Martin Bjaadal Økter

• Økter, Martin Bjaadal; Brekke, Vegard; Dybdahl, Eirik; Tyapin, Ilya & Choux, Martin Marie Hubert (2026). A Robotic Setup for Adaptive EV-Battery Disassembly Using ROS2 in a Near-Industrial Environment. IEEE International Conference on System of Systems Engineering (SoSE). ISSN 2835-3307. doi: 10.1109/SoSE69681.2026.11622357. Full text in Research Archive Show summary

  The growing number of end-of-life electric vehicle (EV) batteries demands scalable and adaptive disassembly solutions to enable efficient recycling. This paper presents a near-industrial robotic demonstrator for adaptive EV battery pack disassembly. The system integrates two industrial manipulators, force/torque sensing, automatic tool changing, and structured-light 3D vision within a ROS2-based perception and control architecture. A YOLO-based detection pipeline combined with point-cloud processing and coordinate transformation enables the automatic generation of robot targets for multi-step operations, including nut removal and battery module extraction. The results demonstrate that the modular integration of industrial robotics and AI-based perception can enable adaptive, multi-operation battery disassembly in a near-industrial environment. Experimental validation across 36 disassembly trials demonstrates reliable module extraction with a 100% success rate and an overall nut removal success rate of 77.6%, with performance degradation primarily linked to perception-localisation errors for off-axis nut detections.

• Økter, Martin Bjaadal; Tyapin, Ilya & Choux, Martin Marie Hubert (2025). Dynamic Robotic Disassembly using Reinforcement Learning and Simulation: Initial Application to EV Batteries. International Conference on Control, Mechatronics and Automation. ISSN 2837-5114. doi: 10.1109/iccma67641.2025.11369636. Full text in Research Archive Show summary

  The disassembly of electric vehicle (EV) battery packs remains a labor-intensive and potentially hazardous process, complicated by significant variations in pack design and condition. Conventional automation relies on rigid programming and prior knowledge of component layout, which limits scalability and adaptability. This work presents a proof-of-concept framework for adaptive robotic disassembly using reinforcement learning (RL) and high-fidelity simulation. A simplified two-stage disassembly task—removing a locking pin from a pipe-and-cylinder assembly, was implemented in NVIDIA Isaac Sim and integrated with the Isaac Lab RL environment. Proximal Policy Optimization (PPO) agents were trained using both the RSL-RL and StableBaselines3 libraries, employing structured reward shaping, targeted hyperparameter tuning, and Cartesian end-effector control to improve learning stability and task precision. Initial results demonstrate consistent task completion, with reduced unintended movement of non-target components and high repeatability across validation runs. The developed simulation and training pipeline provides a flexible, modular platform for future exploration of alternative RL algorithms and more complex disassembly scenarios. These results highlight the potential of RL-based methods to enable scalable, dynamic automation for EV battery recycling in environments with high variability and uncertainty.

• Økter, Martin Bjaadal & Sanfilippo, Filippo (2025). A ROS-Based Framework for Low-Cost Real-Time Haptic Feedback in Human-Robot Teaming. In Scarpa, Marco; Cavalieri, Salvatore; Serrano, Salvatore & Vita, Fabrizio De (Ed.), Proceedings of the 39th ECMS International Conference on Modelling and Simulation (ECMS 2025), June 24th - June 27th, 2025, Catania, Italy. ECMS European Council for Modelling and Simulation. ISSN 9783937436869. p. 677–684. doi: 10.7148/2025-0677. Full text in Research Archive Show summary

  The evolution from human-robot interaction (HRI) to human-robot collaboration (HRC), and ultimately to human-robot teaming (HRT), represents a significant paradigm shift in how humans and robots work together. HRI initially framed robots as tools under human command, while HRC introduced greater autonomy in shared tasks. Today, HRT reimagines robots as equal team members, capable of adaptive communication and synchronized decision-making. A critical challenge in achieving effective HRT is developing haptic feedback systems that provide operators with real-time sensory information. This work presents a low-cost software-driven haptic feedback framework using ROS and micro-ROS to enhance realtime control in HRT environments. Unlike current costly, hardware-specific solutions, the proposed framework emphasizes accessibility and flexibility. System validation through precise force control tasks demonstrates the framework’s potential to advance HRT through cost-effective, software-centric solutions.

