Pub Date : 2022-11-08DOI: 10.1109/SSRR56537.2022.10018693
Chenglong Yu, Zhiqi Li, Weixin Chou, Hong Liu
Recently, with the robotic technique developing toward precision and intelligence, robots have been used more widely in human life and production. As a common feature in the foreseen applications, robots should be able to detect unexpected collisions while ensuring dynamic accuracy, so as to improve safety at work. In the previous model-based collision detection solution, most methods assume that the robot dynamic model is complete and accurate. Unfortunately, reliable robot dynamics is hard to obtain due to model uncertainties, assembly errors, and the lack of information provided by manufacturers. This paper proposed a novel low-gain control strategy based on sparse feature learning dynamics. Firstly, without considering the physical structure parameters, the dynamics was learned directly via the data-driven technique. Secondly, according to the learned accurate dynamics, a model-based low-gain controller was designed to ensure control performance while avoiding excessive unspecified force. Finally, using this control strategy, sensorless collision detection was realized in a 7-DOF manipulator and the performance of the proposed method was evaluated.
{"title":"Low-gain Control Strategy for Robot Manipulators Based on Sparse Feature Learning Dynamics with an Application to Collision Detection","authors":"Chenglong Yu, Zhiqi Li, Weixin Chou, Hong Liu","doi":"10.1109/SSRR56537.2022.10018693","DOIUrl":"https://doi.org/10.1109/SSRR56537.2022.10018693","url":null,"abstract":"Recently, with the robotic technique developing toward precision and intelligence, robots have been used more widely in human life and production. As a common feature in the foreseen applications, robots should be able to detect unexpected collisions while ensuring dynamic accuracy, so as to improve safety at work. In the previous model-based collision detection solution, most methods assume that the robot dynamic model is complete and accurate. Unfortunately, reliable robot dynamics is hard to obtain due to model uncertainties, assembly errors, and the lack of information provided by manufacturers. This paper proposed a novel low-gain control strategy based on sparse feature learning dynamics. Firstly, without considering the physical structure parameters, the dynamics was learned directly via the data-driven technique. Secondly, according to the learned accurate dynamics, a model-based low-gain controller was designed to ensure control performance while avoiding excessive unspecified force. Finally, using this control strategy, sensorless collision detection was realized in a 7-DOF manipulator and the performance of the proposed method was evaluated.","PeriodicalId":272862,"journal":{"name":"2022 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133347754","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 : 2022-11-08DOI: 10.1109/SSRR56537.2022.10018678
Zane Imran, Adam Scott, Joao Buzzatto, Minas Liarokapis
Unmanned Aerial Vehicles (UAVs) are quickly becoming the future of payload delivery. Over the past few years, many designs have surfaced with a variety of different solutions to this problem. Current systems are often bulky and designed for a specific purpose. This makes them difficult to adapt to new environments or payloads. This paper details the design and development of a novel, reconfigurable vehicle system that is able to adapt to a variety of environments and payload dimensions. The system consists of multiple individual mobile modules equipped with rotors, which work collaboratively to grasp a single payload. Each module has the capability to act independently of one another and can move along a 2D plane in any direction, like a mobile robot. Grasping is accomplished using a tethering system which joins adjacent modules together and allows them to clamp onto a payload. The payload becomes the backbone that offers rigidity to the formed drone. Thus, upon reconfiguration, the system is essentially a rigid body with the modules on the exterior surrounding the payload. The system could then takeoff and transport the package to a different location. Significant testing was carried out with the designed prototype, and open loop takeoff was achieved, proving the feasibility of the concept. The system has been experimentally tested to provide up to 14 N per vehicle with a theoretical capacity of 20 N. This results in each module having an estimated payload of 500 g with 25% thrust capacity still available.
