Pub Date : 2021-10-25DOI: 10.1109/SSRR53300.2021.9597681
Jack D. Center, N. Ahmed
This paper develops a novel algorithmic motion planning approach that allows privately-owned volunteer robotic equipment, which might otherwise remain unused, to provide value to a network of relief workers or other robots engaged in a search effort. The specific ‘Volunteer Robot Problem’ considered here is a path planning problem that asks an autonomous volunteer robot to balance information gathering tasks with data fusion when it becomes part of an ad hoc distributed robotic network supporting a deliberate relief effort. Related prior work considered optimal search strategies over information fields, but often these methods assume direct access to high performance centralized computing or to continuous communications for decentralized coordination. In this work, we provide a formal definition for the ‘Volunteer Robot Problem’ and information as it relates to general search tasks, and develop a novel information gathering planning algorithm to solve it. Our method improves upon existing sample-based planning algorithms by accounting for intermittent data fusion opportunities with other search agents, while remaining computationally lightweight and requiring minimal a priori knowledge of both ownship and other agents' states and capabilities. Simulation-based validation and comparisons to alternative planning approaches are provided of the algorithm through simulations for different multi-agent search scenarios and comparisons to other sampling-based algorithms for information-guided path planning.
{"title":"Data Fusion-Aware Motion Planning for Ad Hoc Robotic Search Teams","authors":"Jack D. Center, N. Ahmed","doi":"10.1109/SSRR53300.2021.9597681","DOIUrl":"https://doi.org/10.1109/SSRR53300.2021.9597681","url":null,"abstract":"This paper develops a novel algorithmic motion planning approach that allows privately-owned volunteer robotic equipment, which might otherwise remain unused, to provide value to a network of relief workers or other robots engaged in a search effort. The specific ‘Volunteer Robot Problem’ considered here is a path planning problem that asks an autonomous volunteer robot to balance information gathering tasks with data fusion when it becomes part of an ad hoc distributed robotic network supporting a deliberate relief effort. Related prior work considered optimal search strategies over information fields, but often these methods assume direct access to high performance centralized computing or to continuous communications for decentralized coordination. In this work, we provide a formal definition for the ‘Volunteer Robot Problem’ and information as it relates to general search tasks, and develop a novel information gathering planning algorithm to solve it. Our method improves upon existing sample-based planning algorithms by accounting for intermittent data fusion opportunities with other search agents, while remaining computationally lightweight and requiring minimal a priori knowledge of both ownship and other agents' states and capabilities. Simulation-based validation and comparisons to alternative planning approaches are provided of the algorithm through simulations for different multi-agent search scenarios and comparisons to other sampling-based algorithms for information-guided path planning.","PeriodicalId":423263,"journal":{"name":"2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134525581","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-25DOI: 10.1109/SSRR53300.2021.9597690
Kevin Daun, Marius Schnaubelt, S. Kohlbrecher, O. Stryk
For deployment in previously unknown, unstructured, and GPS-denied environments, autonomous mobile rescue robots need to localize themselves in such environments and create a map of it using a simultaneous localization and mapping (SLAM) approach. Continuous-time SLAM approaches represent the pose as a time-continuous estimate that provides high accuracy and allows correcting for distortions induced by motion during the scan capture. To enable robust and accurate real-time SLAM in challenging terrain, we propose HectorGrapher which enables accurate localization by continuous-time pose estimation and robust scan registration based on multiresolution signed distance functions. We evaluate the method in multiple publicly available real-world datasets, as well as a data set from the RoboCup 2021 Rescue League, where we applied the proposed method to win the Best-in-Class “Exploration and Mapping” Award.
