Autonomous agricultural machines improve farming efficiency but still require human oversight for safety and performance, especially when field conditions demand operator intervention. Human-machine interfaces (HMIs) must support situation awareness (SA), particularly comprehension (Level 2 SA) and projection (Level 3 SA) of system status. Unimodal warnings—visual, auditory, or tactile—typically relay critical information, though their effectiveness varies by modality, user interpretation, and environment. This study examines how unimodal warnings influence SA in remote supervision of an autonomous agricultural sprayer. Two experiments evaluated visual, auditory, and tactile cues on response accuracy, urgency perception, and response time under field-like conditions. We also collected subjective ratings of user preference. Results showed visual warnings were most effective, with the highest comprehension accuracy, urgency projection, shortest response times, and strongest user preference (84%). Auditory cues had moderate performance, and tactile cues were least effective. These findings support existing SA theory, emphasizing that warning modality should match task demands. This research informs the design of user-centred HMIs in agricultural automation and demonstrates how aligning modality with SA levels can enhance operator performance, particularly in time-critical supervision scenarios.

A closed-loop water retting system is developed and fabricated in this study to process discarded canola stalks into fibers. The effects of retting parameters are studied using Latin Hypercube statistical design, modeled using Altair HyperStudyTM, and subjected to a multi-objective optimization. The retting time is reduced from a range of approximate to 168-1080 h for the conventional water retting system to 60 h for the developed closed-loop system. The fiber yield increased from approximate to 0.84% to 11.26%, the crystallinity index (CI) increased from approximate to 55.6% to 67.3%, and linear density decreased from approximate to 73.6 to 51.7 Tex with the increase in retting time, temperature, and water flow rate. However, the overall trends are complicated due to the heterogeneity in the structures and properties of the starting plant materials. The optimal retting parameters are 60 h-time, 60 degrees C-temperature, and 150 mL min(-1)-water flow rate. Under these conditions, canola fibers exhibited approximate to 11.26% yield, approximate to 67.32% crystallinity index, and approximate to 56.24 Tex linear density. Canola fibers exhibited a multifiber structure surface (mean fiber diameter approximate to 957.8 mu m) and non-cellulosic component dominant cross-section due to their higher pectic polysaccharides content (approximate to 32.5-41.8%). The canola fiber production accounts for approximate to 169.42 kg CO(2)e/tonne, which is significantly lower than the emissions associated with equivalent flax fiber production (approximate to 403.15 kg).

Surface treatment of cattail, a lignocellulosic renewable fiber, was investigated to determine the conditions that would reduce moisture absorption while maximizing the properties of cattail fiber-reinforced unsaturated polyester composites. Surface modification of cattail fiber was studied by treating them with 2.5, 5, and 10% of 1,6-diisocyanatohexane (DIH) and 2-hydroxyethyl acrylate (HEA) for three different immersion times (10, 20, and 30 min). DIH-HEA treated fibers were preformed into a non-woven mat and impregnated with unsaturated polyester resin to manufacture composite. The existence of covalent bonds on the treated fibers via N-H and C-N groups was confirmed by FTIR spectroscopy. The 10% DIH-HEA resulted in the best results; while the mean diameter of the treated fiber decreased by similar to 37%, the modulus and the strength of it increased by similar to 267 and similar to 151%, respectively. Equilibrium moisture regain of the treated fibers and their composites decreased by similar to 43% and similar to 40%, respectively. The tensile modulus of the composites increased by similar to 171%. Enhancement in tensile strength is observed but could not be quantified due to the difference in V-f and scatter in the data. SEM examination confirmed the enhancement in fiber-matrix bonding due to surface treatment.

Agriculture encompasses a variety of activities that carry with them a variety of different risks. The unsafe use of vehicles, machinery, and tools as well as animal husbandry, working at heights, and exposure to chemical, biological, and weather events may result in the deaths of agricultural workers. Inexperienced operators and/or their inappropriate conduct may lead to avoidable fatalities. Forensic pathologists operating with the support of agricultural engineers or other professionals must evaluate the death scene, the case background and circumstances, the autopsy findings, and the toxicological data to establish the factors and dynamics responsible for such accidents and deaths.The aim of this review is to focus on the diagnostic approach required, by means of an interdisciplinary approach, to identify the cause of some typical agricultural fatalities, to confirm that death was accidental, and to help exclude the possibility of homicide or suicide.