{"title":"On the Development of Tethered, Modular, Self-Attaching, Reconfigurable Vehicles for Aerial Grasping and Package Delivery","authors":"Zane Imran, Adam Scott, Joao Buzzatto, Minas Liarokapis","doi":"10.1109/SSRR56537.2022.10018678","DOIUrl":"https://doi.org/10.1109/SSRR56537.2022.10018678","url":null,"abstract":"Unmanned Aerial Vehicles (UAVs) are quickly becoming the future of payload delivery. Over the past few years, many designs have surfaced with a variety of different solutions to this problem. Current systems are often bulky and designed for a specific purpose. This makes them difficult to adapt to new environments or payloads. This paper details the design and development of a novel, reconfigurable vehicle system that is able to adapt to a variety of environments and payload dimensions. The system consists of multiple individual mobile modules equipped with rotors, which work collaboratively to grasp a single payload. Each module has the capability to act independently of one another and can move along a 2D plane in any direction, like a mobile robot. Grasping is accomplished using a tethering system which joins adjacent modules together and allows them to clamp onto a payload. The payload becomes the backbone that offers rigidity to the formed drone. Thus, upon reconfiguration, the system is essentially a rigid body with the modules on the exterior surrounding the payload. The system could then takeoff and transport the package to a different location. Significant testing was carried out with the designed prototype, and open loop takeoff was achieved, proving the feasibility of the concept. The system has been experimentally tested to provide up to 14 N per vehicle with a theoretical capacity of 20 N. This results in each module having an estimated payload of 500 g with 25% thrust capacity still available.","PeriodicalId":272862,"journal":{"name":"2022 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124039117","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 : 2022-11-08DOI: 10.1109/SSRR56537.2022.10018726
Katrin Becker, M. Oehler, O. Stryk
Ahstract- On construction sites, progress must be monitored continuously to ensure that the current state corresponds to the planned state in order to increase efficiency, safety and detect construction defects at an early stage. Autonomous mobile robotscan document the state of construction with high data quality and consistency. However, finding a path that fully covers the construction site is a challenging task as it can be large, slowly changing over time, and contain dynamic objects. Existing approaches are either exploration approaches that require a long time to explore the entire building, object scanning approaches that are not suitable for large and complex buildings, or planning approaches that only consider 2D coverage. In this paper, we present a novel approach for planning an efficient 3D path for progress monitoring on large construction sites with multiple levels. By making use of an existing 3D model we ensure that all surfaces of the building are covered by the sensor payload such as a 360-degree camera or a lidar. This enables the consistent and reliable monitoring of construction site progress with an autonomous ground robot. We demonstrate the effectiveness of the proposed planner on an artificial and a real building model, showing that much shorter paths and better coverage are achieved than with a traditional exploration planner.
{"title":"3D Coverage Path Planning for Efficient Construction Progress Monitoring","authors":"Katrin Becker, M. Oehler, O. Stryk","doi":"10.1109/SSRR56537.2022.10018726","DOIUrl":"https://doi.org/10.1109/SSRR56537.2022.10018726","url":null,"abstract":"Ahstract- On construction sites, progress must be monitored continuously to ensure that the current state corresponds to the planned state in order to increase efficiency, safety and detect construction defects at an early stage. Autonomous mobile robotscan document the state of construction with high data quality and consistency. However, finding a path that fully covers the construction site is a challenging task as it can be large, slowly changing over time, and contain dynamic objects. Existing approaches are either exploration approaches that require a long time to explore the entire building, object scanning approaches that are not suitable for large and complex buildings, or planning approaches that only consider 2D coverage. In this paper, we present a novel approach for planning an efficient 3D path for progress monitoring on large construction sites with multiple levels. By making use of an existing 3D model we ensure that all surfaces of the building are covered by the sensor payload such as a 360-degree camera or a lidar. This enables the consistent and reliable monitoring of construction site progress with an autonomous ground robot. We demonstrate the effectiveness of the proposed planner on an artificial and a real building model, showing that much shorter paths and better coverage are achieved than with a traditional exploration planner.","PeriodicalId":272862,"journal":{"name":"2022 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122660515","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 : 2022-11-08DOI: 10.1109/SSRR56537.2022.10018752
Jasper Süß, Marius Schnaubelt, O. Stryk
To be able to perform manipulation tasks within an unknown environment, rescue robots require a detailed model of their surroundings, which is often generated using registered depth images as an input. However, erroneous camera registrations due to noisy motor encoder readings, a faulty kinematic model or other error sources can drastically reduce the model quality. Most existing approaches register the pose of a free-floating single camera without considering constraints by the kinematic robot configuration. In contrast, ARM-SLAM [1] performs dense localization and mapping in the configuration space of the robot arm, implicitly tracking the pose of a single camera and creating a volumetric model. However, using a single camera only allows to cover a small field of view and can only constrain up to six degrees of freedom. Therefore, we propose the Multi-Cam ARM-SLAM (MC-ARM-SLAM) framework, which fuses information of multiple depth cameras mounted on the robot into a joint model. The use of multiple cameras allows to also estimate the motion of the robot base that is modeled as a virtual kinematic chain additionally to the motion of the arm. Furthermore, we use a robust bivariate error formulation, which helps to boost the accuracy of the method and mitigates the influence of outliers. The proposed method is extensively evaluated in simulation and on a real rescue robot. It is shown that the method is able to correct errors in the motor encoders and the kinematic model and outperforms the base version of ARM-SLAM.