{"title":"HectorGrapher: Continuous-time Lidar SLAM with Multi-resolution Signed Distance Function Registration for Challenging Terrain","authors":"Kevin Daun, Marius Schnaubelt, S. Kohlbrecher, O. Stryk","doi":"10.1109/SSRR53300.2021.9597690","DOIUrl":"https://doi.org/10.1109/SSRR53300.2021.9597690","url":null,"abstract":"For deployment in previously unknown, unstructured, and GPS-denied environments, autonomous mobile rescue robots need to localize themselves in such environments and create a map of it using a simultaneous localization and mapping (SLAM) approach. Continuous-time SLAM approaches represent the pose as a time-continuous estimate that provides high accuracy and allows correcting for distortions induced by motion during the scan capture. To enable robust and accurate real-time SLAM in challenging terrain, we propose HectorGrapher which enables accurate localization by continuous-time pose estimation and robust scan registration based on multiresolution signed distance functions. We evaluate the method in multiple publicly available real-world datasets, as well as a data set from the RoboCup 2021 Rescue League, where we applied the proposed method to win the Best-in-Class “Exploration and Mapping” Award.","PeriodicalId":423263,"journal":{"name":"2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"174 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116004512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-25DOI: 10.1109/SSRR53300.2021.9597688
B. A. Blakeslee, Giuseppe Loianno
We present an approach for selective, hierarchical allocation of sensing resources that aims to maximize information gain in exploratory missions such as search and rescue (SAR) or surveillance in an efficient manner. Specifically, we propose a methodology for perception-enabled SAR or crowd surveillance driven by anomaly detection based on low-level statistical assessment of a region. The characterizations of previously-observed regions are used to populate a window of observations that serves as “short-term memory,” providing a contextually-appropriate characterization of proximate regions in the scene. Currently-observed regions are compared with this short-term memory window, and if sufficiently dissimilar, can be considered as candidates for the presence of a SAR target or unexpected event. We adaptively allocate additional sensing resources for subsequent exploration of anomalous regions through a novel utility function that balances varied mission objectives and constraints including exploratory sensing actions, maintaining situational awareness, or ensuring some degree of confidence in self-localization. Simulation results validate the proposed approach and demonstrate its benefits with regards to efficiency in exploration while maximizing potential information gain and balancing other mission requirements and objectives.
{"title":"Selective and Hierarchical Allocation of Sensing Resources for Anomalous Target Identification in Exploratory Missions","authors":"B. A. Blakeslee, Giuseppe Loianno","doi":"10.1109/SSRR53300.2021.9597688","DOIUrl":"https://doi.org/10.1109/SSRR53300.2021.9597688","url":null,"abstract":"We present an approach for selective, hierarchical allocation of sensing resources that aims to maximize information gain in exploratory missions such as search and rescue (SAR) or surveillance in an efficient manner. Specifically, we propose a methodology for perception-enabled SAR or crowd surveillance driven by anomaly detection based on low-level statistical assessment of a region. The characterizations of previously-observed regions are used to populate a window of observations that serves as “short-term memory,” providing a contextually-appropriate characterization of proximate regions in the scene. Currently-observed regions are compared with this short-term memory window, and if sufficiently dissimilar, can be considered as candidates for the presence of a SAR target or unexpected event. We adaptively allocate additional sensing resources for subsequent exploration of anomalous regions through a novel utility function that balances varied mission objectives and constraints including exploratory sensing actions, maintaining situational awareness, or ensuring some degree of confidence in self-localization. Simulation results validate the proposed approach and demonstrate its benefits with regards to efficiency in exploration while maximizing potential information gain and balancing other mission requirements and objectives.","PeriodicalId":423263,"journal":{"name":"2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131970495","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-25DOI: 10.1109/SSRR53300.2021.9597863
Shotaro Kojima, Yuki Harata, K. Ohno, Takahiro Suzuki, Yoshito Okada, S. Tadokoro
Tracked vehicles are expected to be used for factory inspection such as in petrochemical refinery, in which the robot needs to navigate in narrow spaces. During the narrow space navigation, the robot needs to adjust its position in lateral direction. However, it is a difficult problem to realize lateral motion of tracked vehicles for factory inspection, because mechanical complexity is increased if the additional actuator is installed. In this paper, the authors propose a lateral skidding motion of tracked vehicles using wall reaction force. The proposed method convert the direction of driving force by actively colliding the wall with passive wheels, and realize the lateral motion without attaching the additional actuator. Experimental results show that the lateral skidding motion is realized on two types of floor material. In addition, the time for lateral positioning with manual operation was 20 % reduced when the proposed method was used. The use of external force is one solution to change the motion direction in narrow spaces.
