A soft 3-DOF interaction force measurement system for estimating the biomechanical effects of a soft wearable robot on the human joint

Abstract

Recent advancements in wearable robots have focused on developing soft, compliant, and lightweight structures to provide comfort for the users and to achieve the primary function of assisting body motions. The interaction forces induced by physical human-robot interaction (pHRI) not only cause skin discomfort or pain due to relatively high localized pressures but also degrade the wearability and the safety of the wearer's joints by unnaturally altering the joint reaction forces (JRFs) and the joint reaction moments (JRMs). Although the correlation between excessive JRFs/JRMs and joint-related conditions has been reported by researchers, the biomechanical effects of forces and moments caused by the pHRI of a wearable robot on the wearer's joints remain under-analyzed. In this study, we propose a method of measuring and analyzing these interactions and effects, using a custom-designed soft, three-degree-of-freedom (DOF) force sensor. The sensor is made of four Hall effect sensors and a neodymium magnet embedded in a silicone elastomer structure, enabling simultaneous measurement of normal and two-axis shear forces by detecting the distance changes between the magnet and each Hall effect sensor. These sensors are embedded in contact pads of a commercial wearable robot and measure the interaction forces, used for calculating JRF and JRM. We also propose a modified inverse dynamics approach that allows us to consider the physical interactions between the robot and the human body. The proposed method of sensing and analysis provides the potential to enhance the design of future wearable robots, ensuring long-term safety.

Keywords: biomechanics; exosuit; force sensors; interaction force; physical human-robot interaction; wearable robot.

Figure 1.

System methodology overview. The sensor system for measuring full DOF interaction forces was augmented to the commercial wearable robot by replacing original physical interfaces with customized contact pads. A movement experiment was subsequently conducted utilizing the Motion capture system, force plate, and pHRI measurement system. The modified inverse dynamics incorporates these interaction forces from the pHRI into the calculation of joint reaction forces and moments, enabling an accurate assessment of the biomechanical effects of the wearable robot on human joints.

Figure 2.

Sensor design and fabrication procedure. (a) Dimension from the top view and (b) components of the sensor. (c) Silicone elastomer is poured on a glass plate and cured. (d) Four Hall effect sensors are fixed in position and the silicone elastomer is poured on top and cured. (e) Wires are soldered at Hall effect sensors. (f) Magnet is placed at the center and silicone elastomer is poured on top and cured. (g) Sensor is cut into an appropriate size.

Figure 3.

Sensor experimental setup and results for characterization. (a) Experimental setup for normal and shear force testing. A 5 mm diameter indenter was used to apply the normal force, while acrylic plates were attached to the sensor surface for the shear force tests. (b) Hall sensor layout showing sensors 1 through 4, each marked with a different colored box. (c) Normal force characterization results for sensor 1 and 3. (d) Shear force characterization results in the directions corresponding to sensors 1 and 2. (e) Shear force characterization results in the directions corresponding to sensors 3 and 4.

Figure 4.

Schematic diagram for wireless sensor data acquisition. Each contact pad integrates the sensor system consisting of a data acquisition module and 3-DOF soft sensors. The data acquisition module reads the sensor output via a direct connection between each Hall effect sensor of the 3-DOF sensor and a 16-bit ADC. Each data acquisition module is wirelessly connected to an Arduino Uno via Bluetooth for sensor data transfer. A total of 80 sensor outputs from all contact pads were transmitted at a sampling rate of 10 Hz and synchronized with the Motion capture system.

Figure 5.

Augmentation of the sensor system on a commercial wearable robot. (a) The customized soft contact pads replicate the original braces and cushions while providing additional spaces for the fixation of 3-DOF force sensors. (b) Illustrations of the customized contact pad integrated with the sensor system, showing the 3-DOF sensors and data acquisition module positioned on the interior (contact areas) and exterior, respectively. (c) Images depicting the interior and exterior views of the right limb of the commercial exosuit (Myosuit) after attachment of the customized contact pads (Left). A photograph illustrating the subject wearing the exosuit with the sensor system is presented (right). Six contact pads, each equipped with a total of twenty 3-DOF sensors, cover all contact regions on the right lower limb.

Figure 6.

Overview of the experiment design. (a) Schematic illustration of one participant wearing an exosuit on two force plates that measure the ground reaction force. Motion capture cameras were placed around a participant. (b) Schematic illustration of each task.

Figure 7.

Conceptual figure for the modified inverse dynamics. (a) The procedure for calculating net forces and moments exerted on the shank from the measured 3-DOF interaction forces is shown, particularly highlighting the upper shank contact region with equations for deriving the net force F_US and net moment M_US exerted on the center point of the cross-section of the upper shank. (b) A schematic block diagram of the modified inverse dynamics. The distinct feature of the modified inverse dynamics, which considers interaction forces as input parameters in the calculation of JRF and JRM, is highlighted in the blue-colored block. An example illustration to obtain pure JRF F_knee and JRM M_knee at the knee joint by applying the modified inverse dynamics is shown.

Figure 8.

Joint force and moment trajectories observed significant differences in maximum/minimum values before and after applying sensor data during STS, OW, and SC tasks (p < 0.05). The shaded region represents ±1 standard deviation from each mean. TM and AM indicate transparency mode and assistive mode, respectively. Gray arrows indicate joint reaction forces and moments calculated from conventional inverse dynamics (conv) and yellow-extended arrows indicate joint reaction forces and moments calculated from modified inverse dynamics (mod) using sensor-measured forces and moments (yellow arrows). Joint reaction forces and moments were normalized to weight.