Robotics2015, 4(3), 316-340; doi:10.3390/robotics4030316 (registering DOI) - published 28 August 2015 Show/Hide Abstract
Abstract: Multi-robot task allocation (MRTA) is an important area of research in autonomous multi-robot systems. The main problem in MRTA is to allocate a set of tasks to a set of robots so that the tasks can be completed by the robots while ensuring that a certain metric, such as the time required to complete all tasks, or the distance traveled, or the energy expended by the robots is reduced. We consider a scenario where tasks can appear dynamically and a task needs to be performed by multiple robots to be completed. We propose a new algorithm called SQ-MRTA (Spatial Queueing-MRTA) that uses a spatial queue-based model to allocate tasks between robots in a distributed manner. We have implemented the SQ-MRTA algorithm on accurately simulated models of Corobot robots within the Webots simulator for different numbers of robots and tasks and compared its performance with other state-of-the-art MRTA algorithms. Our results show that the SQ-MRTA algorithm is able to scale up with the number of tasks and robots in the environment, and it either outperforms or performs comparably with respect to other distributed MRTA algorithms.
Abstract: In this paper, we propose a new approach for recognizing intentions of humans by observing their activities with a color plus depth (RGB-D) camera. Activities and goals are modeled as a distributed network of inter-connected nodes in an Activation Spreading Network (ASN). Inspired by a formalism in hierarchical task networks, the structure of the network captures the hierarchical relationship between high-level goals and low-level activities that realize these goals. Our approach can detect intentions before they are realized and it can work in real-time. We also extend the formalism of ASNs to incorporate contextual information into intent recognition. We further augment the ASN formalism with special nodes and synaptic connections to model ordering constraints between actions, in order to represent and handle partial-order plans in our ASN. A fully functioning system is developed for experimental evaluation. We implemented a robotic system that uses our intent recognition to naturally interact with the user. Our ASN based intent recognizer is tested against three different scenarios involving everyday activities performed by a subject, and our results show that the proposed approach is able to detect low-level activities and recognize high-level intentions effectively in real-time. Further analysis shows that contextual and partial-order ASNs are able to discriminate between otherwise ambiguous goals.
Abstract: Learning and planning are powerful AI methods that exhibit complementary strengths. While planning allows goal-directed actions to be computed when a reliable forward model is known, learning allows such models to be obtained autonomously. In this paper we describe how both methods can be combined using an expressive qualitative knowledge representation. We argue that the crucial step in this integration is to employ a representation based on a well-defined semantics. This article proposes the qualitative spatial logic QSL, a representation that combines qualitative abstraction with linear temporal logic, allowing us to represent relevant information about the learning task, possible actions, and their consequences. Doing so, we empower reasoning processes to enhance learning performance beyond the positive effects of learning in abstract state spaces. Proof-of-concept experiments in two simulation environments show that this approach can help to improve learning-based robotics by quicker convergence and leads to more reliable action planning.
Abstract: We present KnoWDiaL, an approach for Learning and using task-relevant Knowledge from human-robot Dialog and access to the Web. KnoWDiaL assumes that there is an autonomous agent that performs tasks, as requested by humans through speech. The agent needs to “understand” the request, (i.e., to fully ground the task until it can proceed to plan for and execute it). KnoWDiaL contributes such understanding by using and updating a Knowledge Base, by dialoguing with the user, and by accessing the web. We believe that KnoWDiaL, as we present it, can be applied to general autonomous agents. However, we focus on our work with our autonomous collaborative robot, CoBot, which executes service tasks in a building, moving around and transporting objects between locations. Hence, the knowledge acquired and accessed consists of groundings of language to robot actions, and building locations, persons, and objects. KnoWDiaL handles the interpretation of voice commands, is robust regarding speech recognition errors, and is able to learn commands involving referring expressions in an open domain, (i.e., without requiring a lexicon). We present in detail the multiple components of KnoWDiaL, namely a frame-semantic parser, a probabilistic grounding model, a web-based predicate evaluator, a dialog manager, and the weighted predicate-based Knowledge Base. We illustrate the knowledge access and updates from the dialog and Web access, through detailed and complete examples. We further evaluate the correctness of the predicate instances learned into the Knowledge Base, and show the increase in dialog efficiency as a function of the number of interactions. We have extensively and successfully used KnoWDiaL in CoBot dialoguing and accessing the Web, and extract a few corresponding example sequences from captured videos.
Abstract: In Asia, decreasing farmer and labor populations due to various factors is a serious problem that leads to increases in labor costs, higher harvesting input energy consumption and less resource utilization. To solve these problems, researchers are engaged in providing long term and low-tech alternatives in terms of mechanization and automation of agriculture by way of efficient, low cost and easy to use solutions. This paper reviews various design strategies in recognition and picking systems, as well as developments in fruit harvesting robots during the past 30 years in several countries. The main objectives of this paper are to gather all information on fruit harvesting robots; focus on the technical developments so far achieved in picking devices; highlight the problems still to be solved; and discuss the future prospects of fruit harvesting robots.
Abstract: Robotic agents are spreading, incarnated as embodied entities, exploring the tangible world and interacting with us, or as virtual agents crawling over the web, parsing and generating data. In both cases, they require: (i) processes to acquire information; (ii) structures to model and store information as usable knowledge; (iii) reasoning systems to interpret the information; and (iv) finally, ways to express their interpretations. The H5W (How, Why, What, Where, When, Who) framework is a conceptualization of the problems faced by any agent situated in a social environment, which has defined several robotic studies. We introduce the H5W framework, through a description of its underlying neuroscience and the psychological considerations it embodies, we then demonstrate a specific implementation of the framework. We will focus on the motivation and implication of the pragmatic decisions we have taken. We report the numerous studies that have relied upon this technical implementation as a proof of its robustness and polyvalence; moreover, we conduct an additional validation of its applicability to the natural language domain by designing an information exchange task as a benchmark.