{"title":"Lateral Skidding Motion of Tracked Vehicles using Wall Reaction Force","authors":"Shotaro Kojima, Yuki Harata, K. Ohno, Takahiro Suzuki, Yoshito Okada, S. Tadokoro","doi":"10.1109/SSRR53300.2021.9597863","DOIUrl":"https://doi.org/10.1109/SSRR53300.2021.9597863","url":null,"abstract":"Tracked vehicles are expected to be used for factory inspection such as in petrochemical refinery, in which the robot needs to navigate in narrow spaces. During the narrow space navigation, the robot needs to adjust its position in lateral direction. However, it is a difficult problem to realize lateral motion of tracked vehicles for factory inspection, because mechanical complexity is increased if the additional actuator is installed. In this paper, the authors propose a lateral skidding motion of tracked vehicles using wall reaction force. The proposed method convert the direction of driving force by actively colliding the wall with passive wheels, and realize the lateral motion without attaching the additional actuator. Experimental results show that the lateral skidding motion is realized on two types of floor material. In addition, the time for lateral positioning with manual operation was 20 % reduced when the proposed method was used. The use of external force is one solution to change the motion direction in narrow spaces.","PeriodicalId":423263,"journal":{"name":"2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127262550","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-25DOI: 10.1109/SSRR53300.2021.9597687
Rashid Alyassi, Majid Khonji, Xin Huang, Sungkweon Hong, Jorge Dias
Traffic intersections are natural bottlenecks in transportation networks where traffic lights have traditionally been used for vehicle coordination. With the advent of communication networks and Autonomous Vehicle (AV) technologies, new opportunities arise for more efficient automated schemes. However, with existing automated approaches, a key challenge lies in detecting and reasoning about uncertainty in the operating environment. Uncertainty arises primarily from AV trajectory tracking error and human-driven vehicle behavior. In this paper, we propose a risk-aware intelligent intersection system for AVs along with human-driven vehicles. We formulate the problem as a receding-horizon Chance-Constrained Partially Observable Markov Decision Process (CC-POMDP). We propose two fast risk estimation methods for detecting vehicle collisions. The first provides a theoretical upper bound on risk, whereas the second provides an empirical upper bound and runs faster, hence more suitable for real-time planning. We examine our approach under two scenarios: (1) a fully autonomous intersection with AVs only, and (2) a hybrid of signalized intersection for human-driven vehicles along with an intelligent scheme for AVs. We show via simulation that the system improves the intersection's efficiency and generates policies that operate within a risk threshold.
