14,090 Hits in 3.4 sec

Metrics for performance benchmarking of multi-robot exploration

Zhi Yan, Luc Fabresse, Jannik Laval, Noury Bouraqadi
2015 2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)  
In this paper, we focus on performance benchmarking of multi-robot systems which explore and map unknown terrains.  ...  We present a collection of metrics to objectively compare different algorithms that can be applied to collaborative multi-robot exploration.  ...  CONCLUSIONS In this paper, we considered the performance benchmarking for multi-robot exploration.  ... 
doi:10.1109/iros.2015.7353852 dblp:conf/iros/YanFLB15 fatcat:zmcxig2yjzeevberzw5xyhzt7a

Building a ROS-Based Testbed for Realistic Multi-Robot Simulation: Taking the Exploration as an Example

Zhi Yan, Luc Fabresse, Jannik Laval, Noury Bouraqadi
2017 Robotics  
We also report a series of experiments on multi-robot exploration, in order to demonstrate the capabilities of our testbed.  ...  explicit all elements of a benchmark such as parameters, measurements and metrics.  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/robotics6030021 fatcat:anwrkp2xynasplc7fhagqqqt6q

Evaluating maps produced by urban search and rescue robots: lessons learned from RoboCup

Benjamin Balaguer, Stephen Balakirsky, Stefano Carpin, Arnoud Visser
2009 Autonomous Robots  
The procedure aims to evaluate the quality of maps produced by multi-robot systems with respect to a number of factors, including usability, exploration, annotation and other aspects relevant to robots  ...  We also show how a benchmarking methodology developed for a simulation testbed effortlessly and faithfully transfers to maps built by a real robot.  ...  We subscribe to Baltes's statement that competitions do not provide the ultimate benchmark for robotic performance.  ... 
doi:10.1007/s10514-009-9141-z fatcat:pdsnoxnghjf3hafijkvbi2hs54

Towards an Engineering Science of Robot Foraging [chapter]

Alan F. T. Winfield
2009 Distributed Autonomous Robotic Systems 8  
Foraging is a benchmark problem in robotics -especially for distributed autonomous robotic systems.  ...  The systematic study of robot foraging is important for several reasons: firstly, because foraging is a metaphor for the broad class of problems integrating robotic exploration, navigation and object identification  ...  Introduction Foraging is a benchmark problem for robotics, especially for multi-robot systems.  ... 
doi:10.1007/978-3-642-00644-9_16 dblp:conf/dars/Winfield08 fatcat:wssd7hbrmnc3niagyvjrc7svhq

Response Time Estimation in Robotics Using Hierarchical Performance Modeling Approach

Ahmed Alsheikhy, Muhannad Almutiry
2021 Advances in Science and Technology Research Journal  
The Multi-disciplinary domain of robotics has become instrumental in advancements in many fi elds such as medical, military and industrial automation.  ...  Measuring or estimating a performance metric such as response time or throughput under severe circumstances is crucial since designers want to know the behavior of robots and their reaction when a constrained  ...  Acknowledgement The authors gratefully acknowledge the approval and the support of this research study by the grant no. 1114-ENG-2017-1-8-F from the Deanship of Scientific Research at Northern Border University  ... 
doi:10.12913/22998624/142655 fatcat:5sgvx65kqfexpfoqn3u2pn34pe

CompoSuite: A Compositional Reinforcement Learning Benchmark [article]

Jorge A. Mendez, Marcel Hussing, Meghna Gummadi, Eric Eaton
2022 arXiv   pre-print
We present CompoSuite, an open-source simulated robotic manipulation benchmark for compositional multi-task reinforcement learning (RL).  ...  First, varying the robot/object/objective/obstacle elements leads to hundreds of RL tasks, each of which requires a meaningfully different behavior.  ...  ACKNOWLEDGMENTS We would like to thank Spencer Solit for help in the early stages of development of CompoSuite, and David Kent for technical feedback about the robot simulator.  ... 
arXiv:2207.04136v1 fatcat:xmcmtspgu5babpz3pkpx5dm5c4

Deep Reinforcement Learning for Decentralized Multi-Robot Exploration with Macro Actions [article]

Aaron Hao Tan, Federico Pizarro Bejarano, Goldie Nejat
2021 arXiv   pre-print
The results showed that our MADE-Net method was able to outperform all benchmark methods in terms of computation time, total travel distance, number of local interactions between robots, and exploration  ...  In this paper, we present the first Macro Action Decentralized Exploration Network (MADE-Net) using multi-agent deep reinforcement learning to address the challenges of communication dropouts during multi-robot  ...  For example, as the CSP decreases from 100% to 0%, it had better performance for all the metrics compared to the benchmark methods.  ... 
arXiv:2110.02181v1 fatcat:jcsgrvlxwfeotnashpyf6yomfy

Applying Aspects of Multi-robot Search to Particle Swarm Optimization [chapter]

Jim Pugh, Loïc Segapelli, Alcherio Martinoli
2006 Lecture Notes in Computer Science  
The new algorithms are tested on several standard benchmark problems with a varying number of dimensions and are shown to offer superior performances to the standard algorithm in some cases.  ...  We present a modified version of the Particle swarm Optimization algorithm in which we adjust the virtual swarm search by incorporating inter-agent dynamics native to multi-robot search scenarios.  ...  A one-to-one mapping from particles in PSO to robots in a collective robotic system was used for distributed unsupervised multi-robot learning in [12] .  ... 
doi:10.1007/11839088_54 fatcat:o3s6ch45afg5xfi2ceidwkm7gu

