Generating perception requests and expectations to verify the execution of plans (original) (raw)

Monitoring the execution of robot plans using semantic knowledge

Robotics and Autonomous Systems, 2008

Even the best laid plans can fail, and robot plans executed in real world domains tend to do so often. The ability of a robot to reliably monitor the execution of plans and detect failures is essential to its performance and its autonomy. In this paper, we propose a technique to increase the reliability of monitoring symbolic robot plans. We use semantic domain knowledge to derive implicit expectations of the execution of actions in the plan, and then match these expectations against observations. We present two realizations of this approach: a crisp one, which assumes deterministic actions and reliable sensing, and uses a standard knowledge representation system (LOOM); and a probabilistic one, which takes into account uncertainty in action effects, in sensing, and in world states. We perform an extensive validation of these realizations through experiments performed both in simulation and on real robots.

Automatic Verification of Autonomous Robot Missions

Lecture Notes in Computer Science, 2014

Before autonomous robotics can be used for dangerous or critical missions, performance guarantees should be made available. This paper overviews a software system for the verification of behavior-based controllers in context of chosen hardware and environmental models. Robotic controllers are automatically translated to a process algebra. The system comprising both the robot and the environment are then evaluated by VIPARS, a verification software module in development, and compared to specific performance criteria. The user is returned a probability that the performance criteria will hold in the uncertainty of real-world conditions. Experimental results demonstrate accurate verification for a mission related to the search for a biohazard.

Monitored Execution of Robot Plans Produced by Strips

1971

We describe PLANEXl, a plan executor for the Stanford Research Institute robot system. The problemsolving program STRIPS creates a plan consisting of a sequence of actions, and the PLANEXI program carries out the plan by executing the actions. PLANEXI is designed so that it executes only that portion of the plan necessary for completing the task, reexecutes any portion of the plan that has failed to achieve the desired results, and initiates replanning in situations where the plan can no longer be effective in completing the task. The scenario for an example plan execution is given.

An intent-specifications model for a robotic software control system

Intent specifications are a new way to structure specifications to support human problem solving, system and software development and evolution, traceability, and specification of design rationale. An intent specification provides a hierarchical abstraction based on intent ("why") in addition to the usual "what" and "how." For a given system being specified, an intent specification defines seven levels, each one of them supporting a different type of reasoning about the system. Each level is mapped to the appropriate parts of the intent levels above and below it, providing a means to trace design rationale and decisions from high-level system requirements and constraints down to code and vice versa (from code to specifications, requirements, and safety analyses). The third level of an intent specification contains a black-box model that uses an executable formal specification language, SpecTRM-RL, which provides special support for requirements review and analysis-particularly for completeness and safety. SpecTRM-RL models can be mathematically analyzed and checked for various properties, including human-computer interaction properties such as mode confusion. They can also be executed as part of system simulations. The approach is demonstrated using an industrial robot designed to service the heat resistant tiles on the Space Shuttle.

Experimental Evaluation of a Planning Language Suitable for Formal Verification

Lecture Notes in Computer Science, 2009

The marriage of model checking and planning faces two seemingly diverging alternatives: the need for a planning language expressive enough to capture the complexity of real-life applications, as opposed to a language simple, yet robust enough to be amenable to exhaustive verification and validation techniques. In an attempt to reconcile these differences, we have designed an abstract plan description language, ANMLite, inspired from the Action Notation Modeling Language (ANML). We present the basic concepts of the ANMLite language as well as an automatic translator from ANMLite to the model checker SAL (Symbolic Analysis Laboratory). We discuss various aspects of specifying a plan in terms of constraints and explore the implications of choosing a robust logic behind the specification of constraints, rather than simply propose a new planning language. Additionally, we provide an initial assessment of the efficiency of model checking to search for solutions of planning problems. To this end, we design a basic test benchmark and study the scalability of the generated SAL models in terms of plan complexity.

Plan execution monitoring and control architecture for mobile robots

1995

This paper deals with the architecture and control structure of mobile robots. We decompose robot functions into modules organized according to their predefined interactions: sensor modules that accomplish various processings on data from physical sensors, effector modules that issue commands to effectors, servo-processes that establish links between perception and action to achieve closed-loop behaviors, and functional units that provide specific functionalities. These modules, and hence the robot system itself, are controlled by a control system that also enables the robot to execute missions (plans) expressed in a command language. We introduce and discuss a generic control system structure, composed of a Supervisor that interprets the plan and oversees its execution, an Executive for operating and managing robot modules and resources, a Surveillance Manager for detecting and reacting to asynchronous events, and an Error Recovery module for local plan mending and correction. Several experimental examples are given.

A Formal Interactive Verification Environment for the Plan Execution Interchange Language

Integrated Formal …, 2012

The Plan Execution Interchange Language (PLEXIL) is an open source synchronous language developed by NASA for commanding and monitoring autonomous systems. This paper reports the development of the PLEXIL's Formal Interactive Verification Environment (PLEXIL5), a graphical interface to the formal executable semantics of PLEXIL. Among its main features, PLEXIL5 provides model checking of plans with support for formula editing and visualization of counterexamples, interactive simulation of plans at different granularity levels, and random initialization of external environment variables. The formal verification capabilities of PLEXIL5 are illustrated by means of a human-automation interaction model.

Plan Representation for Robotic Agents

Plan-Based Control of Robotic Agents, 2002

This paper invents symbolic pattern databases (SPDB) to combine two influencing aspects for recent progress in domain-independent action planning, namely heuristic search and model checking. SPDBs are off-line computed dictionaries, generated in symbolic backward traversals of automatically inferred planning space abstractions. The entries of SPDBs serve as heuristic estimates to accelerate explicit and symbolic, approximate and optimal heuristic search planners. Selected experiments highlight that the symbolic representation yields much larger and more accurate pattern databases than the ones generated with explicit methods.

Constraint-Based Online Transformation of Abstract Plans into Executable Robot Actions

National Conference on Artificial Intelligence, 2018

In this paper, we are concerned with making the execution of abstract action plans for robotic agents more robust. To this end, we propose to model the internals of a robot system and its ties to the actions that the robot can perform. Based on these models, we propose an online transformation of an abstract plan into executable actions conforming with system specifics. With our framework, we aim to achieve two goals. First, modeling the system internals is beneficial in its own right in order to achieve long term autonomy, system transparency, and comprehensibility. Second, separating the system details from determining the course of action on an abstract level leverages the use of planning for actual robotic systems.