This paper challenges the common assumption that swarm robotic systems are robust and scalable by default. We present an analysis based on both reliability modelling and experimental trials of a case study swarm perfo...
详细信息
ISBN:
(纸本)9783642327223
This paper challenges the common assumption that swarm robotic systems are robust and scalable by default. We present an analysis based on both reliability modelling and experimental trials of a case study swarm performing team work, in which failures are deliberately induced. Our case study has been carefully chosen to represent a swarm task in which the overall desired system behaviour is an emergent property of the interactions between robots, in order that we can assess the fault tolerance of a self-organising system. Our findings show that in the presence of worst-case partially failed robots the overall system reliability quickly falls with increasing swarm size. We conclude that future large scale swarm systems will need a new approach to achieving high levels of fault tolerance.
This book proposes a complete pipeline for monocular (single camera) based 3D mapping of terrestrial and underwater environments. The aim is to provide a solution to large-scale scene modeling that is both accurate an...
详细信息
ISBN:
(数字)9783642364181
ISBN:
(纸本)9783642364174
This book proposes a complete pipeline for monocular (single camera) based 3D mapping of terrestrial and underwater environments. The aim is to provide a solution to large-scale scene modeling that is both accurate and efficient. To this end, we have developed a novel Structure from Motion algorithm that increases mapping accuracy by registering camera views directly with the maps. The camera registration uses a dual approach that adapts to the type of environment being mapped. In order to further increase the accuracy of the resulting maps, a new method is presented, allowing detection of images corresponding to the same scene region (crossovers). Crossovers then used in conjunction with global alignment methods in order to highly reduce estimation errors, especially when mapping large areas. Our method is based on Visual Bag of Words paradigm (BoW), offering a more efficient and simpler solution by eliminating the training stage, generally required by state of the art BoW algorithms. Also, towards developing methods for efficient mapping of large areas (especially with costs related to map storage, transmission and rendering in mind), an online 3D model simplification algorithm is proposed. This new algorithm presents the advantage of selecting only those vertices that are geometrically representative for the scene.
We consider a weighted communication graph in a network of mobile robots, and its associated Laplacian whose entries depend on the pairwise distance between the robots. We propose a heuristic distributed solution for ...
详细信息
ISBN:
(纸本)9783642327223
We consider a weighted communication graph in a network of mobile robots, and its associated Laplacian whose entries depend on the pairwise distance between the robots. We propose a heuristic distributed solution for the maximization of the algebraic connectivity of the graph by moving the robots to appropriate positions. Our approach is optimization-based and can be extended to handle various "constraints, such as the robots' dynamics. Our proposed distributed solution uses local algorithms that utilize information only from nearby neighboring robots. Numerical simulations show the applicability and effectiveness of the algorithm and indicate that in certain cases the proposed distributed solution can perform better than the centralized version.
The book written by Dr. Radu B. Rusu presents a detailed description of 3D Semantic Mapping in the context of mobile robot manipulation. As autonomous robotic platforms get more sophisticated manipulation capabilities...
详细信息
ISBN:
(数字)9783642354793
ISBN:
(纸本)9783642354786;9783642354793
The book written by Dr. Radu B. Rusu presents a detailed description of 3D Semantic Mapping in the context of mobile robot manipulation. As autonomous robotic platforms get more sophisticated manipulation capabilities, they also need more expressive and comprehensive environment models that include the objects present in the world, together with their position, form, and other semantic aspects, as well as interpretations of these objects with respect to the robot tasks. The book proposes novel 3D feature representations called Point Feature Histograms (PFH), as well as a frameworks for the acquisition and processing of Semantic 3D Object Maps with contributions to robust registration, fast segmentation into regions, and reliable object detection, categorization, and reconstruction. These contributions have been fully implemented and empirically evaluated on different robotic systems, and have been the original kernel to the widely successful open-source project the Point Cloud Library (PCL) -- see http://***.
In this paper we study fractal gene regulatory network (FGRN) controllers based on sensory information. The FGRN controllers are evolved to control a snake robot consisting of seven simulated ATRON modules. Each modul...
详细信息
ISBN:
(纸本)9783642327223
In this paper we study fractal gene regulatory network (FGRN) controllers based on sensory information. The FGRN controllers are evolved to control a snake robot consisting of seven simulated ATRON modules. Each module contains three tilt sensors which represent the direction of gravity in the coordination system of the module. The modules are controlled locally and there is no explicit communication between them. So, they can synchronize implicitly using their sensors, and coordination of their behavior takes place through the environment. In one of our experiments, all the three tilt sensors are available for the FGRNs and a simple controller is evolved. The controller is a linear mapping of one input sensor to the output. It is only based on one sensor input and ignores the other sensors as well as the regulatory part of the network. In another experiment, the controller's input uses one of the other sensors that carries less information. In this case, the evolved controller blends sensory information with the regulatory network capabilities to come up with a proper distributed controller.