This study focuses on enhancing the ergonomic design of tractor cabs using advanced anthropometric modeling tools and a Human-Centered Design (HCD) approach. As the agricultural industry increasingly shifts towards autonomous machinery, operators' roles are evolving from active engagement to more passive oversight. This transition necessitates rethinking cab designs to prioritize operator comfort, safety, and usability. This study investigates the Active Range of Motion (AROM) for various joints (the buttocks, back, shoulders, neck, left leg, right leg, left arm, and right arm) and categorizes these into three zones: comfortable, acceptable, and unsatisfactory. Using RAMSIS software, digital twins of operators were analyzed to assess joint movement and visual field classifications. The findings provide actionable insights for positioning controls and displays within optimal comfort zones and visual cones, ensuring ergonomic efficiency. This study highlights gender-based differences in AROM and validates the symmetrical nature of joint movements across body sides. By employing these findings, designers can develop tractor cabs that meet functional demands and enhance user well-being, safety, and productivity.

The renewable characteristics of natural fibers have prompted consumers to switch from synthetic and petroleum-based resources. The dimension and geometry of the cell wall and lumen determine the microstructural parameters of natural biomass fibers (BFs) and waste biomass fibers (WBFs). The variation in these microstructural parameters, together with the divergences in the degumming methods and processing conditions, causes large variations in their physical and mechanical properties, unlike synthetic fibers. The utilization of WBFs points to a feasible approach to addressing waste disposal problems, while simultaneously creating value-added products with reduced water, energy, and carbon footprints. WBFs exhibit higher sustainability scores than biomass fibers BFs, suggesting that WBF is a more environmentally friendly material choice over BF. The efficacy of extracting high-quality fibers depends on the fiber source and degumming methods being correctly synchronized. High-quality fibers can be extracted from plant stalk through water, chemical, or enzyme retting; however, they can generate a secondary waste water stream, whereas mechanical extraction of fiber is feasible for scalable production. Mechanical technologies for extraction of WBFs are more environmentally friendly, but the technologies need to be further developed to improve the resultant fiber purity and quality. Surface modification is required for lignocellulosic fibers to tailor their flexibility, wettability, and fiber surface roughness for industrial applications. This review aimed to provide an insight on the background of BFs WBFs, together with their environmental impact, macro and microstructural features, structural variations, and current development of fiber processing technologies.

Biosystems engineering students at the University of Manitoba participated in a voluntary workshop series as an extracurricular professional development opportunity. The five-workshop series was designed to engage students in reflection and self-reflection as a foundation for the development of e-portfolios to document their learning over time. Following the workshop series, focus group interviews were held with voluntary participants to explore their perceptions and experiences with self-reflection relative to e-portfolios. Themes that emerged from the focus group data related to i) the value of self-reflection as an activity, ii) the value of e-portfolios for career success, iii) observations of the biosystems engineering curriculum and iv) concerns about the status of the biosystems engineering discipline in the engineering community. The motivations to consider an e-portfolio were immediately focused on job-finding, and within that, on clarifying biosystems engineering both to themselves, to other students outside of biosystems engineering, and employers.

This paper emphasizes the essential role of a support person for faculty teaching and assessing the Canadian Engineering Accreditation Board (CEAB) graduate attributes as part of an ongoing accreditation cycle. It details the continuous program improvement process adopted by the Department of Biosystems Engineering at the University of Manitoba, and the role of engineering stakeholders. It recounts a study that details the supportive efforts of a Research Associate who helped to validate and implement rubrics with individual professors as outcomes-based tools for teaching and assessing the 12 CEAB graduate attributes, which resulted in the creation of 14 rubrics for 12 courses. Findings included new pedagogical understandings, the appreciation of individual support from the Research Associate, and the continued use of rubrics; the work led most professors to think deeply and in new ways about teaching and assessment. There was evidence that six professors engaged in ‘reverse design’, developing rubrics with targeted learning outcomes and course materials in mind. The work led to critical improvement in teaching practices and evidence of continual program improvement. Despite overall engagement and success, some professors continued to struggle with the concept and use of rubrics. In sum, this experience emphasizes the benefit of a dedicated person to support professors to implement rubrics, and in creating and sustaining an outcomes-based assessment culture in the department.

