In this paper, we study human trust and its computational models in supervisory control of swarm robots with varied levels autonomy (LOA) a target foraging task. We implement three LOAs: manual, mixed-initiative (MI), fully autonomous LOA. While the MI LOA is controlled by operator an search algorithm collaboratively, swarms manual LOAs are directed algorithm, respectively. From user studies, find that humans tend to make their decisions based on physical characteristics rather than...

We present an algorithm that produces a plan for relocating obstacles in order to grasp target clutter by robotic manipulator without collisions. consider configurations where objects are densely populated constrained and confined space. Thus, there exists no collision-free path the obstacles. Since problem of planning object rearrangement has shown be NP-hard, it is difficult perform manipulation tasks efficiently which could frequently happen service domains (e.g., taking out from shelf or...

This paper presents a task and motion planning (TAMP) framework for robotic manipulator in order to retrieve target object from clutter. We consider configuration of objects confined space with high density so no collision-free path the exists. The robot must relocate some without collisions. For fast completion rearrangement, aims optimize number pick-and-place actions which often determines efficiency TAMP framework.We propose planner incorporating generate executable plans minimize...

We present an algorithm determining where to relocate objects inside a cluttered and confined space while rearranging retrieve target object. Although methods that decide what remove have been proposed, planning for the placement of removed workspace has not received much attention. Rather, are often placed outside workspace, which incurs additional laborious work (e.g., motion execution manipulator mobile base, perception other areas). Some manipulate only but without principle so...

This paper considers multirobot task allocation problems where the estimated costs for performing tasks are interrelated, and overall team objective need not be a standard sum-of-costs (or utilities) model, enabling straightforward treatment of additional incurred by resource contention. In model we introduce, may choose one set shared resources to perform (e.g., several routes reach destination), interference is modeled when multiple robots use same resource. We show that general problem...

We consider multi-robot teams operating in uncertain dynamic settings where the costs used for computing task-allocations are not known exactly. In such cases, desire to minimize team's expected cost might need be curtailed if, doing so, risk that results is intolerable. describe a parameterizable variant of assignment problem enables designer express preferences, allowing one take risk-averse position if demands it. random variables, but which independent—a useful setting because it permits...

We address the problem of finding optimal assignment tasks to a team robots when associated costs may vary, which arises deal with uncertain or dynamic situations. detail how compute sensitivity analysis that characterizes much change before optimality is violated. Using this analysis, are able avoid unnecessary re-assignment computations and reduce global communication. First, given model evolve, we develop an algorithm partition into independent cliques, each maintains by communicating...

We consider the problem of retrieving a target object from confined space by two robotic manipulators where overhand grasps are not allowed. If other movable obstacles occlude target, more than one should be relocated to clear path reach object. With robots, relocation could done efficiently simultaneously performing tasks. However, precedence constraint between tasks (e.g, some objects at front removed manipulate in back) makes simultaneous task execution difficult. propose coordination...

We consider optimization of the multi-robot task-allocation problem when overall performance team need not be a standard sum-of-cost model. introduce generalization that allows for additional cost incurred by resource contention to treated in straightforward manner. In this variant, robots may choose one shared resources perform task, and interference modeled as occurring multiple use same resource. investigate general NP-hard instances where results linear or convex penalization functions....

In this paper, we study the model of human trust where an operator controls a robotic swarm remotely for search mission. Existing models in human-in-the-loop systems are based on task performance robots. However, find that humans tend to make their decisions physical characteristics rather than its since swarms is not clearly perceivable by humans. We formulate as Markov decision process whose state space includes parameters swarm. employ inverse reinforcement learning algorithm learn...

In this article, we present a task and motion planning method for retrieving target object from clutter using robotic manipulator. We consider dense cluttered environments where some objects must be removed in order to retrieve the without collisions. To ensure successful execution, interplay between ( <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">what remove what order</i> ) xmlns:xlink="http://www.w3.org/1999/xlink">how remove</i> is...