{"title":"Contingency-Aware Intersection System for Autonomous and Human-Driven Vehicles with Bounded Risk","authors":"Rashid Alyassi, Majid Khonji, Xin Huang, Sungkweon Hong, Jorge Dias","doi":"10.1109/SSRR53300.2021.9597687","DOIUrl":"https://doi.org/10.1109/SSRR53300.2021.9597687","url":null,"abstract":"Traffic intersections are natural bottlenecks in transportation networks where traffic lights have traditionally been used for vehicle coordination. With the advent of communication networks and Autonomous Vehicle (AV) technologies, new opportunities arise for more efficient automated schemes. However, with existing automated approaches, a key challenge lies in detecting and reasoning about uncertainty in the operating environment. Uncertainty arises primarily from AV trajectory tracking error and human-driven vehicle behavior. In this paper, we propose a risk-aware intelligent intersection system for AVs along with human-driven vehicles. We formulate the problem as a receding-horizon Chance-Constrained Partially Observable Markov Decision Process (CC-POMDP). We propose two fast risk estimation methods for detecting vehicle collisions. The first provides a theoretical upper bound on risk, whereas the second provides an empirical upper bound and runs faster, hence more suitable for real-time planning. We examine our approach under two scenarios: (1) a fully autonomous intersection with AVs only, and (2) a hybrid of signalized intersection for human-driven vehicles along with an intelligent scheme for AVs. We show via simulation that the system improves the intersection's efficiency and generates policies that operate within a risk threshold.","PeriodicalId":423263,"journal":{"name":"2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128732822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-25DOI: 10.1109/SSRR53300.2021.9597692
Nicolai Iversen, Aljaz Kramberger, Oscar Bowen Schofield, E. Ebeid
Unmanned Aerial Vehicles (UAVs) have been introduced in the energy domain to solve complex tasks involving operations in close proximity to active power lines. Previous research by the authors explore how to grasp such power lines to secure a split-core transformer around the conductor, and hereby harvest energy to recharge the UAVs batteries towards continuous operation. However, no previous research investigate how to integrate an energy harvester (current transformer) into a mechanical grasping solution for a UAV system. In this work, the authors present a novel approach to an integrated mechanism prioritizing low weight for extended flight time. By utilizing the strong electromagnetic forces, the system prove opportunity for further optimization and adoption in other use cases across the UAV domain as well.
{"title":"Novel Power Line Grasping Mechanism with Integrated Energy Harvester for UAV applications","authors":"Nicolai Iversen, Aljaz Kramberger, Oscar Bowen Schofield, E. Ebeid","doi":"10.1109/SSRR53300.2021.9597692","DOIUrl":"https://doi.org/10.1109/SSRR53300.2021.9597692","url":null,"abstract":"Unmanned Aerial Vehicles (UAVs) have been introduced in the energy domain to solve complex tasks involving operations in close proximity to active power lines. Previous research by the authors explore how to grasp such power lines to secure a split-core transformer around the conductor, and hereby harvest energy to recharge the UAVs batteries towards continuous operation. However, no previous research investigate how to integrate an energy harvester (current transformer) into a mechanical grasping solution for a UAV system. In this work, the authors present a novel approach to an integrated mechanism prioritizing low weight for extended flight time. By utilizing the strong electromagnetic forces, the system prove opportunity for further optimization and adoption in other use cases across the UAV domain as well.","PeriodicalId":423263,"journal":{"name":"2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130102702","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-25DOI: 10.1109/SSRR53300.2021.9597679
Jean Chagas Vaz, Norberto Torres-Reyes, P. Oh
A whole-body kinematics approach is applied to a humanoid for maneuvering material-handling equipment normally used during disaster response scenarios. Dynamically different carts are used to explore the effects on gait stability. A shopping cart and a wheelbarrow are both utilized with emphasis being on the latter. In addition, external factors such as terrain and distinct loads are also varied in order to assess the impacts these may have on cart pushing. A full sized humanoid is used as a platform to evaluate gait performance. Furthermore, gait quality was assessed throughout different scenarios by calculating the ZMP error. Experimental results showed a 95% success rate throughout a varied range of tests.
