Using Many-Sorted Logic in the Object-Oriented Data Model for Fast Robot Task Planning

Search space explosion is a critical problem in robot task planning. This problem limits current robot task planners to solve only simple block world problems and task planning in a real robot working environment to be impractical. This problem is mainly due to the lack of utilization of domain information in task planning. In this paper, we describe a fast task planner for indoor robot applications that effectively uses domain information to speed up the planning process. In this planner, domain information is explicitly represented in an object-oriented data model (OODM) that uses many-sorted logic (MSL) representation. The OODM is convenient for the management of complex data and many-sorted logic is effective for pruning in the rule search process. An inference engine is designed to take advantage of the salient features of these two techniques for fast task planning. A simulation example and complexity analysis are given to demonstrate the advantage of the proposed task planner.     

Evaluating strategic options using decision-theoretic planning

The purpose of this research is to examine whether decision-theoretic planning techniques can be used to help managers evaluate strategic options in complex and uncertain environments. Firms faced with choices such as whether to acquire a start-up, develop a new product, or invest in updated production technology continue to make decisions based on unreliable heuristics, “gut feel” or misleading financial measures such as net present value (NPV). In this paper we show that decision-theoretic planning techniques originally developed for robot planning permit us to gain the insights provided by real options analysis without working within the restrictions of models designed to price financial options or incurring the overhead of constructing huge decision trees. A biotechnology licensing problem similar to those addressed elsewhere in the real options literature is used to illustrate the methodology and demonstrate its feasibility.     

Planning in the Real World

In this article, we describe how real world planning problems can be solved by employing Artificial Intelligence planning techniques. We introduce the paradigm of hybrid planning, which is particularly suited for applications where plans are not intended to be automatically executed by systems, but are made for humans. Hybrid planning combines hierarchical planning – the stepwise refinement of complex tasks – with explicit reasoning about causal dependencies between actions, thereby reflecting exactly the kinds of reasoning humans perform when developing plans. We show how plans are generated and how failed plans are repaired in a way that guarantees stability. Our illustrating examples are taken from a domain model for disaster relief missions enforced upon extensive floods. Finally, we present a tool to support the challenging task of constructing planning domain models.     

Planning in the Real World

In this article, we describe how real world planning problems can be solved by employing Artificial Intelligence planning techniques. We introduce the paradigm of hybrid planning, which is particularly suited for applications where plans are not intended to be automatically executed by systems, but are made for humans. Hybrid planning combines hierarchical planning ?C the stepwise refinement of complex tasks ?C with explicit reasoning about causal dependencies between actions, thereby reflecting exactly the kinds of reasoning humans perform when developing plans. We show how plans are generated and how failed plans are repaired in a way that guarantees stability. Our illustrating examples are taken from a domain model for disaster relief missions enforced upon extensive floods. Finally, we present a tool to support the challenging task of constructing planning domain models. The article ends with an overview of a wide varity of actual planning applications and outlines further such in the area of cognitive technical systems.     

A therapy planning architecture that combines decision theory and artificial intelligence techniques

Through our experience with the ONCOCIN cancer therapy consultation system, we have identified a set of medical planning problems to which no single existing computer-based reasoning technique readily applies. In response to the need for automated assistance with this class of problems, we have devised a computer program called ONYX that combines decision-theoretic and artificial intelligence approaches to planning. We discuss our rationale for devising a new planning architecture and describe in detail how that architecture is implemented. The program's planning process consists of three steps: (i) the use of rules derived from therapy planning strategies to generate a small set of plausible plans, (ii) the use of knowledge about the structure and behavior of the human body to create simulations that predict possible consequences of each plan for the patient, and (iii) the use of decision theory to rank the plans according to how well the results of each simulation meet the treatment goals. This architecture explicitly manages the uncertainty inherent in many planning tasks, introduces a possible mechanism for the dissemination of decision-theoretic therapy advice, and potentially increases the number of problem solving domains in which expert system techniques can be effectively applied.     

Interleaving Planning and Robot Execution for Asynchronous User Requests

ROGUE is an architecture built on a real robot which provides algorithms for the integration of high-level planning, low-level robotic execution, and learning. ROGUE addresses successfully several of the challenges of a dynamic office gopher environment. This article presents the techniques for the integration of planning and execution.ROGUE uses and extends a classical planning algorithm to create plans for multiple interacting goals introduced by asynchronous user requests. ROGUE translates the planner';s actions to robot execution actions and monitors real world execution. ROGUE is currently implemented using the PRODIGY4.0 planner and the Xavier robot. This article describes how plans are created for multiple asynchronous goals, and how task priority and compatibility information are used to achieve appropriate efficient execution. We describe how ROGUE communicates with the planner and the robot to interleave planning with execution so that the planner can replan for failed actions, identify the actual outcome of an action with multiple possible outcomes, and take opportunities from changes in the environment.ROGUE represents a successful integration of a classical artificial intelligence planner with a real mobile robot.     