An exploratory case study was designed to determine the relative importance of the Canadian Engineering Accreditation Board (CEAB) graduate attributes as perceived by University of Manitoba engineering stakeholders. Findings were used to examine the content validity of the Biosystems Engineering program. The overarching objective was to explore how graduate attribute emphasis in engineering programs reflect graduate attribute importance reported by key stakeholders. Problem Analysis, Investigation, Design, Communication Skills, Impact of Engineering on Society & the Environment, and Use of Engineering Tools had similar expected (mean relative importance) and observed (content and assessment program coverage) data percentages. The gap was wider for other graduate attributes, with the most surprising being Knowledge Base. Overall, the pattern of results suggests that various professional attributes (e.g., Professionalism, Ethics & Equity, and Lifelong Learning) should be more prominent in content and assessments within an engineering program. Recommendations to improve methods to assess content validity in engineering programs are discussed.

The scientific literature provides a description of various models depicting autonomous agricultural machines working to complete typical field operations. Many of the models involve some form of automation interface that is used by the machine owner to supervise the operation of the machine from a remote location. The objective of this study was to interview experts in the design of autonomous agricultural machines (university researchers, entrepreneurs, and leaders in the agricultural machinery sector) to ascertain their opinions about future autonomous agricultural machines, particularly related to how such machines will be supervised by the machine’s owner. Of the four remote supervision concepts described by participants (within the field, close to the field, from the farm office, and outside the farm site), the close-to-the-field remote supervision concept was determined to be the most viable concept. Designers were divided on the idea of providing real-time live video on the automation interface, however, most of them believed that having live video would reassure the farmer that everything was going well. Desktop computer, tablet and phone were the main devices recommended as tools for remote supervision (i.e., the hardware on which to display the automation interface), with tablet perhaps being the preferred alternative.

HIGHLIGHTS:Humans who supervise autonomous agricultural machines require some type of warning to perceive abnormal conditions in the machine or its environment. Visual and tactile warnings were the most suitable warning methods for in-field and close-to-field remote supervision. This study will help improve the performance of remote supervisors and minimize unexpected incidents or liabilities during operation of autonomous machines.ABSTRACT:As agricultural machinery moves toward full autonomy, human supervisors will need to monitor the autonomous machines during operation and minimize system failures or malfunctions. However, to intervene in an emergency, the supervisor must first recognize the emergency in a timely manner. Existing warning devices rely on the human visual, auditory, and tactile senses. However, these warning methods vary in their ability to attract attention. Hence, it is important to determine which warning method is best suited to draw the attention of a remote supervisor of an autonomous machine in an emergency. To achieve this objective, participants were recruited and asked to interact with a simulation of an autonomous sprayer. Seven warning methods (presented alone or in combinations of visual, auditory, and tactile sensory cues) and four remote supervision scenarios (in-field, close-to-field, farm office, outside the farmland) were considered in this study. The findings revealed that a combination of tactile and visual methods was most suitable for in-field and close-to-field remote supervision, in comparison to the other warning methods. However, there was insufficient evidence to recommend the best warning methods for supervisors at the farm office or outside the farmland. This study will help improve the performance of remote supervisors and minimize unexpected incidents during field operations with autonomous agricultural machines.

Biomass fibers are being widely investigated for industrial applications as an alternative to synthetic fibers using a standard humidity condition. In this study, the mechanical properties of two waste biomass fibers – canola and cattail – have been investigated when subjected to different environmental conditions, fiber length, and type of estimators used during analysis. The effect of different environmental conditions and structural variations were investigated by measuring the tensile properties after exposing them to eight different relative humidity conditions using a fixed fiber length of 25 mm. Further investigation was conducted using fiber lengths of 25, 35 and 45 mm using the most conservative relative humidity condition. The data were analyzed by a Weibull distribution model using four different estimators. The results revealed that Weibull strength ( σavg) and modulus (Eavg) closely followed experimental values for cattail and canola fibers. The different relative humidity conditions and fiber lengths resulted in different Weibull parameters with 11% relative humidity and the mean rank estimator predicted the most conservative tensile strength for both waste biomass fibers. The experimental and characteristic Weibull strength decreased when fiber gauge length increased from 25 to 45 mm. The tensile strength and modulus of both waste biomass fibers at 50% reliability lie within the range of average experimental values. However, these values are reduced to 155 MPa (strength) and 20 GPa (modulus) for cattail fiber at 90% reliability. The survival probability of the tensile strength and modulus were found to be the highest at 75% and 100% relative humidity for cattail and canola fibers, respectively.