{"title":"Humanoid Interaction with Material-Moving Carts and Wheelbarrows","authors":"Jean Chagas Vaz, Norberto Torres-Reyes, P. Oh","doi":"10.1109/SSRR53300.2021.9597679","DOIUrl":"https://doi.org/10.1109/SSRR53300.2021.9597679","url":null,"abstract":"A whole-body kinematics approach is applied to a humanoid for maneuvering material-handling equipment normally used during disaster response scenarios. Dynamically different carts are used to explore the effects on gait stability. A shopping cart and a wheelbarrow are both utilized with emphasis being on the latter. In addition, external factors such as terrain and distinct loads are also varied in order to assess the impacts these may have on cart pushing. A full sized humanoid is used as a platform to evaluate gait performance. Furthermore, gait quality was assessed throughout different scenarios by calculating the ZMP error. Experimental results showed a 95% success rate throughout a varied range of tests.","PeriodicalId":423263,"journal":{"name":"2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125774816","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-25DOI: 10.1109/SSRR53300.2021.9597689
Zifan Xu, Xuesu Xiao, Garrett A. Warnell, Anirudh Nair, P. Stone
While decades of research efforts have been devoted to developing classical autonomous navigation systems to move robots from one point to another in a collision-free manner, machine learning approaches to navigation have been recently proposed to learn navigation behaviors from data. Two representative paradigms are end-to-end learning (directly from perception to motion) and parameter learning (from perception to parameters used by a classical underlying planner). These two types of methods are believed to have complementary pros and cons: parameter learning is expected to be robust to different scenarios, have provable guarantees, and exhibit explainable behaviors; end-to-end learning does not require extensive engineering and has the potential to outperform approaches that rely on classical systems. However, these beliefs have not been verified through real-world experiments in a comprehensive way. In this paper, we report on an extensive study to compare end-to-end and parameter learning for local motion planners in a large suite of simulated and physical experiments. In particular, we test the performance of end-to-end motion policies, which directly compute raw motor commands, and parameter policies, which compute parameters to be used by classical planners, with different inputs (e.g., raw sensor data, costmaps), and provide an analysis of the results.
{"title":"Machine Learning Methods for Local Motion Planning: A Study of End-to-End vs. Parameter Learning","authors":"Zifan Xu, Xuesu Xiao, Garrett A. Warnell, Anirudh Nair, P. Stone","doi":"10.1109/SSRR53300.2021.9597689","DOIUrl":"https://doi.org/10.1109/SSRR53300.2021.9597689","url":null,"abstract":"While decades of research efforts have been devoted to developing classical autonomous navigation systems to move robots from one point to another in a collision-free manner, machine learning approaches to navigation have been recently proposed to learn navigation behaviors from data. Two representative paradigms are end-to-end learning (directly from perception to motion) and parameter learning (from perception to parameters used by a classical underlying planner). These two types of methods are believed to have complementary pros and cons: parameter learning is expected to be robust to different scenarios, have provable guarantees, and exhibit explainable behaviors; end-to-end learning does not require extensive engineering and has the potential to outperform approaches that rely on classical systems. However, these beliefs have not been verified through real-world experiments in a comprehensive way. In this paper, we report on an extensive study to compare end-to-end and parameter learning for local motion planners in a large suite of simulated and physical experiments. In particular, we test the performance of end-to-end motion policies, which directly compute raw motor commands, and parameter policies, which compute parameters to be used by classical planners, with different inputs (e.g., raw sensor data, costmaps), and provide an analysis of the results.","PeriodicalId":423263,"journal":{"name":"2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134462396","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-25DOI: 10.1109/SSRR53300.2021.9597684
Sarah Al-Hussaini, J. Gregory, N. Dhanaraj, Satyandra K. Gupta
In a multi-agent mission with failures, uncertainty, complex dependencies, and intermittent information flow, the role of human supervisors is stressful and challenging. Alerts based on future mission predictions can be useful to assist the supervisors in responding to mission updates quickly, and devise more effective strategies. Monte-Carlo forward simulations can be used to estimate future mission states and build probability distributions of possible mission outcomes and generate alerts. However, in order to get reasonable estimates, we need a large number of simulations, representing a long-duration multi robot mission. All this needs to be performed within seconds, and therefore traditional physics based robotic simulations are infeasible. We adapt ideas from discrete event simulation paradigm, and present our novel simulation techniques like adaptive time step size, robot grouping, and intelligent time interval selection. Our technique achieves a sufficient level of accuracy in estimating probabilities, thereby generating higher quality alerts, while lowering overall fidelity of the discrete simulations for faster computation. We also provide theoretical insights on error levels in probability estimation using our method, which can guide in choosing appropriate levels of fidelity while maintaining accuracy requirements in different application scenarios. Lastly, we demonstrate sufficiently accurate real-time alert generation for a few representative mission scenarios, where the computational time is in the order of seconds using our adaptive techniques.
