Showing papers in "Artificial Intelligence in 2017"

TL;DR: It is shown how explicit knowledge management, both symbolic and geometric, proves to be instrumental to richer and more natural humanrobot interactions by pushing for pervasive, human-level semantics within the robot's deliberative system.

TL;DR: A global overview of deliberation functions in robotics is presented and the main characteristics, design choices and constraints of these functions are discussed.

TL;DR: By combining the knowledge layers with the models of knowledge effects, this paper can simultaneously solve several problems in robotics: (i) task planning and execution under uncertainty; (ii) task Planning and execution in open worlds; (iii) explaining task failure; (iv) verifying those explanations.

TL;DR: A unified approach to learning from constraints is proposed, which integrates the ability of classical machine learning techniques to learn from continuous feature-based representations with the ability to reasoning using higher-level semantic knowledge typical of Statistical Relational Learning.

TL;DR: This article discusses why the requirements of a robot knowledge processing system differ from what is commonly investigated in AI research, and proposes to re-consider a KR system as a semantically annotated view on information and algorithms that are often already available as part of the robot's control system.

TL;DR: This article presents a solution to a challenging, and vital problem of planning a constraint-balancing task for an inherently unstable non-linear system in the presence of obstacles and defines formal conditions for a class of robotics problems where learning can occur in a simplified problem space and successfully transfer to a broader problem space.

TL;DR: The results show that using non-essential, implied constraints in the best discovered configuration can lead to a significant improvement in performance and showsignificant improvement in speed using a state-of-the-art Bayesian network structure learner.

TL;DR: The inference capability introduced in this study was integrated into a joint space control loop for a humanoid robot, an iCub, for achieving similar goals to the human demonstrator online.

TL;DR: The early promise of the impact of machine intelligence did not involve the partitioning of the nascent field of Artificial Intelligence, according to the founders of AI.

TL;DR: Experiments show that combining the agent's intrinsic rewards with external task rewards enables the agent to learn faster than using external rewards alone, and the applicability of this approach to learning on robots is presented.

TL;DR: This dissertation explores Constraint Programming (CP) and proposes two models based on CP to address constrained clustering tasks and shows that these models can easily be embedded in a more general process and illustrate this on the problem of finding the Pareto front of a bi-criterion optimization process.

TL;DR: This paper proposes a methodology called Empirical Model Learning (EML) that relies on Machine Learning for obtaining components of a prescriptive model, using data either extracted from a predictive model or harvested from a real system, and uses two learning methods, namely Artificial Neural Networks and Decision Trees.

TL;DR: A novel model-based contextual policy search algorithm that is able to generalize lower-level controllers, and is data-efficient is proposed, based on learned probabilistic forward models and information theoretic policy search.

TL;DR: A new general-purpose algorithm that reuses knowledge learned from previous teammates or provided by experts to quickly adapt to new teammates is introduced, PLASTIC, that was able to identify and exploit similarities between its current and past teammates' behaviors.

TL;DR: A main contribution of the proposed algorithm recommender Alors system is to handle the cold start problem – emitting recommendations for a new problem instance – through the non-linear modeling of the latent factors based on the initial instance representation, extending the linear approach proposed by Stern et al.

TL;DR: The technical setup of the ICCMA'15 took place in the first half of 2015 and focused on reasoning tasks in abstract argumentation frameworks, and an overview on the submitted solvers is given.

TL;DR: By envisioning the outcome of actions before committing to them, a robot is able to reason about physical phenomena and can therefore prevent itself from ending up in unwanted situations.

TL;DR: In this paper, the authors proposed a novel approach for utilizing automated advising agents in assisting an operator to better manage a team of multiple robots in complex environments, such as search and rescue and warehouse operation tasks.

TL;DR: This work presents an approach to hybrid task and motion planning, in which state-based forward-chaining task planning is tightly coupled with motion planning and other forms of geometric reasoning, and explores two avenues to deal with the problem of geometric backtracking.

TL;DR: This paper investigates the incremental elicitation of the capacity through a sequence of preference queries selected one-by-one using a minimax regret strategy so as to progressively reduce the set of possible capacities until the regret (the worst-case loss due to reasoning with only partially specified capacities) is low enough.

TL;DR: A generic framework for measuring the degree of envy in a society is introduced and the computational complexity of checking whether a given scenario allows for a deal that is beneficial to every agent involved and that will reduce overall envy is established.

TL;DR: Results of experiments with an iCub humanoid robot that uses CCSA to incrementally acquire skills to topple, grasp and pick-place a cup, driven by its intrinsic motivation from raw pixel vision are presented.

TL;DR: A new transfer learning framework for recommender systems is proposed, which relaxes the above assumption to facilitate flexible knowledge transfer across different systems with low cost by using an active learning principle to construct entity correspondences across systems.

TL;DR: This paper demonstrates how to apply machine learning techniques to solve the optimal ordering problem in sequential auctions, and proposes two types of optimization methods: a black-box best-first search approach and a novel white-box approach that maps learned regression models to integer linear programs (ILP), which can be solved by any ILP-solver.

TL;DR: A new SLS algorithm named CCEHC for WPMS, an extended framework of CCLS with a heuristic emphasizing hard clauses, called EHC that significantly outperforms its state-of-the-art SLS competitors and shows the effectiveness on a number of application WPMS instances.

TL;DR: The results indicate that: 1) a greedy heuristic manipulation approach is not sufficient, multi-object manipulation requires multi-step POMDP planning, and 2) on-line planning is beneficial since it allows the adaptation of the system dynamics model based on actual experience.

TL;DR: This work focuses on the optimisation problem of forming the travellers' coalitions that minimise the travel cost of the overall system, and model the formation problem as a Graph-Constrained Coalition Formation (GCCF) one, where the set of feasible coalitions is restricted by a graph.

TL;DR: A novel algorithm is proposed that integrates the option of requesting teacher demonstrations to learn new domains with fewer action executions and no previous knowledge to reduce the amount of exploration required and improve the success ratio.

TL;DR: In this paper, a max-margin approach for learning in hybrid domains based on Satisfiability Modulo Theories, which allows to combine Boolean reasoning and optimization over continuous linear arithmetical constraints, is presented.

TL;DR: A new algorithm is introduced and described in detail to perform Associative–Commutative Common Subexpression Elimination (AC-CSE) in constraint problems, significantly improving existing CSE techniques for associative and commutative operators such as +.