We describe a new low-cost robot design that enables large-scale multi-robot research, innovative new curriculum, and multi-robotics outreach to younger students. There are four main parts to the system: the r-one rob...
详细信息
ISBN:
(纸本)9783642327223
We describe a new low-cost robot design that enables large-scale multi-robot research, innovative new curriculum, and multi-robotics outreach to younger students. There are four main parts to the system: the r-one robot, a Python development environment, a camera tracking system for ground-truth localization, and server software to connect all the pieces together. This paper presents our preliminary work on the robot design and our experience using it to teach an introductory engineering class. The hardware can support classes in computer science, electrical engineering, and mechanical engineering. The low-cost and small size will enable more research groups to perform multi-robot experiments on physical hardware. The Python development environment greatly simplifies programming and will make robotics more accessible to a larger group of educators, students, and researchers.
Motivated by the success of stochastic process sampling methods in solving complex estimation problems, we explore the possibility to utilize stochastic processes for computing optimal control for a large-size robot p...
详细信息
ISBN:
(纸本)9783642327223
Motivated by the success of stochastic process sampling methods in solving complex estimation problems, we explore the possibility to utilize stochastic processes for computing optimal control for a large-size robot population. We assume that the individual robot state is composed of discrete and continuous components, while the population is controlled in a probability space. The optimal control solution is based on an infinite dimensional Pontryagin-like minimum principle, which involves an evaluation of systems of partial differential equations. The paper shows that these equations can be evaluated with computations involving stochastic process samples. This is an important result because generating stochastic process multi-dimensional trajectories is much easier than solving corresponding multi-dimensional partial differential equations. The proposed evaluations are illustrated and verified by an example of the centralized optimal control for a large-size robot population.
This paper proposes a cooperative visual object tracking by multi-robot system, where robust cognitive sharing is essential between the robots. However, one of the main issues in vision-based distributed observation i...
详细信息
ISBN:
(纸本)9783642327223
This paper proposes a cooperative visual object tracking by multi-robot system, where robust cognitive sharing is essential between the robots. However, one of the main issues in vision-based distributed observation is the significant differences in the background image for the interested object. According to the observing point of the robot, effective invariant feature to identify the interested object is different. In this paper, we propose an ambiguity index to select better feature algorithm for object tracking. Experimental result shows promising result for the effective multi-robot cognitive sharing.
In this paper, we present a novel method for performing collective transport in the presence of obstacles. Three robots are physically connected to an object to be transported from a start to a goal location. The task...
详细信息
ISBN:
(纸本)9783642327223
In this paper, we present a novel method for performing collective transport in the presence of obstacles. Three robots are physically connected to an object to be transported from a start to a goal location. The task is particularly challenging because the robots have a heterogeneous perception of the environment. In fact, the goal and the obstacles can be perceived only by some of the robots. Hence, the task requires appropriate negotiation of the direction among the robots. We developed a novel negotiation strategy in order to tackle this challenge. We perform experiments in simulation. In the experiments, we analyze efficiency in an environment with only one obstacle, and robustness in an environment with several obstacles.
Reconfiguration allows a self-reconfiguring modular robot to adapt to its environment. The reconfiguration planning problem is one of the key algorithmic challenges in realizing self-reconfiguration. Many existing suc...
详细信息
ISBN:
(纸本)9783642327223
Reconfiguration allows a self-reconfiguring modular robot to adapt to its environment. The reconfiguration planning problem is one of the key algorithmic challenges in realizing self-reconfiguration. Many existing successful approaches rely on grouping modules together to act as meta-modules. However, we are interested in reconfiguration planning that does not impose fixed meta-module relationships but instead forms cooperative relationships between modules dynamically. This approach avoids the need to hand-code meta-module motions and potentially allows reconfiguration with fewer modules. In this paper we present a general two-level reconfiguration framework. The top level plans in module-connector space using distributed dynamic programming. The lower level accepts a transition function for the kinematic model of the chosen module type as input. As an example, we implement such a transition function for the 3R, SuperBot-style module. Although not explored in this paper, this general approach is naturally extended to consider power use, clock time, or other quantities of interest.
暂无评论