{"title":"A Simulation-Based Framework for Generating Alerts for Human-Supervised Multi-Robot Teams in Challenging Environments","authors":"Sarah Al-Hussaini, J. Gregory, N. Dhanaraj, Satyandra K. Gupta","doi":"10.1109/SSRR53300.2021.9597684","DOIUrl":"https://doi.org/10.1109/SSRR53300.2021.9597684","url":null,"abstract":"In a multi-agent mission with failures, uncertainty, complex dependencies, and intermittent information flow, the role of human supervisors is stressful and challenging. Alerts based on future mission predictions can be useful to assist the supervisors in responding to mission updates quickly, and devise more effective strategies. Monte-Carlo forward simulations can be used to estimate future mission states and build probability distributions of possible mission outcomes and generate alerts. However, in order to get reasonable estimates, we need a large number of simulations, representing a long-duration multi robot mission. All this needs to be performed within seconds, and therefore traditional physics based robotic simulations are infeasible. We adapt ideas from discrete event simulation paradigm, and present our novel simulation techniques like adaptive time step size, robot grouping, and intelligent time interval selection. Our technique achieves a sufficient level of accuracy in estimating probabilities, thereby generating higher quality alerts, while lowering overall fidelity of the discrete simulations for faster computation. We also provide theoretical insights on error levels in probability estimation using our method, which can guide in choosing appropriate levels of fidelity while maintaining accuracy requirements in different application scenarios. Lastly, we demonstrate sufficiently accurate real-time alert generation for a few representative mission scenarios, where the computational time is in the order of seconds using our adaptive techniques.","PeriodicalId":423263,"journal":{"name":"2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131603041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-10-25DOI: 10.1109/SSRR53300.2021.9597871
Bradley Woosley, Carlos Nieto-Granda, J. Rogers, Nicholas Fung, Arthur Schang
Teams of autonomous mobile robots have potential to contribute to surveillance as well as search and rescue operations. Larger and more complex disaster scenarios with high operational tempo, such as when delay may mean further loss of life, may benefit from cooperative teams of many robots working together for efficient search operations. Unfortunately, these scenarios also exhibit communications disruptions which can limit the ability for distributed algorithms to coordinate the actions of a team of coordinating robots. This paper will present an approach to overcome these communications disruptions by predicting the bids of disconnected teammates in a distributed auction over a spatially partitioned set of exploration tasks.
{"title":"Bid Prediction for Multi-Robot Exploration with Disrupted Communications","authors":"Bradley Woosley, Carlos Nieto-Granda, J. Rogers, Nicholas Fung, Arthur Schang","doi":"10.1109/SSRR53300.2021.9597871","DOIUrl":"https://doi.org/10.1109/SSRR53300.2021.9597871","url":null,"abstract":"Teams of autonomous mobile robots have potential to contribute to surveillance as well as search and rescue operations. Larger and more complex disaster scenarios with high operational tempo, such as when delay may mean further loss of life, may benefit from cooperative teams of many robots working together for efficient search operations. Unfortunately, these scenarios also exhibit communications disruptions which can limit the ability for distributed algorithms to coordinate the actions of a team of coordinating robots. This paper will present an approach to overcome these communications disruptions by predicting the bids of disconnected teammates in a distributed auction over a spatially partitioned set of exploration tasks.","PeriodicalId":423263,"journal":{"name":"2021 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128306355","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：