Key Takeaways & Executive Findings
- •• Proposes a novel virtual impedance adaptation strategy (VIADRL) for lower-limb exoskeletons, leveraging deep reinforcement learning to reduce reliance on accurate dynamic models. • Introduces a hybrid inverse-forward dynamics simulation approach for safe and efficient policy training in a multibody environment. • Demonstrates significant reduction in human-exoskeleton interaction forces (up to 19% in simulation and 11% on prototype) compared to the sensitivity amplification control with deep reinforcement learning (SADRL) benchmark. • Provides a quantitative evaluation method based on HEI forces at back, thighs, and shanks, offering a new metric for exoskeleton control performance.
Abstract
This paper proposes virtual impedance adaptation of the lower-limb exoskeleton for human performance augmentation (LEHPA) based on deep reinforcement learning (VIADRL) to mitigate reliance on model accuracy and address the ever-changing human-exoskeleton interaction (HEI) dynamics. The classical sensitivity amplification control strategy is expanded to the virtual impedance control strategy with more learnable virtual impedance parameters. The adjustment of these virtual impedance parameters is formalized as finding the optimal policy for a Markov Decision Process and can then be effectively resolved using deep reinforcement learning algorithms. To ensure safe and efficient policy training, a multibody simulation environment is established to facilitate the training process, supplemented by the innovative hybrid inverse-forward dynamics simulation approach for executing the simulation. For comparison purposes, the SADRL strategy is introduced as a benchmark. A novel control performance evaluation method based on the HEI forces at the back, thighs, and shanks is proposed to quantitatively evaluate the performance of our proposed VIADRL strategy. The VIADRL controller is systematically compared with the SADRL controller at five selected walking speeds. The lumped ratio of HEI forces under the SADRL strategy relative to those under the SADRL strategy is as low as 0.81 in simulation and approximately 0.89 on the LEHPA prototype. The overall reduction of HEI forces demonstrates the superiority of the VIADRL strategy in comparison to the SADRL strategy.
1. Introduction
The lower-limb exoskeleton for human performance augmentation (LEHPA) represents a distinct category of wearable robotic systems that operate in conjunction with the human body, transfer payload weight to the ground, and thereby enhance human strength and endurance [1–3]. Integrating human intelligence with robot power and stamina, the coupled human-exoskeleton system demonstrates a clear advantage over bipedal or quadrupedal robots in adapting to challenging and unstructured environments and offers excellent potential for performing hazardous and complex tasks, such as military missions, disaster relief, firefighting, manufacturing [4–7]. Research on the LEHPA system dates back to the 1960s, with notable advancements achieved in various domains over the past two decades, such as mechanical design [8, 9], sensors [10], actuators [11], control strategies [12, 13], performance evaluation [14, 15] and so on.
Particularly, the control strategy garnered significantly greater focus from researchers. Numerous strategies have been proposed to enhance the assistance efficacy and wearing comfort of the LEHPA system. The most famous control strategy is Sensitivity Amplification Control (SAC) [16], which was originally formulated for Berkeley Lower Extremity Exoskeleton (BLEEX) [17], the first load-bearing and energetically autonomous exoskeleton developed by Human Engineering and Robotics Laboratory at U.C. Berkeley with the support of the DARPA Exoskeletons for Human Performance Augmentation (EHPA) program, and had been implemented later in the control of HULC [18], XOS [19], and HLEER [20]. The SAC strategy recognizes the human motion intention using measurements only from the exoskeleton, eliminating the need for direct measurements of bioelectric signals from the pilot or human-exoskeleton interaction (HEI) force signals at human-exoskeleton interfaces, which facilitates reducing system complexity and enhancing reliability. The sensitivity transfer function is defined as the mapping from the equivalent pilot torque to the exoskeleton’s angular velocity, demonstrating the influence of the HEI forces on the exoskeleton motion. To guarantee a high closed-loop sensitivity without directly measuring the equivalent pilot torque, the SAC strategy utilizes the inverse dynamic model of the exoskeleton as positive feedback, causing the control effect to heavily rely on the model accuracy.
Loading authentic research manuscript (Pages 1–5)...
Ranran Zheng, Zhiyuan Yu, Hongwei Liu, Junqin Lin, Bo Zeng, Longfei Jia (2025). Virtual Impedance Adaptation of Lower-Limb Exoskeleton for Human Performance Augmentation Based on Deep Reinforcement Learning. Chinese Journal of Mechanical Engineering. https://doi.org/10.1186/s10033-025-01355-y
Research & Educational Purpose Only:The translations, structured abstracts, analytical annotations, and data reports provided by SinoTechIntel are intended exclusively for academic research, internal corporate R&D, and educational benchmarking. They do not constitute formal engineering, chemical safety, legal, or professional advice.
Copyright & Intellectual Property Notice: Original copyright of the underlying source articles and experimental data remains with the respective authors, institutions, and original publishing journals. SinoTechIntel claims intellectual property only over its proprietary translations, analytical syntheses, and AEO structured enhancements in accordance with international fair use and academic citation principles.
