Abstract not found

Abstract — Executing plans by mobile robots, in real world environments, faces the challenging issues of uncertainty and environment dynamics. Thus, execution monitoring is needed to verify that plan actions are executed as expected. Semantic domain-knowledge has lately been proposed as a source of information to derive and monitor implicit expectations of executing actions. For instance, when a robot moves into a room asserted to be an office, it would expect to see a desk and a chair. We propose to extend the semantic knowledge-based execution monitoring to take uncertainty in actions and sensing into account when verifying the expectations derived from semantic knowledge. We consider symbolic probabilistic action models, and show how semantic knowledge is used together with a probabilistic sensing model in the monitoring process of such actions. Our approach is illustrated by showing test scenarios run in an indoor environment using a mobile robot. I.

Abstract — We describe a novel intelligent execution monitoring approach for mobile robots acting in indoor environments such as offices and houses. Traditionally, monitoring execution in mobile robotics amounted to looking for discrepancies between the model-based predicted state of executing an action and the real world state as computed from sensing data. We propose to employ semantic knowledge as a source of information to monitor execution. The key idea is to compute implicit expectations, from semantic domain information, that can be observed at run time by the robot to make sure actions are executed correctly. We present the semantic knowledge representation formalism, and how semantic knowledge is used in monitoring. We also describe experiments run in an indoor environment using a real mobile robot. I.

The concept of Ecology of Physically Embedded Intelligent Systems, or PEIS-Ecology, combines insights from the fields of ubiquitous robotics and ambient intelligence to provide a new solution to building intelligent robots in the service of people. While this concept provides great potential, it also presents a number of new scientific challenges. In this paper we introduce this concept, discuss its potential and its challenges, and present our current steps toward its realization. We also point to experimental results that show the viability of this concept. The discussion in this paper is also relevant to any type of ubiquitous robot or network robotic system. 1

Agent programming in complex, partially observable, and stochastic domains usually requires a great deal of understanding of both the domain and the task in order to provide the agent with the knowledge necessary to act effectively. While symbolic methods allow the designer to specify declarative knowledge about the domain, the resulting plan can be brittle since it is difficult to supply a symbolic model that is accurate enough to foresee all possible events in complex environments, especially in the case of partial observability. Reinforcement Learning (RL) techniques, on the other hand, can learn a policy and make use of a learned model, but it is difficult to reduce and shape the scope of the learning algorithm by exploiting a priori information. We propose a methodology for writing complex agent programs that can be effectively improved through experience. We show how to derive a stochastic process from a partial specification of the plan, so that the latter’s perfomance can be improved solving a RL problem much smaller than classical RL formulations. Finally, we demonstrate our approach in the context of Keepaway Soccer, a common RL benchmark based on a RoboCup Soccer 2D simulator.

Abstract. We propose a methodology to automatically generate agent controllers, represented as state machines, to act in partially observable environments. We define a multi-step process, in which increasingly accurate models- generally too complex to be used for planning- are employed to generate possible traces of execution by simulation. Those traces are then utilized to induce a state machine, that represents all reasonable behaviors, given the approximate models and planners previously used. The state machine will have multiple possible choices in some of its states. Those states are choice points, and we defer the learning of those choices to the deployment of the agent in the real environment. The controller obtained can therefore adapt to the actual environment, limiting the search space in a sensible way.

Abstract — Detecting and reacting to faults (i.e., abnormal situations) are essential skills for robots to safely and autonomously perform tasks in human-populated environments. This paper presents a fault detection algorithm that statistically monitors robot motion execution. The algorithm does not model possible motion faults, but it instead uses a model of normal execution to detect anomalies. The model of normal execution is based on comparisons between redundant sources of information; specifically, wheel encoder readings and localization algorithm output are used as the redundant sources of displacement information. The algorithm was implemented on a service robot that often navigates in a human-populated environment without supervision. Experimental results show that the algorithm can detect even minor motion faults and stop execution immediately to guarantee safety to the humans around the robot. I.