FOFrederik Ostyn

Frederik Ostyn

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Frederik Ostyn has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Optimizing Link Flexibility for Safety and Dynamic Performance for Collaborative Manipulators

    by Hafsa Nouhi, Thomas De Clercq, Chaoyue Fei, Frederik Ostyn, Bram Vanderborght, Guillaume Crevecoeur, Greet Van De Perre

    Cobots are designed to work in close collaboration with humans. To ensure safety in shared workspaces, ISO/TS 15066 imposes limits on the collaborative robot speeds to limit the impact forces during collisions. These limits depend on robot design, including inertia. Flexible link manipulators combine the advantage of lightweight design and the introduction of an elastic element, which is promising in the context of collaborative robots. However, reduced stiffness affects dynamic performance. As trade-offs between link flexibility for safety and dynamic performance remain unclear, this paper investigates how undesired side effects of flexibility relate to the positive aspects of compliance and lightweightness. To investigate the effect of flexibility on both safety towards a human and controlled manipulator dynamics, a generic simulation framework was designed. Safety is assessed by a simulation study on the influence of varying geometrical parameters on impact force at collision with a human head, after which the corresponding maximum allowable end-effector velocities per ISO/TS 15066 threshold were derived. To analyze control performance, a generic controller was implemented, consisting of a PID with direct strain vibration control, with gains optimized for each link design. The resulting end-effector tracking performance during point-to-point motion is evaluated. Based on these results, a co-design methodology was proposed to optimize link geometry and control gains for the fastest possible, yet safe motion for a given task. The effectiveness of the method was experimentally validated to assess whether optimal link stiffness and controller gains yield the desired dynamic performance while respecting ISO safety thresholds.

  • Open Access

    Energy-Based Exploration for Reinforcement Learning of Underactuated Mechanical Systems

    by Jeroen Taets, Tom Lefebvre, Frederik Ostyn, Guillaume Crevecoeur

    Reinforcement Learning (RL) for underactuated mechanical systems presents unique challenges due to the limited control inputs and complex dynamics of the system. Efficient exploration poses a significant problem for two reasons: First, these systems must start each episode of learning from an equilibrium position instead of a random position, severely limiting exploration. Second, these systems are often chaotic, which limits model-based exploration. To address these challenges, we introduce Energy-based Exploration for Reinforcement Learning (EBERL), which exploits a model of the system’s energy represented by a Deep Lagrangian Network (DeLaN), coupled to an energy-based controller to ensure goal-directed exploration on top of the exploration principles that are already present in RL. First, we validated our method in simulation on a Cartpole, Furuta pendulum and Pendubot with challenging torque constraints that cannot be solved by traditional methods. Additionally, we experimentally validated our method on the swing-up and stabilization of a Quanser QUBE2 Furuta pendulum.


  • Open Access

    Automated human-in-the-loop commissioning of industrial processes: a glue dispensing case study

    by Jeroen Taets, Jeroen Jordens, Tom Lefebvre, Frederik Ostyn, Guillaume Crevecoeur


  • Enhanced Force Estimation and Autonomous Force Tuning Through Fusion of Tactile Sensor and Quasi-Direct Drive Gripper

    by Thomas De Clercq, Frederik Ostyn, Guillaume Crevecoeur

    Robotic manipulation relies on accurate force sensing and control mechanisms to ensure efficient and safe operation. This paper presents a novel approach to enhance robotic manipulation capabilities by integrating a barometric tactile sensor with a quasi-direct drive gripper (QDDG). The synergy between these technologies addresses inherent limitations: QDDGs struggle with high current requirements and potential overheating, while tactile sensors often have restricted force ranges and sampling rates. By fusing data from these systems using an adaptive sensor fusion model, this study improves force estimation accuracy, extends force range capability, and boosts sampling rates up to 100 Hz. The integrated approach not only enhances grasping efficiency but also enables autonomous adjustment of grip force levels to prevent slippage. Experimental results demonstrate significant improvements in force estimation accuracy over individual sensor outputs, validating the effectiveness of the proposed integration for advanced robotic manipulation tasks. Furthermore, based on this sensor fusion framework, a slip detection and control mechanism was developed capable of grasping and lifting a diverse array of objects with high success-rates (>90%).


  • Improving the Collision Tolerance of High-Speed Industrial Robots via Impact-Aware Path Planning and Series Clutched Actuation

