated perception, analysis, planning and control. The AI techniques applied to each of the specified requirements are considered. The system implementation status is discussed. The original contributions include a general architecture that integrates perception, analysis, planning and control for scientific experiments. The new analysis instrument integrates two previously distinct methods. Issues at the integration level as well as those relating to the individual components are examined
ArXiv, 2021
We present planning challenges, methods and preliminary results for a new model-based paradigm fo... more We present planning challenges, methods and preliminary results for a new model-based paradigm for earth observing systems in adaptive remote sensing. Our heuristically guided constraint optimization planner produces coordinated plans for multiple satellites, each with multiple instruments (payloads). The satellites are agile, meaning they can quickly maneuver to change viewing angles in response to rapidly changing phenomena. The planner operates in a closed-loop context, updating the plan as it receives regular sensor data and updated predictions. We describe the planner's search space and search procedure, and present preliminary experiment results. Contributions include initial identification of the planner's search space, constraints, heuristics, and performance metrics applied to a soil moisture monitoring scenario using spaceborne radars.
Proceedings of the AAAI …, 2008
We are investigating how sensors can improve a portable reminder system (PEAT) that helps individ... more We are investigating how sensors can improve a portable reminder system (PEAT) that helps individuals accomplish their daily routines. PEAT is designed for individuals who have difficulty remembering when to perform activities be-cause of cognitive impairments from strokes ...
Proceedings of the International Conference on Automated Planning and Scheduling, Jun 13, 2022
We compare two planner solutions for a challenging Earth science application to plan coordinated ... more We compare two planner solutions for a challenging Earth science application to plan coordinated measurements (observations) for a constellation of satellites. This problem is combinatorically explosive, involving many degrees of freedom for planner choices. Each satellite carries two different sensors and is maneuverable to 61 pointing angle options. The sensors collect data to update the predictions made by a high-fidelity global soil moisture prediction model. Soil moisture is an important geophysical variable whose knowledge is used in applications such as crop health monitoring and predictions of floods, droughts, and fires. The global soil-moisture model produces soil-moisture predictions with associated prediction errors over the globe represented by a grid of 1.67 million Ground Positions (GPs). The prediction error varies over space and time and can change drastically with events like rain/fire. The planner's goal is to select measurements which reduce prediction errors to improve future predictions. This is done by targeting high-quality observations at locations of high prediction-error. Observations can be made in multiple ways, such as by using one or more instruments or different pointing angles; the planner seeks to select the way with the least measurement-error (higher observation quality). In this paper we compare two planning approaches to this problem: Dynamic Constraint Processing (DCP) and Mixed Integer Linear Programming (MILP). We match inputs and metrics for both DCP and MILP algorithms to enable a direct apples-to-apples comparison. DCP uses domain heuristics to find solutions within a reasonable time for our application but cannot be proven optimal, while the MILP produces provably optimal solutions. We demonstrate and discuss the trades between DCP flexibility and performance vs. MILP's promise of provable optimality. Science Problem and Application Soil moisture is an important geophysical variable that can forewarn of impending drought or flood conditions before other more standard indicators are triggered (NIDIS, 2021). Other soil moisture applications include wildfire
I. INTRODUCTION Writing autonomous software is complex, requiring the coordination of functionall... more I. INTRODUCTION Writing autonomous software is complex, requiring the coordination of functionally and technologically diverse software modules [Bonasso et al. 9"/] [Currie & Tate 91] [Firby 89] [Georgeff & Lanskey 89] [McDermott 92] [Musliner et al. 93] [Simmons 92]. System and mission engineers must rely on specialists familiar with the different software modules to translate requirements into application software. Also, each module often encodes the same requirement in different forms. The results are high costs and reduced reliability due to the difficulty of tracking discrepancies in these encodings. In this paper we describe a unified approach to planning and execution that we believe provides a unified representational and computational framework for an autonomous agent. We identify the four main components whose interplay provides the basis for the agent's autonomous behavior: the domain model, the plan database, the plan running module, and the planner modules. This representational and problem solving approach can be applied at all levels of the architecture of a complex agent, such as Remote Agent. In the rest of the paper we briefly describe the Remote Agent architecture. The new agent architecture proposed here aims at achieving the full Remote Agent functionality. We then give the fundamental ideas behind the new agent architecture and point out some implication of the structure of the architecture, mainly in the area of reactivity and interaction between reactive and deliberative decision making. We conclude with related work and current status. transition the system to a specified state for a specified period of time. We define robust as the ability to overcome
Proceedings of 9th IEEE Conference on Artificial Intelligence for Applications
ABSTRACT The authors describe an autonomous system that performs closed loop control of a differe... more ABSTRACT The authors describe an autonomous system that performs closed loop control of a differential thermal analyzer (DTA) and a gas chromatograph (GC) to identify minerals and organics in soil samples. The system is presented as an instantiation of an integrated agent architecture designed to autonomously control scientific equipment in remote locations. The motivational context and general requirements of the application are described, followed by a description of the DTA-GC problem in terms of specific requirements for integrated perception, analysis, planning and control. The AI techniques applied to each of the specified requirements are considered. The system implementation status is discussed. The original contributions include a general architecture that integrates perception, analysis, planning and control for scientific experiments. The new analysis instrument integrates two previously distinct methods. Issues at the integration level as well as those relating to the individual components are examined
ArXiv, 2021
We present planning challenges, methods and preliminary results for a new model-based paradigm fo... more We present planning challenges, methods and preliminary results for a new model-based paradigm for earth observing systems in adaptive remote sensing. Our heuristically guided constraint optimization planner produces coordinated plans for multiple satellites, each with multiple instruments (payloads). The satellites are agile, meaning they can quickly maneuver to change viewing angles in response to rapidly changing phenomena. The planner operates in a closed-loop context, updating the plan as it receives regular sensor data and updated predictions. We describe the planner's search space and search procedure, and present preliminary experiment results. Contributions include initial identification of the planner's search space, constraints, heuristics, and performance metrics applied to a soil moisture monitoring scenario using spaceborne radars.
Proceedings of the AAAI …, 2008
We are investigating how sensors can improve a portable reminder system (PEAT) that helps individ... more We are investigating how sensors can improve a portable reminder system (PEAT) that helps individuals accomplish their daily routines. PEAT is designed for individuals who have difficulty remembering when to perform activities be-cause of cognitive impairments from strokes ...