Search

This paper studies the problem of designing analog circuits to achieve target specifications, which can be formulated as a multi-objective combinatorial optimization (MOCO) under uncertainty. We address this challenging problem using the $g_{m} / I_{D}$ methodology and a reinforcement learning (RL) framework. The proposed fast RL-based analog circuit designer (fRL-AD) maintains circuits’ DC bias conditions while determining their sizing parameters associated with AC characteristics. This ensures robust convergence to optimal sizing parameters across target specifications and proficiently captures layout effects. Specifically, by decomposing the problem into a sequence of feasible problems, our pre-trained RL agent can efficiently seek a solution for each feasible problem by generating states (i.e., candidate solutions) following a learned policy. Since the sequence of feasible regions is designed to approach an optimal solution to our main problem, the RL agent can find a near-optimal solution by sequentially tackling the feasible problems. Remarkably, using better initial points (or states), our approach is more efficient than directly solving the last feasible problem. Furthermore, we introduce an adaptive action space in our RL framework, which can dynamically modulate the size of the action space elements. The proposed method provides an effective and stable design of various analog circuits, overcoming their traditionally low productivity due to reliance on human expertise and time-consuming simulations to handle uncertainties. We verify the effectiveness of our algorithm via experiments with various analog circuit topologies.

Abstract Soft exosuits used for supporting human muscle strength must be lightweight and wearable. Shape memory alloy (SMA) spring-based fabric muscles (SFM) are light and flexible, making them suitable for soft and shape-conformable exosuits. However, SFMs have a slow actuation speed owing to the slow cooling rate of the SMA spring. This paper proposes a forced air-cooling fan-integrated fabric muscle (FCFM) that improves the cooling rate by arranging a thin-diameter SMA spring bundle with a high surface-area-to-volume ratio inside a breathable fabric with integrated fans. The relaxation time of an FCFM weighing 30 g and containing a 2.6 g SMA spring bundle, which contains 200 thin springs, was reduced by over 70.2% via forced-air cooling using the integrated fans. A 4 kg weight, which is 1530 times the mass of the SMA spring bundle, was hung from the FCFM and was repeatedly actuated in ten-second cycles. An upper limb assistive soft exosuit with FCFMs was fabricated and worn on a mannequin holding a dumbbell, and the arm extension time after flexion was improved by 4.5 times. Additionally, the assistive performance of the exosuits for repetitive tasks in specific scenarios was evaluated, and the strong potential of the proposed FCFM for soft exosuits was verified.

In the field of robotics, sensors are crucial in enabling the interaction between robots and their users. To ensure this interaction, sensors mainly measure the user’s strength, and based on this, wearable robots are controlled. In this paper, we propose a novel three-axis force/torque sensor for wearable robots that is compact and has a high load capacity. The bolt and nut combination of the proposed sensor is designed to measure high-load weights, and the simple structure of this combination allows the sensor to be compact and light. Additionally, to measure the three-axis force/torque, we design three capacitance-sensing cells. These cells are arranged in parallel to measure the difference in capacitance between the positive and negative electrodes. From the capacitance change measured by these sensing cells, force/torque information is converted through deep neural network calibration. The sensing point can also be confirmed using the geometric and kinematic relation of the sensor. The proposed sensor is manufactured through a simple and inexpensive process using cheap and simply structured components. The performance of the sensor, such as its repeatability and capacity, is evaluated using several experimental setups. In addition, the sensor is applied to a wearable robot to measure the force of an artificial muscle.

This study proposes a soft inductive coil spring (SICS) strain sensor that can measure the strain of soft actuators. The SICS sensor, produced by transforming a shape memory alloy (SMA) wire with the same materials as that of an SMA spring bundle actuator (SSBA) into a coil spring shape, measures inductance changes according to length changes. This study also proposes a manufacturing method, output characteristics of the SICS sensor applicable to the SSBA among soft actuators, and the structure of the SICS sensor-integrated SSBA (SI-SSBA). In the SI-SSBA, the SMA spring bundle and SICS sensor have structures corresponding to the muscle fiber and spindle of the skeletal muscle, respectively. It is demonstrated that when a robotic arm with one degree of freedom is operated by attaching two SI-SSBAs in an antagonistic structure, the displacement of the SSBA can be measured using the proposed strain sensor. The output characteristics of the SICS sensor for the driving speed of the robotic arm were evaluated, and it was experimentally proven that the strain of the SSBA can be stably measured in water under a temperature change of 54 °C from 36 to 90 °C.