Robot Platooning Strategy for Search and Rescue Operations

Manuel, Melvin P.; Faied, Mariam; Krishnan, M.; Paulik, Mark

doi:10.1007/s11370-021-00390-7

Cited by 7 publications

(6 citation statements)

References 18 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Autonomous vehicles (aerial and/or ground) have commonly been proposed for urban search and rescue (USAR) [1][2][3][4][5][6][7][8][9] and wilderness search and rescue (WiSAR) applications [10][11][12][13][14][15][16][17][18]. They have also been suggested for city searches [19][20][21][22][23][24], although, with limited scale or autonomy.…”

Section: Introductionmentioning

confidence: 99%

An Aerial Robotic Missing-Person Search in Urban Settings—A Probabilistic Approach

Haigh,

Nejat,

Benhabib

2024

Robotics

View full text Add to dashboard Cite

Autonomous robotic teams have been proposed for a variety of lost-person searches in wilderness and urban settings. In the latter scenarios, for missing persons, the application of such teams, however, is more challenging than it would be in the wilderness. This paper, specifically, examines the application of an autonomous team of unmanned aerial vehicles (UAVs) to perform a sparse, mobile-target search in an urban setting. A novel multi-UAV search-trajectory planning method, which relies on the prediction of the missing-person’s motion, given a known map of the search environment, is the primary focus. The proposed method incorporates periodic updates of the estimates of where the lost/missing person may be, allowing for intelligent re-coverage of previously searched areas. Additional significant contributions of this work include a behavior-based motion-prediction method for missing persons and a novel non-parametric estimator for iso-probability-based (missing-person-location) curves. Simulated experiments are presented to illustrate the effectiveness of the proposed search-planning method, demonstrating higher rates of missing-person detection and in shorter times compared to other methods.

show abstract

Section: Introductionmentioning

confidence: 99%

An Aerial Robotic Missing-Person Search in Urban Settings—A Probabilistic Approach

Haigh,

Nejat,

Benhabib

2024

Robotics

View full text Add to dashboard Cite

show abstract

“…The greatest anticipated technological advancement in the near future is autonomous ground vehicles (AGV), which operate entirely automatically. A vehicle operating autonomously requires precise and reliable information regarding its position for a successful navigation [1], [2], [3], [4]. There are currently many popular methods of providing comparatively reliable positioning information, such as the Global Navigation Satellite System (GNSS), Visual Odometry, and the Inertial Navigation System (INS) [5], [6], [7], [8], [9], [10], [11].…”

Section: Introductionmentioning

confidence: 99%

Incorporating Learned Depth Perception Into Monocular Visual Odometry to Improve Scale Recovery

Mailka,

Abouzahir,

Ramzi

2023

IJACSA

View full text Add to dashboard Cite

A growing interest in autonomous driving has led to a comprehensive study of visual odometry (VO). It has been well studied how VO can estimate the pose of moving objects by examining the images taken from onboard cameras. In the last decade, it has been proposed that deep learning under supervision can be employed to estimate depth maps and visual odometry (VO). In this paper, we propose a DPT (Dense Prediction Transformer)-based monocular visual odometry method for scale estimation. Scale-drift problems are common in traditional monocular systems and in recent deep learning studies. In order to recover the scale, it is imperative that depth estimation to be accurate. A framework for dense prediction challenges that bases its computation on vision transformers instead of convolutional networks is characterized as an accurate model that is utilized to estimate depth maps. Scale recovery and depth refinement are accomplished iteratively. This allows our approach to simultaneously increase the depth estimate while eradicating scale drift. The depth map estimated using the DPT model is accurate enough for the purpose of achieving the best efficiency possible on a VO benchmark, eliminating the scaling drift issue.

show abstract

“…Recent advances in autonomous robotic systems are promising to shape future industries and services such as public spaces surveillance operations [1], search and rescue applications [2], sample and data collection in large manufacturing plants and dangerous places [3], maintenance operations [4], logistic services [5], emergency first responders [6], and military operations [7]. This research aims to evolve the multi-robot team to function as a cooperative team of specialized robotic agents based on formal consideration of each individual robot's specialization.…”

Section: Introductionmentioning

confidence: 99%

Task Allocation for Multi-Agent Specialized Systems Using Probabilistic Estimate of Robots Competencies

Al-Buraiki,

Payeur

2023

IEEE Access

View full text Add to dashboard Cite

An innovative task allocation scheme for a multi-robotic system in a specific context is introduced in this paper, where functionalities of the individual robots are considered, and a probabilistic estimate of each robot specialization is computed. The problem is formulated based on the assumption that each robotic agent is qualified for performing specialized functionalities, and the expected tasks distributed in the surrounding environment enforce specific requirements. The task allocation algorithm evolves through three stages to compute individual robot allocation probabilities. First, recognizing the features of the target task is addressed by leveraging the output of a vision system in the sensing layer to drive the proposed agent-task allocation scheme. Second, a matching strategy is formulated to match each robot's unique functionalities with the corresponding features of target tasks. The specialization of each agent is developed in two approaches as a main part of the matching process: first, a binary association of the capabilities of each agent, and second, based on the suitability of each agent to tackle the various tasks. Finally, the developed robot-task-matching system is expanded to fully utilize the potential of the robot specializations, considering the agents attendance level with the availability of services of each agent. The developed framework is extensively validated through MATLAB simulations. To demonstrate the feasibility of the proposed system for real-life applications, the developed framework is implemented on real robots. The results show that the performance of the proposed allocation scheme is increased significantly when the suitability levels of the agents' specializations inform the task allocation process and agent attendance levels are activated.INDEX TERMS Robot-task matching, heterogeneous robotic system, robots' specialized functionalities, probabilistic estimation of specialization.

show abstract

Robot Platooning Strategy for Search and Rescue Operations

Cited by 7 publications

References 18 publications

An Aerial Robotic Missing-Person Search in Urban Settings—A Probabilistic Approach

An Aerial Robotic Missing-Person Search in Urban Settings—A Probabilistic Approach

Incorporating Learned Depth Perception Into Monocular Visual Odometry to Improve Scale Recovery

Task Allocation for Multi-Agent Specialized Systems Using Probabilistic Estimate of Robots Competencies

Contact Info

Product

Resources

About