Logical sensor/actuator : knowledge-based robotic plan execution

Complex tasks are usually described as high-level goals, leaving out the details on how to achieve them. However, to control a robot, the task must be described in terms of primitive commands for the robot. Having the robot move itself to and through an unknown, and possibly narrow, doorway is an example of such a task. It is shown how the transformation from high-level goals to primitive commands can be performed at execution time and an architecture is proposed based on reconfigurable objects that contain domain knowledge and knowledge about the sensors and actuators available. The approach is illustrated using actual data from a real robot.     

Artificial intelligence and robotic assembly

Traditionally, most industrial robots are programmed by teaching. The emergence of robot-level programming languages has improved the programmer's ability to describe and modify the robot moves. However, commercially available robot-level programming languages still fall short of the robot user's need to program complex tasks, and consequently, are not widely used in industry. There is an increasing need for integrating sensors feedback into the robot system to provide better perception and for improving the capacity of the robot to reason and make decisions intelligently in real time.The role of artificial intelligence in programming and controlling robots is discussed. Available robot programming systems including robot-level, object-level, and task-level languages are reviewed. The importance of developing intelligent robots in broadening the scope of flexible automation and opening the door to new robotic applications in space, under water and in harsh environments is outlined. The current development and implementation of programming and control systems for intelligent robots, at McMaster University, are explained. A number of research issues are discussed such as (1) automatic task planning, (2) knowledge representation and use, (3) world modeling, (4) reasoning in automatic assembly planning, and (5) vision monitoring of actions. Examples of geometric, functional, and handling reasoning, as they apply to assembly, are provided. The systems described in this paper are being implemented in the center for flexible manufacturing research and development. Several pieces of hardware are used, including a six-axis articulated robot, a grey-level vision system with a multi-camera, Micro VAX II, and a variety of graphics monitors. The languages available for software development include Common LISP, C, OPS5, VAL II, PASCAL, and FORTRAN 77. The domain of application is currently focused on mechanical assembly.     

Legal modeling and automated reasoning with ON-LINE

In this paper we present a modeling approach to legal knowledge systems and its computational realization in the ON-LINE architecture. ON-LINE has modules for modeling legal sources, for storing and retrieving legal information and for reasoning with legal knowledge. The approach takes two perspectives: domain and task. In the domain perspective, a core ontology divides legal knowledge into five major categories: normative, world, responsibility, reactive and creative. For the normative knowledge, which is most typical of legal domains, we developed a new representation and inference formalisms which are an alternative to deontic logic. For the world knowledge, we argue for using a terminological knowledge representation language. The structure of the ontology is not a taxonomy, but a network of dependencies between the categories. These dependencies reflect the global structure of arguments in legal reasoning. In the task perspective, we followed a top-down approach using the CommonKADS modeling library. Design, planning and assessment were identified as typical tasks in the legal domain. For assessment, a model was specified and implemented.     

基于不确定性知识的实时道路场景理解

由于室外机器人的工作环境非常复杂，因此机器人的视觉导航必须具有足够的智能和鲁棒性，为此，提出了一种基于不确定性知识的实时道路理解算法，该算法通过不确定性知识推理来融合多种信息和知识，以满足在复杂道路环境下的鲁棒性要求，它即使在有强烈阴影、水迹等干扰下也能给出比较好的结果；通过图象边缘信息的提取可以得到精确的道路边界，以满足视觉导航的精确性要求；同时在算法设计时，兼顾了实时性要求；使得算法得以实时实现，该算法已在实际的机器人上进行了测试，并得到了很好的结果。     

基于反射的规划方法

本文针对机器人在实际环境中执行任务时所面临的不确定性和实时性提出了一种基于反射的规划方法．该方法在较好地利用全局信息的基础上，充分发挥出机器人自身的能动的反射作用．我们首先讨论该方法的基本原理，然后着重讨论它在移动机器人规划和导航中的应用．     

JLU-RLAO和JLU-QLAO:两个不确定智能规划求解系统

不确定环境下的智能规划问题往往假设世界状态的转移概率是确切可知的,然而规划建模专家有时只能在信息不完备的条件下进行建模.从而只能通过猜测或者不完全统计的方法来获取不完备的有关状态转移不确定性的定量信息,有时甚至只能荻取相关的定性信息.在2004年概率规划比赛冠军LAO系统的基础上设计了JLU-RLAO系统和JLU-QLAO系统.它们可以在无法获得精确的状态转移概率条件下,依然保证规划求解的健壮性.实验结果表明,JLU-RLAO系统和JLU-QLA0系统可以快速高效地解决上述不确定智能规划问题.     

