University of Illinois Urbana-Champaign

Exploring the current methods used to improve the safety of autonomous agricultural machines and evaluating the effectiveness and applicability of a more quantitative risk assessment method

Aby, Guy Roger

Content Files
ABY-DISSERTATION-2024.pdf

Permalink

https://hdl.handle.net/2142/125590

Description

Title
Exploring the current methods used to improve the safety of autonomous agricultural machines and evaluating the effectiveness and applicability of a more quantitative risk assessment method
Author(s)
Aby, Guy Roger
Issue Date
2024-07-12
Director of Research (if dissertation) or Advisor (if thesis)
Issa, Salah F.
Doctoral Committee Chair(s)
Issa, Salah F.
Committee Member(s)
  • Bhattarai, Rabin
  • Mohaghegh, Zahra
  • Reid, John F.
Department of Study
Engineering Administration
Discipline
Agricultural & Biological Engr
Degree Granting Institution
University of Illinois at Urbana-Champaign
Degree Name
Ph.D.
Degree Level
Dissertation
Keyword(s)
Agriculture, Safety, Health, Autonomous, Machine, Risk Assessment, Hazard Analysis, Standard.
Abstract
The agricultural landscape is undergoing a profound transformation. The utilization of cutting-edge automation, artificial intelligence, and robotics in agriculture has given rise to a new generation of production agriculture practices. Autonomous agricultural machinery, equipped with a variety of sensors, processors, and actuators, has the capability to plow, sow, cultivate, and harvest crops with unprecedented precision and efficiency. As this shift becomes more prominent, ensuring the safety of these autonomous machineries remains crucial. As of now, one of the major obstacles to the full deployment of autonomous agricultural machines is safety. Autonomous agricultural machines must be designed to work safely, their safety record must be confirmed, and, more importantly, they must be viewed as safe by end users. Therefore, investigating and ensuring the safety of autonomous agricultural machines will be critical for their adoption. The overall objective of this research was to identify and investigate the limitations of the current methods used to ensure the safety of autonomous agricultural machines and a propose novel and more effective method. This overall research objective was divided into 4 sub-objectives. The first objective was to conduct a systematic literature review to identify and understand the different types of research that were conducted to ensure the safety of autonomous agriculture machines. The second objective focused on determining whether the International Organization for Standardization ISO 12100:2012 (ISO, 2012) and iso 18497 (ISO, 2018) can be applied to effectively ensure the safety of autonomous agricultural machines. The third objective identified the advantages and limitations of current risk assessment and hazard analysis methods when applied on autonomous agricultural machines. The fourth objective were to (1) conduct a survey to demonstrate the subjectivity of a conventional risk assessment and hazard analysis method commonly applied in the agricultural industry, (2) conduct a panel of expert meetings to demonstrate and discuss the subjectivity issues associated with the conventional risk assessment method, introduce a new more quantitative risk assessment and hazard analysis method and obtain feedback regarding its effectiveness and applicability the agricultural industry. Previous autonomous agricultural machines’ safety-related studies are analyzed and grouped into three categories: (1) environmental perception, (2) risk assessment as well as risk mitigation, and (3) human factors as well as ergonomics. The key findings are as follows: (1) The usage of single perception, multiple perception sensors, developing datasets of agricultural environments, different algorithms, and external solutions to improve sensor performance were all explored as options to improve autonomous agricultural machines’ safety. (2) Current risk assessment methods cannot be efficient when dealing with new technology, such as autonomous agricultural machines, due to a lack of pre-existing knowledge. Full compliance with the guidelines provided by the current International Organization for Standardization (ISO 18497) cannot ensure autonomous agricultural machines’ safety. A regulatory framework and being able to test the functionalities of autonomous agricultural machines within a reliable software environment are efficient ways to mitigate risks. (3) Knowing foreseeable human activity is critical to ensure safe human–robot interaction. The safety implications of an autonomous agricultural machine (TerraPreta) were investigated using the standards ISO 18497 (ISO, 2018) and ISO 12100:2012 (ISO, 2012), as well as to investigate the ergonomics associated with the use of the autonomous agricultural machine. The results showed that (50%) of the functionalities of the autonomous agricultural machine complied with the safety requirements and protective measures described within the standard ISO 18497 (ISO, 2018). The heavy reliance on past incident data of the risk assessment procedure described within the standard ISO 12100:2012 (ISO, 2012) makes it ineffective for new and revolutionary technologies such as autonomous agricultural machines where such data are not available. Lifting a bag to fill the robot hopper with seeds was found to be a moderately hazardous activity associated with human-robot interaction. Multiple tentative solutions were provided to avoid this moderately hazardous activity. The three main types of risk assessment and hazard analysis techniques applied to autonomous agricultural machines are (a) Informal group analysis (e.g., Brainstorming), (b) Hazard analysis and risk assessment (HARA), and (c) Failure Mode and Effects Analysis (FMEA). Replicability is perceived as the main advantage of FMEA, and HARA while cost-effectiveness is the main advantage of Informal group analysis. The need to have pre-existing data of the autonomous agricultural machine at hand to be able to perform risk assessment and subjectivity are the main limitations of FMEA, HARA, and Informal Group Analysis dealing with novel and revolutionary autonomous agricultural machines. Industry experts do not believe that the risk assessment and hazard analysis procedures now used are reliable and efficient enough to guarantee the safety of autonomous agricultural tractors. For the 24 incident scenarios presented to participants, the average standard deviation of the values provided by participants for the probability, severity, and completion are ± 1.25, ± 0.93, ± 1.13, respectively on a scale of 0 to 5. when the conventional risk assessment and hazard analysis method was used. When the new more quantitative risk assessment and hazard analysis method was applied to 3 different incident scenarios, the average standard deviation of the values provided by participants for the probability, completion, and severity are ± 0.0, ± 0.007, ± 0.0. These results indicate significant subjectivity in the traditional method, with high standard deviations in risk assessments. Conversely, the new more quantitative risk assessment method demonstrated higher repeatability and consistency. Moreover, the new more quantitative risk assessment method significantly improves handling complex scenarios involving multiple injury types, such as multiple fatalities, compared to conventional methods that lack clear procedures. However, for both the conventional and the new more quantitative risk assessment and hazard analysis methods, the lack of data for new and revolutionary technologies like autonomous agricultural machines poses a challenge to their effective application.
Graduation Semester
2024-08
Type of Resource
Thesis
Handle URL
https://hdl.handle.net/2142/125590
Copyright and License Information
Copyright 2024 Guy Aby

Owning Collections

Graduate Dissertations and Theses at Illinois PRIMARY
Graduate Theses and Dissertations at Illinois