Robotics, Volume 4, Issue 2 (June 2015) – 6 articles , Pages 103-252

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. Full article

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. Full article

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. Full article

This article presents: (i) a formal, generic model for active sensing tasks; (ii) the insight that active sensing actions can very often be searched on less than six-dimensional configuration spaces (bringing an exponential reduction in the computational costs involved in the search); (iii) an algorithm for selecting actions explicitly trading off information gain, execution time and computational cost; and (iv) experimental results of touch-based localization in an industrial setting. Generalizing from prior work, the formal model represents an active sensing task by six primitives: configuration space, information space, object model, action space, inference scheme and action-selection scheme; prior work applications conform to the model as illustrated by four concrete examples. On top of the mentioned primitives, the task graph is then introduced as the relationship to represent an active sensing task as a sequence of low-complexity actions defined over different configuration spaces of the object. The presented act-reason algorithm is an action selection scheme to maximize the expected information gain of each action, explicitly constraining the time allocated to compute and execute the actions. The experimental contributions include localization of objects with: (1) a force-controlled robot equipped with a spherical touch probe; (2) a geometric complexity of the to-be-localized objects up to industrial relevance; (3) an initial uncertainty of (0.4 m, 0.4 m, 2Π); and (4) a configuration of act-reason to constrain the allocated time to compute and execute the next action as a function of the current uncertainty. Localization is accomplished when the probability mass within a 5-mm tolerance reaches a specified threshold of 80%. Four objects are localized with final {mean; standard-deviation} error spanning from {0.0043 m; 0.0034 m} to {0.0073 m; 0.0048 m}. Full article

This paper reports on a navigation method for the snow-removal robot called SnowEater. The robot is designed to work autonomously within small areas (around 30 m² or less) following line segment paths. The line segment paths are laid out so as much snow as possible can be cleared from an area. Navigation is accomplished by using an onboard low-resolution USB camera and a small marker located in the area to be cleared. Low-resolution cameras allow only limited localization and present significant errors. However, these errors can be overcome by using an efficient navigation algorithm to exploit the merits of these cameras. For stable robust autonomous snow removal using this limited information, the most reliable data are selected and the travel paths are controlled. The navigation paths are a set of radially arranged line segments emanating from a marker placed in the environment area to be cleared, in a place where it is not covered by snow. With this method, by using a low-resolution camera (640 × 480 pixels) and a small marker (100 × 100 mm), the robot covered the testing area following line segments. For a reference angle of 4.5° between line paths, the average results are: 4° for motion on hard floor and 4.8° for motion on compacted snow. The main contribution of this study is the design of a path-following control algorithm capable of absorbing the errors generated by a low-cost camera. Full article

Concentrated solar power (CSP) plants are expansive facilities that require substantial inspection and maintenance. A fully automated inspection robot increases the efficiency of maintenance work, reduces operating and maintenance costs, and improves safety and work conditions for service technicians. This paper describes a climbing robot that is capable of performing inspection and maintenance on vertical surfaces of solar power plants, e.g., the tubes of the receiver in a central tower CSP plant. Specifically, the service robot’s climbing mechanism is explained and the results of the nondestructive inspection methods are reviewed. The robot moves on the panels of the receiver in the tower and aligns the sensors correctly for inspection. The vertical movement of the climbing kinematics is synchronized with the movement of the tower’s crane. Various devices that detect surface defects and thickness losses inside the tube were integrated into the robot. Since the tubes are exposed to very high radiation, they need to be inspected regularly. Full article