{"title":"Multi-Cam ARM-SLAM: Robust Multi-Modal State Estimation Using Truncated Signed Distance Functions for Mobile Rescue Robots","authors":"Jasper Süß, Marius Schnaubelt, O. Stryk","doi":"10.1109/SSRR56537.2022.10018752","DOIUrl":"https://doi.org/10.1109/SSRR56537.2022.10018752","url":null,"abstract":"To be able to perform manipulation tasks within an unknown environment, rescue robots require a detailed model of their surroundings, which is often generated using registered depth images as an input. However, erroneous camera registrations due to noisy motor encoder readings, a faulty kinematic model or other error sources can drastically reduce the model quality. Most existing approaches register the pose of a free-floating single camera without considering constraints by the kinematic robot configuration. In contrast, ARM-SLAM [1] performs dense localization and mapping in the configuration space of the robot arm, implicitly tracking the pose of a single camera and creating a volumetric model. However, using a single camera only allows to cover a small field of view and can only constrain up to six degrees of freedom. Therefore, we propose the Multi-Cam ARM-SLAM (MC-ARM-SLAM) framework, which fuses information of multiple depth cameras mounted on the robot into a joint model. The use of multiple cameras allows to also estimate the motion of the robot base that is modeled as a virtual kinematic chain additionally to the motion of the arm. Furthermore, we use a robust bivariate error formulation, which helps to boost the accuracy of the method and mitigates the influence of outliers. The proposed method is extensively evaluated in simulation and on a real rescue robot. It is shown that the method is able to correct errors in the motor encoders and the kinematic model and outperforms the base version of ARM-SLAM.","PeriodicalId":272862,"journal":{"name":"2022 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115829955","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 : 2022-11-08DOI: 10.1109/SSRR56537.2022.10018586
F. Arzberger, J. Zevering, A. Bredenbeck, D. Borrmann, A. Nüchter
Situational awareness in search and rescue missions is key to successful operations, e.g., in collapsed buildings, underground mine shafts, construction sites, and underwater caves. LiDAR sensors in robotics play an increasingly important role in this context, as do robust and application-specific algorithms for simultaneous localization and mapping (SLAM). In many of these scenarios mapping requires the utilization of a vertically descended scanning system. This work presents a mobile system designed to solve this task, including a SLAM approach for descended LiDAR sensors with small field of view (FoV), which are in uncontrolled rotation. The SLAM approach is based on planar polygon matching and is not limited to the presented scenario. We test the system by lowering it from a crane inside a tall building at a fire-fighter school, applying our offline SLAM approach, and comparing the resulting point clouds of the environment with ground truth maps acquired by a terrestrial laser scanner (TLS). We also compare the SLAM approach to a state-of-the-art approach with respect to runtime and accuracy of the resulting maps. Our solution achieves comparable mapping accuracy at 0.2% of the runtime.