Highlights Automatic classification of harvester sounds. Final classification obtained using three convolutional neural networks. The results of the networks were combined via stacking and voting to achieve 100% accuracy. Abstract. The use of deep learning in agricultural tasks has recently become popular. Deep learning networks have been used for analyzing images of crops, identifying paddy areas, distinguishing sick plants from healthy ones, to name a few applications. Besides visual systems, sound analysis of agricultural machinery is a time-sensitive task that can also be incorporated in decision making and can be done with the help of deep learning models. We propose a method to generate spectrogram images from the sound of a harvester and classify them into three working modes in real-time. We used three convolutional neural networks and use the outputs of these networks as inputs to a stacking ensemble method to improve the accuracy of the system. To achieve 100% classification accuracy, a final decision is made by voting based on several consecutive classifications made by the stacking step. We were able to perform classifications in less than 1 s which was the standard to be considered as a safe time for the harvester. Keywords: Convolutional neural networks, Deep learning, Spectrograms, Stacking, Voting.

As the prominence of autonomous vehicles continues to rise within agriculture, remote surveillance of the equipment is likely to become a key aspect of operation. Transmission latency during the relay of video from vehicle to viewer is not well explored and is an important part of communications which should be assessed. A riding mower was equipped with a Raspberry Pi using GStreamer and an open-source latency measurement library to assemble a real-time streaming system to evaluate transmission latency in different environments using cellular and radio transmission. In most locations, measured latencies were under 200-300 ms. In areas where cellular connection quality was adequate, cellular latency and variance were reduced compared to that of radio transmission for higher qualities of video. In areas of poor cellular network coverage, cellular transmission latency increased while radio transmission latencies remained constant. Overall, latency tends to increase with video quality to a statistically significant degree. It is recommended that real-time video can be transmitted over short distances for edge-of-field surveillance of autonomous agricultural machines using existing cellular networks in areas where adequate cellular signal strength is available. If adequate cellular signal strength is not available in a specific field location, it is recommended that video should be transmitted using radio transmission.

Artificial intelligence, deep learning, big data, self-driving cars horizontal ellipsis , these are words that have become familiar to most people and have captured the imagination of the public and have brought hopes as well as fears. We have been told that artificial intelligence will be a major part of our lives, and almost all of us witness this when decisions made by algorithms show us commercial advertisements that specifically target our interests while using the web. In this paper, the conversation around artificial intelligence focuses on a particular application, agricultural machinery, but offers enough content so that the reader can have a very good idea on how to consider this technology for not only other agricultural applications such as sorting and grading produce, but also other areas in which this technology can be a part of a system that includes sensors, hardware and software that can make accurate decisions. Narrowing the application and also focusing on one specific artificial intelligence approach, that of deep learning, allow us to illustrate from start to end the steps that are usually considered and elaborate on recent developments on artificial intelligence.

Vacuum-assisted resin transfer molding (VARTM), used in manufacturing medium to large-sized composites for transportation industries, requires non-woven mats. While non-woven glass mats used in these applications are optimized for resin impregnation and properties, such optimized mats for natural fibers are not available. In the current research, cattail fibers were extracted from plants (18–30% yield) using alkali retting and non-woven cattail fiber mat was manufactured. The extracted fibers exhibited a normal distribution in diameter ( d avg. = 32.1 µm); the modulus and strength varied inversely with diameter, and their average values were 19.1 GPa and 172.3 MPa, respectively. The cattail fiber composites were manufactured using non-woven mats, Stypol polyester resin, VARTM pressure (101 kPa) and compression molding pressures (260 and 560 kPa) and tested. Out-of-plane permeability changed with the fiber volume fraction ( V f ) of the mats, which was influenced by areal density, thickness, and fiber packing in the mat. The cattail fibers reinforced the Stypol resin significantly. The modulus and the strength increased with consolidation pressures due to the increase in V f , with maximum values of 7.4 GPa and 48 MPa, respectively, demonstrating the utility of cattail fibers from waste biomass as reinforcements.

