| 1. |
- Arain, Muhammad Asif, 1983-
(författare)
-
Efficient Remote Gas Inspection with an Autonomous Mobile Robot
- 2020
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Human-caused greenhouse gas emissions are one of the major sources of global warming, which is threatening to reach a tipping point. Inspection systems that can provide direct information about critical factors causing global warming, such as systems for gas detection and location of gas sources, are urgently needed to analyze the fugitive emissions and take necessary actions.This thesis presents an autonomous robotic system capable of performing efficient exploration by selecting informative sampling positions for gas detection and gas distribution mapping – the Autonomous Remote Methane Explorer (ARMEx). In the design choice of ARMEx, a ground robot carries a spectroscopybased remote gas sensor, such as a Remote Methane Leak Detector (RMLD), that collects integral gas measurements along up to 30 m long optical-beams. The sensor is actuated to sample a large area inside an adjustable field of view, and with the mobility of the robot, adaptive sampling for high spatial resolution in the areas of interest is made possible to inspect large environments.In a typical gas sampling mission, the robot needs to localize itself and plan a traveling path to visit different locations in the area, which is a largely solved problem. However, the state-of-the-art prior to this thesis fell short of providing the capability to select informative sampling positions autonomously. This thesis introduces efficient measurement strategies to bring autonomy to mobile remote gas sensing. The strategies are based on sensor planning algorithms that minimize the number of measurements and distance traveled while optimizing the inspection criteria: full sensing coverage of the area for gas detection, and suitably overlapping sensing coverage of different viewpoints around areas of interest for gas distribution mapping.A prototype implementation of ARMEx was deployed in a large, real-world environment where inspection missions performed by the autonomous system were compared with runs teleoperated by human experts. In six experimental trials, the autonomous system created better gas maps, located more gas sources correctly, and provided better sensing coverage with fewer sensing positions than human experts.
|
|
| 2. |
- Schindler, Maike, et al.
(författare)
-
Identifying student strategies through eye tracking and unsupervised learning : The case of quantity recognition
- 2020
-
Ingår i: Interim Proceedings of the 44th Conference of the International Group for the Psychology of Mathematics Education. Khon Kaen, Thailand: PME. ; , s. 518-527
-
Konferensbidrag (refereegranskat)abstract
- Identifying student strategies is an important endeavor in mathematics education research. Eye tracking (ET) has proven to be valuable for this purpose: E.g., analysis of ET videos allows for identification of student strategies, particularly in quantity recognition activities. Yet, “manual”, qualitative analysis of student strategies from ET videos is laborious—which calls for more efficient methods of analysis. Our methodological paper investigates opportunities and challenges of using unsupervised machine learning (USL) in combination with ET data: Based on empirical ET data of N = 164 students and heat maps of their gaze distributions on the task, we used a clustering algorithm to identify student strategies from ET data and investigate whether the clusters are consistent regarding student strategies.
|
|
| 3. |
- Winkler, Nicolas P., 1991-, et al.
(författare)
-
High-quality meets low-cost : Approaches for hybrid-mobility sensor networks
- 2020
-
Ingår i: MATERIALS TODAY-PROCEEDINGS. - : Elsevier. ; , s. 250-253
-
Konferensbidrag (refereegranskat)abstract
- Air pollution within industrial scenarios is a major risk for workers, which is why detailed knowledge about the dispersion of dusts and gases is necessary. This paper introduces a system combining stationary low-cost and high-quality sensors, carried by ground robots and unmanned aerial vehicles. Based on these dense sampling capabilities, detailed distribution maps of dusts and gases will be created. This system enables various research opportunities, especially on the fields of distribution mapping and sensor planning. Standard approaches for distribution mapping can be enhanced with knowledge about the environment's characteristics, while the effectiveness of new approaches, utilizing neural networks, can be further investigated. The influence of different sensor network setups on the predictive quality of distribution algorithms will be researched and metrics for the quantification of a sensor network's quality will be investigated.
|
|