Performance study of single-query motion planning for grasp execution using various manipulators

Jonathan Meijer, Qujiang Lei, Martijn Wisse
2017 2017 18th International Conference on Advanced Robotics (ICAR)  
Sampling-based motion planners of OMPL available for use in MoveIt! are compared by performing several grasping-related motion planning problems.  ...  The performance of the planners is measured by means of solved runs, computing time and path length.  ...  Performance depends on the need of the user, high performance for one metric can result in low performance for an other metric.  ... 
doi:10.1109/icar.2017.8023648 dblp:conf/icar/MeijerLW17 fatcat:bkg4jcyqjjclpj6zrq6535bfuy

FLYBO: A Unified Benchmark Environment for Autonomous Flying Robots

Anthony Brunel, Amine Bourki, Olivier Strauss, Cedric Demonceaux
2021 2021 International Conference on 3D Vision (3DV)  
FLYBO provides datasets, references and a framework to benchmark such systems w.r.t their volumetric exploration and online surface reconstruction capabilities.  ...  Figure 1: An MAV equipped with odometry-and active depth sensors autonomously explores a complex synthetic area from FLYBO (a) while gradually mapping the scene throughout different exploration stages  ...  This is made possible thanks to the unified nature of our FLYBO benchmarking framework. Datasets and Benchmarks for Autonomous Flying Robots.  ... 
doi:10.1109/3dv53792.2021.00149 fatcat:zyuo4zp3vndq5etzahnkb5n454

USARSim: a RoboCup virtual urban search and rescue competition

Stephen Balakirsky, Chris Scrapper, Stefano Carpin, Mike Lewis, Grant R. Gerhart, Douglas W. Gage, Charles M. Shoemaker
2007 Unmanned Systems Technology IX  
The framework allows for the realistic modeling of robots, sensors, and actuators, as well as complex, unstructured, dynamic environments.  ...  A virtual USAR robotic competition was established in 2006 under the RoboCup umbrella to foster collaboration amongst institutions and to provide benchmark test environments for system evaluation.  ...  : • Autonomous multi-robot control, • Human, multi-robot interfaces, • True 3D mapping and exploration of environments by multi-robot teams, • Development of novel mobility modes for obstacle traversal  ... 
doi:10.1117/12.720735 fatcat:hw4qewtbc5d3vexrtlsu5jchr4

Exploration and Mapping with Groups of Robots: Recent Trends

Alberto Quattrini Li
2020 Current Robotics Reports  
Purpose of Review Multi-robot exploration-i.e., the problem of mapping unknown features of an environment-is fundamental in many tasks, including search and rescue, planetary exploration, and environmental  ...  and attacks, so that robots can be deployed safely in real-world environments.  ...  Human and Animal Rights and Informed Consent This article does not contain any studies with human or animal subjects performed by any of the authors.  ... 
doi:10.1007/s43154-020-00030-5 fatcat:ryasgbxoyfgtvehhzbfnespeie

AxBench: A Multiplatform Benchmark Suite for Approximate Computing

Amir Yazdanbakhsh, Divya Mahajan, Hadi Esmaeilzadeh, Pejman Lotfi-Kamran
2017 IEEE design & test  
In this paper, we introduce AXBENCH, a general, diverse and representative set of benchmarks for CPUs, GPUs, and hardware design.  ...  The current paradigm of microprocessor design falls significantly short of the historical cadence of performance improvements.  ...  For example, image difference, which is an appropriate quality metric for image processing applications, is not applicable to a robotic application, which changes the location of a robotic arm.  ... 
doi:10.1109/mdat.2016.2630270 fatcat:torsq2gu35gwbeortupgjcylym

Multi-Objective Multi-Learner Robot Trajectory Prediction Method for IoT Mobile Robot Systems

Fei Peng, Li Zheng, Zhu Duan, Yu Xia
2022 Electronics  
Robot trajectory prediction is an essential part of building digital twin systems and ensuring the high-performance navigation of IoT mobile robots.  ...  In the study, a novel two-stage multi-objective multi-learner model is proposed for robot trajectory prediction.  ...  All multi-objective optimization algorithms are effective for ensemble prediction of robot trajectory.  ... 
doi:10.3390/electronics11132094 fatcat:zvjsqlcnqjgf3fesenmgw6kgee

An empirical study of single-query motion planning for grasp execution

Jonathan Meijer, Qujiang Lei, Martijn Wisse
2017 2017 IEEE International Conference on Advanced Intelligent Mechatronics (AIM)  
Simultaneously, this paper presents useful benchmark data. The single-query performance of the planners was measured by means of solved runs, computing time and path length.  ...  Based on the results, recommendations are made for planner choice that shows high performance.  ...  For the defined benchmarks, the bi-directional planners SBL, LBKPIECE, RRTConnect and BiTRRT are high performing planners in terms of all the studied metrics.  ... 
doi:10.1109/aim.2017.8014187 dblp:conf/aimech/MeijerLW17 fatcat:pokvjykepnbpllgttbfzn4u7hm
« Previous Showing results 1 — 15 out of 14,090 results