Charting a New Course: The Promise of Adaptive 3D Learning Paths in Training

By: Robert Murdoch

As educators and trainers, we are always looking for ways to increase learner engagement and improve learning outcomes. As technology evolves and educational paradigms shift, instructors and learning centers are increasingly motivated to adopt adaptive methodologies and technologies to increase the efficiency and effectiveness of their instruction.

One adaptive methodology instructors are implementing more and more is adaptive 3D learning paths, a dynamic methodology that leverages 3D technology and adjusts to individual learner’s needs and progress in real time. These highly interactive and personalized training programs tout many benefits from data-driven insights for the learner to enhanced methods for continuous improvement for instructors.

Adopting this methodology is not without its challenges: budget, security, and infrastructure to name a few. But when in place, adaptive 3D learning paths can enhance the user experience for both the learner and the instructor.

An Adaptive 3D Learning Solution

In order to create highly immersive, diverse, and personalized learning experiences, we must incorporate high fidelity media, specifically 3D art. As Mike Schreiner discusses in his article Simulating Scenarios: Creating Lifelike 3D Environments for Interactive Training Modules leveraging 3D art and placing a learner in a hyperrealistic environment increases engagement and knowledge retention. The challenge comes when we attempt to cater this type of training to individuals with varying learning styles and capabilities.

Creating separate training products for each type of learner is not a cost-effective solution when dealing with a complex product involving dozens if not hundreds of unique 3D models. This approach would also rely on the learner self-identifying skills and preferences ahead of time, which can lead to the delivery of an incorrect product. The goal then is to design a learning program that creates learning paths dynamically as learners progress through the training. The program itself analyzes the metrics gathered from previous learner actions and performance to create the optimum path based on the learner profile.

When immersed in a 3D environment, learners are presented with a large amount of visual objects and data, from scenery and props to the scenario state. Each of these elements has a differing level of importance to the scenario and learning objectives. Some learners are adept at sorting out which items are important, while others need more guidance. Adaptive systems can present a learner with aids and guides based on their profile that will help them navigate the complex world of the training product without getting distracted or lost in the scene. This framework can also adjust the speed at which the learner progresses through the training and the mix of educational and entertainment objects in the learning environment to elicit optimum engagement without diminishing the learning objectives.

“The competent students can complete all the work in less time and can utilize it in some other useful activities while [the] weak learner is provided more time to get the desired knowledge.” (Alam et al., 2016, p. 264)

Together, 3D immersive environments and adaptive, dynamically created scenarios, user interfaces, and learning paths form a powerful tool for effective instructional design that not only benefits the learner, but the instructor and learning center as well.

xAPI, Data Collection, and Personalization

The implementation of adaptive 3D learning paths is a prime example of how learning centers and instructors are constantly looking for ways to improve the curriculum for their students. The goal is always to provide training efficiently, cost-effectively, and in a way that leads to the learner’s ultimate success in the field.

As training products have become more complex, many of our customers are jumping from the limited reporting provided by SCORM to the more robust reporting framework provided by xAPI. The xAPI framework allows us to capture virtually every learner action, from beginning a lesson to selecting a mode on a tool before using it. This allows for the necessary dynamic architecture that supports adaptive 3D learning paths.

Typically, instructors and learning centers use this data to improve a training program when a course or module comes up for revision and maintenance, but that only happens every few years at most. A product designed with adaptive 3D learning paths modifies itself for each specific learner as they move through the curriculum. The program analyzes the learner’s performance metrics and decides if they need to be presented with additional learning aids or if they are competent enough to be presented with associated advanced activities. It also allows instructors to see how many students in a particular class are struggling with a particular topic, which may point to a need for instructor intervention or curriculum revision.

Challenges to Adopting Adaptive 3D Learning Paths in Interactive Training

As good as this all sounds, every training framework comes with its challenges. As with any complex media involving 3D scenarios, learners may encounter technical issues within an immersive scenario that can disrupt the learning process. Learners must also have access to the tech-based training through the internet or access to a training center. Some learners not familiar with this type of training will experience a learning curve that can require additional support while others can struggle to maintain focus or self-regulate their attention.

Additionally, learning centers may find this framework to be resource intensive, requiring significant time, expertise, and technological infrastructure. Instructors may require specialized training and support to successfully implement this type of training and they must actively monitor learner progress and engagement because no matter how sophisticated a program may be, it is no substitute for the support and intervention of a qualified instructor.

The Benefits of Implementing Adaptive 3D Learning Paths in Interactive Training

Despite challenges, there are myriad reasons to adopt adaptive 3D learning paths into the curriculum.

For learners, the immediate feedback provided in this framework allows them to identify and correct errors in real time, fostering a sense of achievement. The framework allows them to learn “at any time and any place, taking into account the needs and characteristics of learners who are usually heterogeneous to achieve a specific skill within a certain time.” (Mustapha, et al., 2023, p. 265) The flexible pacing allows them to progress at their own speed while data-driven insights provide visibility into their strengths and weaknesses and empower them to make informed decisions about their learning journey.

Instructors benefit from enhanced teaching and learning processes through detailed analytics that inform instructional design, content development, and intervention strategies. The framework allows instructors to provide personalized support to individuals based on unique needs while the 3D immersion helps them to motivate their learners and stimulate their curiosity. Finally, adaptive learning systems offer flexibility in course delivery and differentiation of instruction to accommodate diverse learning styles, abilities, and preferences.

Summary

Educators and trainers are increasingly drawn to adaptive 3D learning paths to boost learner engagement and improve outcomes, leveraging technologies that dynamically adjust to individual needs. Despite its challenges, this approach offers personalized experiences, data-driven insights, and increased engagement for the learner, while revolutionizing training methods for the training center.

Citations

Alam, A., Ullah, S., & Ali, N. (2016). A Student-friendly Framework for Adaptive 3D-Virtual Learning Environments. Proceedings of the Pakistan Academy of Sciences: A. Physical and Computational Sciences, 53(3), 255–266. https://paspk.org/wp-content/uploads/2016/10/A-Student-friendly.pdf

Mustapha, R., Soukaina, G., Mohammed, Q., & Es-Saadia, A. (2023). Towards an Adaptive e-Learning System Based on Deep Learner Profile, Machine Learning Approach, and Reinforcement Learning. International Journal of Advanced Computer Science and Applications, 14(5), 265–274. DOI: 10.14569/IJACSA.2023.0140528

Streicher, A., & Pickl, S. W. (2020). Characterization and Analysis with xAPI based graphs for adaptive interactive learning environments. WMSCI, Orlando, FL, USA. https://publica-rest.fraunhofer.de/server/api/core/bitstreams/fb4bfa1b-1b83-4e93-a00f-ed81f4cde9b6/content