{"title":"Mobile 3D scanning and mapping for freely rotating and vertically descended LiDAR","authors":"F. Arzberger, J. Zevering, A. Bredenbeck, D. Borrmann, A. Nüchter","doi":"10.1109/SSRR56537.2022.10018586","DOIUrl":"https://doi.org/10.1109/SSRR56537.2022.10018586","url":null,"abstract":"Situational awareness in search and rescue missions is key to successful operations, e.g., in collapsed buildings, underground mine shafts, construction sites, and underwater caves. LiDAR sensors in robotics play an increasingly important role in this context, as do robust and application-specific algorithms for simultaneous localization and mapping (SLAM). In many of these scenarios mapping requires the utilization of a vertically descended scanning system. This work presents a mobile system designed to solve this task, including a SLAM approach for descended LiDAR sensors with small field of view (FoV), which are in uncontrolled rotation. The SLAM approach is based on planar polygon matching and is not limited to the presented scenario. We test the system by lowering it from a crane inside a tall building at a fire-fighter school, applying our offline SLAM approach, and comparing the resulting point clouds of the environment with ground truth maps acquired by a terrestrial laser scanner (TLS). We also compare the SLAM approach to a state-of-the-art approach with respect to runtime and accuracy of the resulting maps. Our solution achieves comparable mapping accuracy at 0.2% of the runtime.","PeriodicalId":272862,"journal":{"name":"2022 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131707928","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 : 2022-11-08DOI: 10.1109/SSRR56537.2022.10018635
B. Okken, S. Stramigioli, W. Roozing
We present the design and development of a non-linear series-elastic element based on repelling magnets. Progressive stiffness offers the transparency advantages of a low-stiffness elastic actuator at low load levels, and the high torque tracking bandwidth of a high-stiffness actuator at high loads. The design space of this magnet-based concept is thoroughly analysed, for both box- and arc-segment magnets. A proof-of-concept prototype is presented which is experimentally validated. A gain-scheduled torque controller is used to exploit its non-linear dynamics. Simulation and experimental results demonstrate the viability of the concept.
{"title":"Progressive Series-Elastic Actuation with Magnet-based Non-linear Elastic Elements","authors":"B. Okken, S. Stramigioli, W. Roozing","doi":"10.1109/SSRR56537.2022.10018635","DOIUrl":"https://doi.org/10.1109/SSRR56537.2022.10018635","url":null,"abstract":"We present the design and development of a non-linear series-elastic element based on repelling magnets. Progressive stiffness offers the transparency advantages of a low-stiffness elastic actuator at low load levels, and the high torque tracking bandwidth of a high-stiffness actuator at high loads. The design space of this magnet-based concept is thoroughly analysed, for both box- and arc-segment magnets. A proof-of-concept prototype is presented which is experimentally validated. A gain-scheduled torque controller is used to exploit its non-linear dynamics. Simulation and experimental results demonstrate the viability of the concept.","PeriodicalId":272862,"journal":{"name":"2022 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"86 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131724480","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 : 2022-10-26DOI: 10.1109/SSRR56537.2022.10018684
Manthan Patel, Gabriel Waibel, Shehryar Khattak, M. Hutter
Detecting objects of interest, such as human survivors, safety equipment, and structure access points, is critical to any search-and-rescue operation. Robots deployed for such time-sensitive efforts rely on their onboard sensors to perform their designated tasks. However, as disaster response operations are predominantly conducted under perceptually degraded conditions, commonly utilized sensors such as visual cameras and LiDARs suffer in terms of performance degradation. In response, this work presents a method that utilizes the complementary nature of vision and depth sensors to leverage multi-modal information to aid object detection at longer distances. In particular, depth and intensity values from sparse LiDAR returns are used to generate proposals for objects present in the environment. These proposals are then utilized by a Pan-Tilt-Zoom (PTZ) camera system to perform a directed search by adjusting its pose and zoom level for performing object detection and classification in difficult environments. The proposed work has been thoroughly verified using an ANYmal quadruped robot in underground settings and on datasets collected during the DARPA Subterranean Challenge finals.