Frequently Asked Questions
What is the main contribution of this paper?
The paper proposes a virtual impedance adaptation strategy based on deep reinforcement learning (VIADRL) for lower-limb exoskeletons, which reduces reliance on accurate dynamic models and adapts to changing human-exoskeleton interaction dynamics, leading to improved assistance performance.
How does VIADRL differ from traditional sensitivity amplification control (SAC)?
VIADRL expands SAC to a virtual impedance control strategy with more learnable parameters, and uses deep reinforcement learning to optimize these parameters, whereas SAC relies on an inverse dynamic model and fixed sensitivity gains.
What evaluation method is proposed in the paper?
A novel control performance evaluation method based on human-exoskeleton interaction (HEI) forces at the back, thighs, and shanks is proposed to quantitatively assess the assistance effectiveness.
What are the key results of the study?
The VIADRL strategy reduced HEI forces by up to 19% in simulation and approximately 11% on the prototype compared to the SADRL benchmark, demonstrating its superiority in enhancing human performance.
How was the training of the reinforcement learning policy conducted?
Training was conducted in a multibody simulation environment using a hybrid inverse-forward dynamics simulation approach, ensuring safety and efficiency before deployment on the physical prototype.
Related Technical Papers & Translations
Direct Repair of the Crystal Structure and Coating Surface of Spent LiFePO4 Materials Enables Superfast Li-Ion Migration
The rapid accumulation of spent LiFePO4 (LFP) cathodes from retired lithium-ion batteries necessitates the development of effective and environmental-friendly recycling strategies. In this context, direct regeneration has emerged as a promising approach for reclaiming LFP cathode materials, offering a streamlined pathway to restore their electrochemical functionality. We report an integrated regeneration protocol that simultaneously repairs the degraded crystal structure and reconstructs the damaged carbon coating in spent LFP. The regenerated cathode material had superfast lithium-ion diffusion kinetics and a stable cathode–electrolyte interface, giving a remarkable rate capability with specific capacities of 122 mAh g−1 at 5C and 106 mAh g−1 at 10C (1C = 170 mA g−1). It also maintained capacities of 110.7 mAh g−1 (5C) and 84.1 mAh g−1 (10C) after 400 cycles. It could be used in harsh environments and could be stably cycled at subzero temperatures (−10 and −20 °C) and in solid-state electrolyte batteries. Life cycle assessment combined with economic evaluation using the EverBatt model reveals that this direct regeneration approach has high economic and environmental benefits.
Oxide Semiconductor for Advanced Memory Architectures: Atomic Layer Deposition, Key Requirement and Challenges
Oxide semiconductors (OSs), introduced by the Hosono group in the early 2000s, have evolved from display backplane materials to promising candidates for advanced memory and logic devices. The exceptionally low leakage current of OSs and compatibility with three-dimensional (3D) architectures have recently sparked renewed interest in their use in semiconductor applications. This review begins by exploring the unique material properties of OSs, which fundamentally originate from their distinct electronic band structure. Subsequently, we focus on atomic layer deposition (ALD), a core technique for growing excellent OS films, covering both basic and advanced processes compatible with 3D scaling. The basic surface reaction mechanisms—adsorption and reaction—and their roles in film growth are introduced. Furthermore, material design strategies, such as cation selection, crystallinity control, anion doping, and heterostructure engineering, are discussed. We also highlight challenges in memory applications, including contact resistance, hydrogen instability, and lack of p-type materials, and discuss the feasibility of ALD-grown OSs as potential solutions. Lastly, we provide an outlook on the role of ALD-grown OSs in memory technologies. This review bridges material fundamentals and device-level requirements, offering a comprehensive perspective on the potential of ALD-driven OSs for next-generation semiconductor memory devices.
Laser powder bed fusion of biodegradable Zn-4Cu alloy: Processing, microstructure and properties
Zn's natural degradability and biocompatibility make it a promising candidate for implants, however, its mechanical properties remain insufficient for bone applications. In this study, the performance of Zn was enhanced by developing Zn-Cu alloys via laser powder bed fusion (LPBF). Optimal LPBF parameters for forming stable tracks were achieved by adjusting laser power and scanning speed. Under optimized conditions of 100 W and 100 mm/s, high-density (99.58%) Zn-Cu alloys with improved hardness (68.2HV) and yield strength (160 MPa) were achieved. These improvements are attributed to solid solution strengthening, segregation strengthening, and grain refinement. The Zn-Cu alloys also demonstrated favorable degradation behavior, with a rate of 0.16 mm/year. This degradation is primarily driven by micro-galvanic corrosion between the CuZn5 phase and Zn matrix, along with refined grains and increased grain boundary density. This work demonstrates a viable strategy for fabricating Zn-based implants with enhanced structural integrity and mechanical performance via LPBF.