• Păcurar, Răzvan Ioan; Sanfilippo, Filippo; Økter, Martin Bjaadal; Băilă, Diana-Irinel; Zaharia, Cătălin & Nicoară, Adrian Ionuţ [Show all 14 contributors for this article] (2024). Use of high-performance polymeric materials in customized low-cost robotic grippers for biomechatronic applications: experimental and analytical research. Frontiers in Materials. 11. doi: 10.3389/fmats.2024.1304339. Full text in Research Archive
• Sanfilippo, Filippo; Økter, Martin Bjaadal; Dale, Jørgen; Hua, Minh Tuan & Ottestad, Morten (2024). Revolutionising Prosthetics and Orthotics with Affordable Customisable Open-Source Elastic Actuators. In NN, . (Eds.), International Conference on Automation, Robotics and Applications (ICARA). Institute of Electrical and Electronics Engineers (IEEE). ISSN 9798350394252. p. 57–63. doi: 10.1109/ICARA60736.2024.10553120. Full text in Research Archive Show summary

  Collaborative robots, also known as cobots, have become progressively popular as they are designed to safely work alongside humans or in shared environments. The adoption of compliant actuators, which avoid damage in the event of an unintentional collision, is an important feature of their design. In prosthetic and orthotic applications, the use of compliant actuators, which minimise damage in the case of an inadvertent contact, is critical to ensuring safety and comfort for the user. In dynamic settings, elastic actuators are preferred over rigid ones, however most compliant cobots are currently too expensive or complex to construct for prosthetic and orthotic applications. To address this challenge, this study presents a low-cost sensorised elastic actuator design for prosthetics and orthotics. This is presented as an educational framework. The design is modular and can be quickly customised using 3D printing technology, allowing for efficient and cost-effective fabrication. Both the hardware and software are open-source, enabling easy access for students, researchers and practitioners. The design also allows for the introduction of impedance and admittance control techniques, providing even greater versatility to the system.

• Sanfilippo, Filippo; Økter, Martin Bjaadal; Dale, Jørgen; Hua, Minh Tuan; Zafar, Muhammad Hamza & Ottestad, Morten (2024). Open-source design of low-cost sensorised elastic actuators for collaborative prosthetics and orthotics. HardwareX. 19. doi: 10.1016/j.ohx.2024.e00564. Full text in Research Archive
• Borge, Jørgen; Wad, Martin Sauar; Økter, Martin Bjaadal; Ottestad, Morten; Rudolfsen, Morten H. & Zhou, Jing (2022). Design and Implementation of Mechatronics Home Lab for Undergraduate Mechatronics Teaching, 2022 IEEE 17th International Conference on Control & Automation (ICCA). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781665495721. p. 291–296. doi: 10.1109/ICCA54724.2022.9831876. Full text in Research Archive Show summary

  The field of mechatronics is a multidisciplinary field of engineering, where the combination of physical components and theory from several engineering fields is applied to build complex machines. Mechatronics education is an active learning process through practical laboratory exercises and problem-based learning. This paper presents the design and implementation of a mechatronics home lab to support undergraduate mechatronics teaching. The purpose is to support theoretical teaching in mechatronics with a low-cost, 3D-printable platform where the students can experiment and practice instrumentation and control theory with a practical problem-based approach. Five projects were introduced for experiment implementation of the developed home lab. Throughout these experiments, it is intended to facilitate the understanding of theories and concepts in mechatronics, and enhance the ability to design and implementation of experiments, the collection and analysis of data, and the conducting of simulation in MATLAB.

• Sanfilippo, Filippo; Økter, Martin Bjaadal; Eie, Tine Cecilia & Ottestad, Morten (2022). An Open Framework for teaching Motion Control for Mechatronics Education, 2022 7th International STEM Education Conference (iSTEM-Ed). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781665498210. doi: 10.1109/iSTEM-Ed55321.2022.9920788. Full text in Research Archive Show summary

  This paper proposes the introduction of a novel open prototyping framework that involves using low-cost commercial off-the-shelf (COTS) components and tools for the module of motion control, within mechatronics education. The goal of this study is to propose a novel structure for the motion control module in the engineering mechatronics curriculum. This is accomplished by integrating students in a series of well-organised theoretical lectures as well as hands-on, highly engaging labora-tory group projects. Surface learning parts and deep learning sections are combined frequently to encourage learners to grasp, make connections, and expand their knowledge. The structure of the course as well as the key topics are discussed. The proposed open framework, which consist of an elevator model, is presented in details.

• Sanfilippo, Filippo; Økter, Martin Bjaadal; Eie, Tine Cecilia & Ottestad, Morten (2022). Teaching Motion Control in Mechatronics Education Using an Open Framework Based on the Elevator Model. Machines. 10(10). doi: 10.3390/machines10100945. Full text in Research Archive Show summary

  Universities and other educational institutions may find it difficult to afford the cost of obtaining cutting-edge teaching resources. This study introduces the adoption of a novel open prototyping framework in the context of mechatronics education, employing low-cost commercial off-the-shelf (COTS) components and tools for the motion control module. The goal of this study is to propose a novel structure for the motion control module in the engineering mechatronics curriculum. The objective is to foster a new teaching method. From a methodology perspective, students are involved in a series of well-organised theoretical lectures as well as practical, very engaging group projects in the lab. To help students understand, draw connections, and broaden their knowledge, the methods of surface learning and deep learning are frequently mixed thoroughly. The structure of the course as well as the key topics are discussed. The proposed open framework, which consists of an elevator model, is presented in details. Students’ early evaluation indicates that the course organisation and subjects are successful and beneficial.

View all works in NVA