Several authors have previously promoted the transformation of the application-based agricultural engineering discipline into a biology-based biological engineering discipline. A systematic analysis of titles for courses being taught by ASABE-umbrella programs across North America was undertaken to identify curricular differences between biology-based and application-based “bio” engineering disciplines. Based on 44 ASABE-umbrella programs analyzed, the four most commonly used program names were biological engineering (25%), biosystems engineering (20%), biological systems engineering (15.9%) and agricultural engineering (13.6%). Definitions of these four program names were reviewed; biosystems, biological systems and agricultural engineering are typically defined such that they are best described as application-based “bio” engineering disciplines while biological engineering is best described as a biology-based engineering discipline. Based on statistical analysis of the frequency of words in course titles, there was a significant increase in the usage of the word “food” and a lack of the word “project” in the course titles within biological engineering programs. Over half of the unique options were found in biological engineering programs suggesting that they do offer unique course content compared with biosystems, biological systems and agricultural engineering degree programs, however, it is noteworthy that four options appear across all four degrees. It is concluded that there are curricular differences between biology-based and application-based “bio” engineering disciplines, however, the curricular differences are not as substantive as one might conclude from the philosophical discussions in the literature. Alternatively, it may simply not be possible to detect curricular differences solely from an analysis of the course titles

As agricultural machinery moves into the digital era, significant developments in available technology will likely make autonomous farm vehicles more feasible, affordable, and desirable. One of the challenges of effective autonomous vehicle control specific to agriculture is the ability of the vehicle to interpret and adapt to constantly changing conditions. Auditory information is a primary indicator of changing conditions to an in-cab operator, particularly in situations such as detecting mechanical overload in a combine. This paper explores the potential for auditory information to be used in autonomous vehicle control. The sound was recorded at a sampling rate of 48 kHz near the straw chopper of a combine for three different operating modes during the same harvest day. Samples from each clip were segmented and analyzed to extract 31 audio features. Six different feature selection methods ranked the importance of each of the 31 features to identify the features that lead to accurate classification with a minimal number of calculations. These six rankings were assessed by Fagin’s algorithm to yield two features (both mel-frequency cepstral coefficients). Twenty-five distinct machine learning classification methods were evaluated using these two features. Three of these classification methods reached 100% accuracy, and 9 classifiers exceeded an individual success rate of more than 99% using those same features. These feature extraction and classification steps took less than 1 s, assuring that such a classification system could be implemented in real-time.

In various automated machines currently used in agriculture and field applications, the operator still retains responsibility for numerous other tasks the machines perform. Even with completely autonomous machines of the future, ergonomics will continue to play an important role for the overall system performance. This chapter on human-machine interactions, therefore, covers four distinct topics around ergonomics and how humans interact with machines. In the first section, readers can expect to gain an understanding of human-machine interaction associated with agricultural machines. This discussion will be followed by some description of the tools for assessing human-machine interaction. The third section will discuss the progression of technologies that have been used to support the operator of an agricultural machine up to and including fully autonomous agricultural machines. In the final section, future challenges associated with remote supervision of autonomous agricultural machines will be discussed.

There has been substantial growth in the formal focus on the pedagogy of engineering in the last two decades. Formalized pathways in Engineering Education (Eng.Ed), including Master’s and Ph.D. degree programs and university departments, have been established in several prestigious universities globally, with many founded in the U.S.. Interest in Eng.Ed in Canada has also grown, but up until very recently there has only been one formal pathway for graduate research in this field. In Fall 2020, the Department of Biosystems Engineering at the University of Manitoba welcomed the first three doctoral students into the Graduate Specialization in Eng.Ed (GSEE). In this paper we discuss the motivations for, and objectives and benefits of the GSEE, and describe its development. We share challenges encountered, and opportunities envisioned, and theintentions and motivations of the three graduate students who chose this pathway. We reflect on the importance of Eng.Ed programs for the advancement of engineering education research and the development of the discipline in Canada. Descriptions of our efforts and challenges areintended to help the development of additional Eng.Ed specializations or graduate programs in Canada.