Autonomous AI systems need complex computational techniques for planning and performing actions. Planning and acting require significant deliberation because an intelligent system must coordinate and integrate these activities in order to act effectively in the real world. This book presents a comprehensive paradigm of planning and acting using the most recent and advanced automated-planning techniques. It explains the computational deliberation capabilities that allow an actor, whether physical or virtual, to reason about its actions, choose them, organize them purposefully, and act deliberately to achieve an objective. Useful for students, practitioners, and researchers, this book covers state-of-the-art planning techniques, acting techniques, and their integration which will allow readers to design intelligent systems that are able to act effectively in the real world.

An autonomous robot offers a challenging and ideal field for the study of intelligent architectures. Autonomy within a rational be havior could be evaluated by the robot's effectiveness and robust ness in carrying out tasks in different and ill-known environments. It raises major requirements on the control architecture. Further more, a robot as a programmable machine brings up other archi tectural needs, such as the ease and quality of its specification and programming. This article describes an integrated architecture that allows a mobile robot to plan its tasks—taking into account temporal and domain constraints, to perform corresponding actions and to con trol their execution in real-time—while being reactive to possible events. The general architecture is composed of three levels: a de cision level, an execution level, and a functional level. The latter is composed of modules that embed the functions achieving sensor- data processing and effector control. The decision level is goal and event driven, and it may have several layers, according to the application; their basic structure is a planner/supervisor pair that enables the architecture to integrate deliberation and reaction. The proposed architecture relies naturally on several representa tions, programming paradigms, and processing approaches, which meet the precise requirements that are specified for each level. The authors have developed proper tools to meet these specifications and implement each level of the architecture: a temporal planner, IxTeT; a procedural system for task refinement and supervision, PRS; Kheops for the reactive control of the functional level, and GenoM for the specification and integration of modules at that level Validation of the temporal and logical properties of the reactive parts of the system, through these tools, are presented. Instances of the proposed architecture have been integrated into several indoor and outdoor robots. Examples from real-world ex perimentations are provided and analyzed.

International audienceAutonomous robots facing a diversity of open environments and performing a variety of tasks and interactions need explicit deliberation in order to fulfill their missions. Deliberation is meant to endow a robotic system with extended, more adaptable and robust functionalities, as well as reduce its deployment cost. The ambition of this survey is to present a global overview of deliberation functions in robotics and to discuss the state of the art in this area. The following five deliberation functions are identified and analyzed: planning, acting, monitoring, observing, and learning. The paper introduces a global perspective on these deliberation functions and discusses their main characteristics, design choices and constraints. The reviewed contributions are discussed with respect to this perspective. The survey focuses as much as possible on papers with a clear robotics content and with a concern on integrating several deliberation functions

Planning is motivated by acting. Most of the existing work on automated planning underestimates the reasoning and deliberation needed for acting; it is instead biased towards path-finding methods in a compactly specified state-transition system. Researchers in this AI field have developed many planners, but very few actors. We believe this is one of the main causes of the relatively low deployment of automated planning applications. In this paper, we advocate a change in focus to actors as the primary topic of investigation. Actors are not mere plan executors: they may use planning and other deliberation tools, before and during acting. This change in focus entails two interconnected principles: a hierarchical structure to integrate the actor's deliberation functions, and continual online planning and reasoning throughout the acting process. In the paper, we discuss open problems and research directions toward that objective in knowledge representations, model acquisition and verification, synthesis and refinement, monitoring, goal reasoning, and integration.

No abstract

This position paper discusses the requirements and challenges for responsible AI with respect to two interdependent objectives: (i) how to foster research and development efforts toward socially beneficial applications, and (ii) how to take into account and mitigate the human and social risks of AI systems.

No abstract

In this paper we describe a machine learning approach for acquiring a model of a robot behaviour from raw sensor data. We are interested in automating the acquisition of behavioural models to provide a robot with an introspective capability. We assume that the behaviour of a robot in achieving a task can be modelled as a finite stochastic state transition system. Beginning with data recorded by a robot in the execution of a task, we use unsupervised learning techniques to estimate a hidden Markov model (HMM) that can be used both for predicting and explaining the behaviour of the robot in subsequent executions of the task. We demonstrate that it is feasible to automate the entire process of learning a high quality HMM from the data recorded by the robot during execution of its task.The learned HMM can be used both for monitoring and controlling the behaviour of the robot. The ultimate purpose of our work is to learn models for the full set of tasks associated with a given problem domain, and to integrate these models with a generative task planner. We want to show that these models can be used successfully in controlling the execution of a plan. However, this paper does not develop the planning and control aspects of our work, focussing instead on the learning methodology and the evaluation of a learned model. The essential property of the models we seek to construct is that the most probable trajectory through a model, given the observations made by the robot, accurately diagnoses, or explains, the behaviour that the robot actually performed when making these observations. In the work reported here we consider a navigation task. We explain the learning process, the experimental setup and the structure of the resulting learned behavioural models. We then evaluate the extent to which explanations proposed by the learned models accord with a human observer's interpretation of the behaviour exhibited by the robot in its execution of the task