Behavioral task processing for cognitive robots using artificial emotions

This paper presents an artificial emotional-cognitive system-based autonomous robot control architecture for a four-wheel driven and four-wheel steered mobile robot. Discrete stochastic state-space mathematical model is considered for behavioral and emotional transition processes of the autonomous mobile robot in the dynamic realistic environment. The term of cognitive mechanism system which is composed from rule base and reinforcement self-learning algorithm explain all of the deliberative events such as learning, reasoning and memory (rule spaces) of the autonomous mobile robot. The artificial cognitive model of autonomous robot control architecture has a dynamic associative memory including behavioral transition rules which are able to be learned for achieving multi-objective robot tasks. Motivation module of architecture has been considered as behavioral gain effect generator for achieving multi-objective robot tasks. According to emotional and behavioral state transition probabilities, artificial emotions determine sequences of behaviors for long-term action planning. Also reinforcement self-learning and reasoning ability of artificial cognitive model and motivational gain effects of proposed architecture can be observed on the executing behavioral sequences during simulation. The posture and speed of the robot and the configurations, speeds and torques of the wheels and all deliberative and cognitive events can be observed from the simulation plant and virtual reality viewer. This study constitutes basis for the multi-goal robot tasks and artificial emotions and cognitive mechanism-based behavior generation experiments on a real mobile robot.     

Task Planning For A Mobile Robot In An Indoor Environment Using Object-oriented Domain Information

For a mobile robot to be practical, it needs to navigate in dynamically changing environments and manipulate objects in the environment with operating ease. The main challenges to satisfying these requirements in mobile robot research include the collection of robot environment information, storage and organization of this information, and fast task planning based on available information. Conventional approaches to these problems are far from satisfactory due to their requirement of high computation time. In this paper, we specifically address the problems of storage and organization of the environment information and fast task planning in the area of robotic research. We propose an special object-oriented data model (OODM) for information storage and management in order to solve the first problem. This model explicitly represents domain knowledge and abstracts a global perspective about the robot's dynamically changing environment. To solve the second problem, we introduce a fast task planning algorithm that fully uses domain knowledge related to robot applications and to the given environment. Our OODM based task planning method presents a general frame work and representation, into which domain specific information, domain decomposition methods and specific path planners can be tailored for different task planning problems. This method unifies and integrates the salient features from various areas such as database, artificial intelligence, and robot path planning, thus increasing the planning speed significantly     

AGAINST OPTIMALITY: LOGICAL FOUNDATIONS FOR DECISION-THEORETIC PLANNING IN AUTONOMOUS AGENTS

This paper investigates decision-theoretic planning in sophisticated autonomous agents operating in environments of real-world complexity. An example might be a planetary rover exploring a largely unknown planet. It is argued that existing algorithms for decision-theoretic planning are based on a logically incorrect theory of rational decision making. Plans cannot be evaluated directly in terms of their expected values, because plans can be of different scopes, and they can interact with other previously adopted plans. Furthermore, in the real world, the search for optimal plans is completely intractable. An alternative theory of rational decision making is proposed, called "locally global planning."     

Decision-Theoretic Planning for Autonomous Robotic Surveillance

In this paper, we introduce a decision-theoretic strategy for surveillance as a first step towards automating the planning of the movement of an autonomous surveillance robot. In our opinion, this particular application is interesting in its own right, but it also provides a test-case for formalisms aimed at dealing both with (low-level) sensor, localisation, and navigation uncertainty and with uncertainty at a more abstract planning level. After a brief discussion of our view on surveillance, we describe a very simple formal model of an environment in which the surveillance task has to be performed. We use this model to illustrate our decision-theoretic strategy and to compare this strategy with other proposed strategies. We treat several simple examples and obtain some general results.     

智能空间下基于分层任务网络的服务机器人任务规划

针对在复杂、动态的家庭环境下,如何让机器人获取足够多的环境信息并根据环境信息进行自主的任务规划,提出了智能空间技术支持下基于分层任务网络的服务机器人任务规划方案.利用智能空间技术为机器人提供充足的环境上下文信息,用基于分层任务网络设计的JSHOP2规划器执行机器人任务规划.为了提高机器人任务规划的自主性和智能性,在规划领域文件中加入不同的模板信息,使机器人具有根据环境的不同自动对任务进行调整的能力.仿真实验结果表明利用该方法能够有效地提高机器人任务规划的性能.     

Safety assessment of robot trajectories for navigation in uncertain and dynamic environments

This paper presents a probabilistic framework for reasoning about the safety of robot trajectories in dynamic and uncertain environments with imperfect information about the future motion of surrounding objects. For safety assessment, the overall collision probability is used to rank candidate trajectories by considering the probability of colliding with known objects as well as the estimated collision probability beyond the planning horizon. In addition, we introduce a safety assessment cost metric, the probabilistic collision cost, which considers the relative speeds and masses of multiple moving objects in which the robot may possibly collide with. The collision probabilities with other objects are estimated by probabilistic reasoning about their future motion trajectories as well as the ability of the robot to avoid them. The results are integrated into a navigation framework that generates and selects trajectories that strive to maximize safety while minimizing the time to reach a goal location. An example implementation of the proposed framework is applied to simulation scenarios, that explores some of the inherent computational trade-offs.