In this paper, we propose an algorithmic compass that yields the heading information of a mobile robot using vanishing point in indoor environments: VPass. With VPass, loop-closing effect (which is significant reduction errors by revisiting known place through loop) can be achieved even for loop-less environment. From implementation view, VPass useful because it appended upon any existing navigation algorithms. Experimental results show accurate angle environments paths with lengths around 200 m.

In this paper, we study trust-related human factors in supervisory control of swarm robots with varied levels autonomy (LOA) a target foraging task. We compare three LOAs: manual, mixed-initiative (MI), and fully autonomous LOA. the manual LOA, operator chooses headings for flocking swarm, issuing new as needed. is redirected automatically by changing using search algorithm. if performance declines, switched from to or human. The result work extends current knowledge on control....

This paper presents a software architecture for robots providing manipulation services autonomously in human environments. In an unstructured environment, service robot often needs to perform tasks even without intervention and prior knowledge about For autonomous execution of tasks, varied processes are necessary such as perceiving environments, representing knowledge, reasoning with the planning task motion. While developing each is important, integrating them into working system...

We propose a tree search-based planning algorithm for robot manipulator to rearrange objects and grasp target in dense space. consider environments where tasks cannot be completed with prehensile only. As assuming that is only allowed from the top, we aim minimize number of rearrangement actions total execution time, which affects efficiency manipulation. The proposed search determines optimal sequence object non-prehensile grasping until target. For grasping, heuristic function employed...

Abstract In the case of a visually impaired person, literal communication often relies on braille, system predominantly dependent vision and touch. This study entailed development visual tactile perception technique for braille character recognition. approach, recognition was performed using deep learning model (Faster R-CNN–FPN–ResNet-50), based custom-made dataset collected through data augmentation preprocessing. The attained performance indicated by an mAP50 94.8 mAP75 70.4 generated...

This paper presents planning algorithms for a robotic manipulator with fixed base in order to grasp target object cluttered environments. We consider configuration of objects confined space high density so no collision-free path the exists. The robot must relocate some retrieve while avoiding collisions. For fast completion retrieval task, needs compute plan optimizing an appropriate objective value directly related execution time relocation plan. propose that aim minimize number be...

In this article, we study multirobot task allocation problems where costs vary. The variation may be, for example, due to the revelation of new information or other dynamic circumstances. As robots update their cost estimates, typically they will assignments reflect using additional communication and computation. settings, are continually repairing optimality system's assignments, which can incur substantial We investigate how one reduce centralized computation expense during execution by a...

In this paper, we consider the problem of Multi-Robot Path Planning (MRPP) in continuous space to find conflict-free paths. The difficulty arises from two primary factors. First, involvement multiple robots leads combinatorial decision-making, which escalates search exponentially. Second, presents potentially infinite states and actions. For problem, propose a two-level approach where low level is sampling-based planner Safe Interval RRT* (SI-RRT*) that finds collision-free trajectory for...

We consider the problem of rearranging objects in a cluttered and confined space using robotic manipulator. The goal is to retrieve target object from clutter where occluded by other objects. In situations overhand grasps are not allowed, robot needs remove some make accessible. course removing objects, also determine locations place removed If can access enough empty spaces around or inside clutter, placement trivially simple. scarce, placing should be done principled way as an incorrect...

Development of Robotic-Crane Based Automatic Construction System for Steel Structures High-Rise Buildings Tae-Koo Kang, Changjoo Nam, Ung-Kyun Lee, Nakju Lett Doh, Gwi-Tae Park Pages 670-671 (2011 Proceedings the 28th ISARC, Seoul, Korea, ISBN 978-89-954572-4-5, ISSN 2413-5844) Abstract: In this paper, we address a new technique automatic construction steel structure in high-rise buildings termed RCA system (Robotics & Crane based Automated System). can be divided into four core systems: 1)...