{"title":"LiDAR-guided object search and detection in Subterranean Environments","authors":"Manthan Patel, Gabriel Waibel, Shehryar Khattak, M. Hutter","doi":"10.1109/SSRR56537.2022.10018684","DOIUrl":"https://doi.org/10.1109/SSRR56537.2022.10018684","url":null,"abstract":"Detecting objects of interest, such as human survivors, safety equipment, and structure access points, is critical to any search-and-rescue operation. Robots deployed for such time-sensitive efforts rely on their onboard sensors to perform their designated tasks. However, as disaster response operations are predominantly conducted under perceptually degraded conditions, commonly utilized sensors such as visual cameras and LiDARs suffer in terms of performance degradation. In response, this work presents a method that utilizes the complementary nature of vision and depth sensors to leverage multi-modal information to aid object detection at longer distances. In particular, depth and intensity values from sparse LiDAR returns are used to generate proposals for objects present in the environment. These proposals are then utilized by a Pan-Tilt-Zoom (PTZ) camera system to perform a directed search by adjusting its pose and zoom level for performing object detection and classification in difficult environments. The proposed work has been thoroughly verified using an ANYmal quadruped robot in underground settings and on datasets collected during the DARPA Subterranean Challenge finals.","PeriodicalId":272862,"journal":{"name":"2022 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128719586","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 : 2022-10-13DOI: 10.1109/SSRR56537.2022.10018764
J. Bolarinwa, Alex Smith, Adnan Aijaz, Aleksandar Stanoev, M. Sooriyabandara, M. Giuliani
Communication delays and packet losses are commonly investigated issues in the area of robotic teleoperation. This paper investigates application of a novel low-power wireless control technology (GALLOP) in a haptic teleoperation scenario developed to aid in nuclear decommissioning. The new wireless control protocol, which is based on an off-the-shelf Bluetooth chipset, is compared against standard implementations of wired and wireless TCP/IP data transport. Results, through objective and subjective data, show that GALLOP can be a reasonable substitute for a wired TCP/IP connection, and performs better than a standard wireless TCP/IP method based on Wi-Fi connectivity.
{"title":"Haptic Teleoperation goes Wireless: Evaluation and Benchmarking of a High-Performance Low-Power Wireless Control Technology","authors":"J. Bolarinwa, Alex Smith, Adnan Aijaz, Aleksandar Stanoev, M. Sooriyabandara, M. Giuliani","doi":"10.1109/SSRR56537.2022.10018764","DOIUrl":"https://doi.org/10.1109/SSRR56537.2022.10018764","url":null,"abstract":"Communication delays and packet losses are commonly investigated issues in the area of robotic teleoperation. This paper investigates application of a novel low-power wireless control technology (GALLOP) in a haptic teleoperation scenario developed to aid in nuclear decommissioning. The new wireless control protocol, which is based on an off-the-shelf Bluetooth chipset, is compared against standard implementations of wired and wireless TCP/IP data transport. Results, through objective and subjective data, show that GALLOP can be a reasonable substitute for a wired TCP/IP connection, and performs better than a standard wireless TCP/IP method based on Wi-Fi connectivity.","PeriodicalId":272862,"journal":{"name":"2022 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129097186","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}
This paper proposes a taxonomy of semantic information in robot-assisted disaster response. Robots are increasingly being used in hazardous environment industries and emergency response teams to perform various tasks. Operational decision-making in such applications requires a complex semantic understanding of environments that are remote from the human operator. Low-level sensory data from the robot is transformed into perception and informative cognition. Currently, such cognition is predominantly performed by a human expert, who monitors remote sensor data such as robot video feeds. This engenders a need for AI-generated semantic understanding capabilities on the robot itself. Current work on semantics and AI lies towards the relatively academic end of the research spectrum, hence relatively removed from the practical realities of first responder teams. We aim for this paper to be a step towards bridging this divide. We first review common robot tasks in disaster response and the types of information such robots must collect. We then organize the types of semantic features and understanding that may be useful in disaster operations into a taxonomy of semantic information. We also briefly review the current state-of-the-art semantic understanding techniques. We highlight potential synergies, but we also identify gaps that need to be bridged to apply these ideas. We aim to stimulate the research that is needed to adapt, robustify, and implement state-of-the-art AI semantics methods in the challenging conditions of disasters and first responder scenarios.