    by Frederik Ostyn, Bram Vanderborght, Guillaume Crevecoeur

    Robots are more often deployed in unstructured or unpredictable environments. Particularly collisions at high speed can severely damage the drivetrains and joint bearings of robots. In order to avoid such collisions, path planners exist that adapt the robot's original trajectory online if a collision hazard is detected. These methods require additional sensors such as cameras, are computationally costly and never flawless due to occlusions. Another approach is to incorporate a cost function that promotes collision tolerance while planning the initial trajectory. The resulting impact-aware path plan minimizes the chance of robot hardware damage if a collision would occur. Two algorithms are presented to assess collision tolerance in high-speed robots, taking into account factors such as robot pose, impact direction, and maximum intermittent loading of the gearboxes and bearings. The first algorithm is more general while the second assumes the presence of joint overload clutches that decouple upon impact. These algorithms are applied to plan an impact-aware path for a custom 6-axis series clutched actuated robot that serves as use case. Both for the case with and without clutches, a generic impact-aware plan is presented as well as at least one derived, heuristic alternative. Without clutches, trajectories that are perpendicular to the end effector flange were found to be desirable, as they allow the robot to mitigate the highest collision force without overloading the gearboxes or bearings. On the other hand, with clutches, trajectories that are parallel to the end effector flange were found to be more collision tolerant. The effect of impact direction was also experimentally validated using the custom 6-axis robot. Collisions at velocities up to 1.2m/s were mitigated through the combination of impact-aware path planning and series clutched actuation.


  • Open Access

    Soft Barometric Tactile Sensor Utilizing Iterative Pressure Reconstruction

    by Thomas de Clercq, Anatolii Sianov, Frederik Ostyn, Guillaume Crevecoeur

    Tactile sensors play a pivotal role in enhancing robotic gripping systems across various industries, allowing robots to interact with their environment with precision and adaptability. This study introduces a novel soft barometric tactile sensor designed to capture pressure data beneath the contact pad within an elastomer layer. By employing an iterative fitting process for a parameterized pressure distribution, the sensor eliminates the need for extensive calibration or complex training procedures. A novel metric was introduced to evaluate the accuracy of pressure reconstruction in tactile sensors. This was complemented by quantitative investigations. Moreover, the precision of multiple contact detection and the capabilities of force estimation were examined. Finally, the practical applications of the sensor were demonstrated through in-hand measurement of object orientation. The sensor exhibits promising results, accurately reconstructing pressure distributions for a wide range of indenters, reliably discerning two contacts when their distance exceeds 5 mm and estimating forces with a Mean Absolute Error (MAE) of 1.83 N . Additionally, the inhand reorientation achieved a Mean Absolute Rotation Error (MARE) of 6.81°, demonstrating the sensor’s potential for real-world applications.


  • Series Clutched Actuation for Collision-Tolerant High-Speed Robots

    by Frederik Ostyn, Bram Vanderborght, Guillaume Crevecoeur

    Collisions at high-speed can severely damage robots with non-backdrivable drivetrains. Adding an overload clutch in series can improve the robot’s collision tolerance without compromising its high dynamic performance. This paper aims at determining the speed above which overload clutches are required in a two-link manipulator arm. Furthermore, the optimal clutch topology as function of the impact velocity is investigated. Third, it is evaluated if adding clutches can lower the impact force on the arm. Finally, the maximum speed is identified below which impact-aware robot control is possible. The latter requires that none of the clutches decouple during an intentional collision with the environment. These answers are obtained through collision simulations and experiments with a custom build two-link arm. It was found that adding a clutch reduces the torque experienced by the drivetrain by an order of magnitude and below the limit momentary peak torque of the strain wave gears that are used. Adding a clutch to the elbow joint of the two-link arm was effective in protecting the shoulder as well if the impact occurred at the tool center point. With respect to a rigid elbow joint, the clutched elbow joint reduced the collision force at the tool by only 8%. To demonstrate that the arm is impact-aware, a box of 8 kg is approached, impacted, and pushed at 1 m/s without decoupling a clutch, nor damaging the robot’s hardware.


  • Overload Clutch With Integrated Torque Sensing and Decoupling Detection for Collision Tolerant Hybrid High-Speed Industrial Cobots

    by Frederik Ostyn, Bram Vanderborght, Guillaume Crevecoeur

    A hybrid high-speed industrial collaborative robot can switch between collaborative mode and high-speed mode, combining the advantages of both. While promising, this concept comes with some challenges such as dealing with collisions at high speed. An overload clutch with integrated torque sensing and clutch decoupling detection is presented as enabling technology. Both joint torque sensing and clutch decoupling detection are realized with the same capacitive measurement hardware that consists of paired electrodes. A prototype device is experimentally validated through comparison with a reference torque sensor.


  • Design and Control of a Quasi-Direct Drive Robotic Gripper for Collision Tolerant Picking At High Speed

    by Frederik Ostyn, Bram Vanderborght, Guillaume Crevecoeur

    Faster robotic picking of objects can improve industrial production throughput. A gripper design with appropriate control strategy is demonstrated to pick objects at high speed, while being tolerant to unintentional collisions. The design has a quasi–direct drive with backdrivable, rigid finger mechanism to transfer collision forces with minimal delay towards the motor side. These forces are detected based on band–pass filtered momentum and motor speed monitoring. The motor velocity is observed through Kalman filtering in order to reduce noise in the low–level control loop and band–pass momentum observer, resulting in a higher collision detection sensitivity. On a higher level, the path of the gripper is planned with respect to the trade–off picking speed versus collision tolerance, quantified by the remaining gripper stroke upon impact. The gripper collision tolerance was experimentally verified in several scenarios during high–speed object picking where it mitigated collisions up to 0.6 m/s.