{"title":"A Taxonomy of Semantic Information in Robot-Assisted Disaster Response","authors":"Tianshu Ruan, Hao Wang, Rustam Stolkin, Manolis Chiou","doi":"10.1109/SSRR56537.2022.10018727","DOIUrl":"https://doi.org/10.1109/SSRR56537.2022.10018727","url":null,"abstract":"This paper proposes a taxonomy of semantic information in robot-assisted disaster response. Robots are increasingly being used in hazardous environment industries and emergency response teams to perform various tasks. Operational decision-making in such applications requires a complex semantic understanding of environments that are remote from the human operator. Low-level sensory data from the robot is transformed into perception and informative cognition. Currently, such cognition is predominantly performed by a human expert, who monitors remote sensor data such as robot video feeds. This engenders a need for AI-generated semantic understanding capabilities on the robot itself. Current work on semantics and AI lies towards the relatively academic end of the research spectrum, hence relatively removed from the practical realities of first responder teams. We aim for this paper to be a step towards bridging this divide. We first review common robot tasks in disaster response and the types of information such robots must collect. We then organize the types of semantic features and understanding that may be useful in disaster operations into a taxonomy of semantic information. We also briefly review the current state-of-the-art semantic understanding techniques. We highlight potential synergies, but we also identify gaps that need to be bridged to apply these ideas. We aim to stimulate the research that is needed to adapt, robustify, and implement state-of-the-art AI semantics methods in the challenging conditions of disasters and first responder scenarios.","PeriodicalId":272862,"journal":{"name":"2022 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131453183","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 : 2022-09-28DOI: 10.1109/SSRR56537.2022.10018692
Jacob Hartzer, S. Saripalli
Visual-inertial navigation systems are powerful in their ability to accurately estimate localization of mobile systems within complex environments that preclude the use of global navigation satellite systems. However, these navigation systems are reliant on accurate and up-to-date temporospatial calibrations of the sensors being used. As such, online estimators for these parameters are useful in resilient systems. This paper presents an extension to existing Kalman Filter based frameworks for estimating and calibrating the extrinsic parameters of multi-camera IMU systems. In addition to extending the filter framework to include multiple camera sensors, the measurement model was reformulated to make use of measurement data that is typically made available in fiducial detection software. A secondary filter layer was used to estimate time translation parameters without closed-loop feedback of sensor data. Experimental calibration results, including the use of cameras with non-overlapping fields of view, were used to validate the stability and accuracy of the filter formulation when compared to offline methods. Finally the generalized filter code has been open-sourced and is available online.
{"title":"Online Multi Camera-IMU Calibration","authors":"Jacob Hartzer, S. Saripalli","doi":"10.1109/SSRR56537.2022.10018692","DOIUrl":"https://doi.org/10.1109/SSRR56537.2022.10018692","url":null,"abstract":"Visual-inertial navigation systems are powerful in their ability to accurately estimate localization of mobile systems within complex environments that preclude the use of global navigation satellite systems. However, these navigation systems are reliant on accurate and up-to-date temporospatial calibrations of the sensors being used. As such, online estimators for these parameters are useful in resilient systems. This paper presents an extension to existing Kalman Filter based frameworks for estimating and calibrating the extrinsic parameters of multi-camera IMU systems. In addition to extending the filter framework to include multiple camera sensors, the measurement model was reformulated to make use of measurement data that is typically made available in fiducial detection software. A secondary filter layer was used to estimate time translation parameters without closed-loop feedback of sensor data. Experimental calibration results, including the use of cameras with non-overlapping fields of view, were used to validate the stability and accuracy of the filter formulation when compared to offline methods. Finally the generalized filter code has been open-sourced and is available online.","PeriodicalId":272862,"journal":{"name":"2022 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121858272","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：