Guoping Zhao

User preference-based human-in-the-loop tuning of exoskeleton assistance during walking

Niklas Schäfer, Guoping Zhao, Bing Li, Mario Kupnik et autres

Personalized exoskeleton assistance has substantial potential to enhance human locomotion performance. However, current human-in-the-loop optimization methods for generating personalized assistance are cumbersome and time-consuming. Since humans can perceive locomotion through internal sensory feedback, user preference-based self-tuning may facilitate the individualization of exoskeleton …

de, bd, cn (code pays fourni par la source)

Electromyography (EMG)-Based Feature Selection for Detecting Movement Effort in Human-in-the-Loop Optimization of Lower Limb Exoskeletons

Martin Grimmer, Fabian Just, Guoping Zhao

This study identifies electromyography (EMG) features as an alternative to metabolic cost for distinguishing varying levels of movement effort. Data from two experiments was used to analyze the performance of 50 EMG-based features. The first experiment, the Load experiment, involved participants walking …

de, se, cn (code pays fourni par la source)

Navigation Scheme of Tracked Robots Based on LiDAR SLAM and Improved A* Algorithm

Linjie Dong, Junfei Wang, Mengqian Tian, Guoping Zhao et autres

Tracked robots are often deployed in environments characterized by narrow passages and uneven terrains, necessitating efficient and accurate path planning to ensure reliable navigation. This paper presents a comprehensive navigation framework based on the SC-A-LOAM LiDAR SLAM system and the OctoMap-based environment …

cn (code pays fourni par la source)

A biarticular prosthetic foot to modulate gait biomechanics and improve walking economy

Bowen Li, Julian Zeiss, Florian Weigand, Guoping Zhao et autres

While powered prosthetic feet with monoarticular actuation allow for the restoration of human ankle biomechanics, gait asymmetries and increased walking effort have been found for transtibial amputees. We hypothesize that this is because of the missing mechanical coupling between the foot and …

cn, de, bd (code pays fourni par la source)

Human-Exoskeleton Interaction Force Estimation Based on Quasi-Direct Drive Actuators

Julian Seiler, Niklas Schêfer, Guoping Zhao, Bastian Latsch et autres

Exoskeletons have emerged as a promising tech-nological solution to provide functional compensation, training support, physical enhancement, and rehabilitation for an aging population. High torque density and control bandwidth are essential for exoskeleton actuation. In addition, monitoring and control of human-exoskeleton interaction forces …

de, cn (code pays fourni par la source)

Hip Exoskeleton for Cycling Assistance

Martin Grimmer, Guoping Zhao

Cycling stands as one of the most widely embraced leisure activities and serves purposes such as exercise, rehabilitation, and commuting. This study aimed to assess the feasibility of assisting three unimpaired participants (age: 34.0 ± 7.9 years, height: 1.86 ± 0.02 m, …

de, cn (code pays fourni par la source)

Joint power, joint work and lower limb muscle activity for transitions between level walking and stair ambulation at three inclinations

Martin Grimmer, Julian Zeiss, Florian Weigand, Guoping Zhao

To enhance human mobility, training interventions and assistive lower limb wearable robotic designs must draw insights from movement tasks from daily life. This study aimed to analyze joint peak power, limb and joint work, and muscle activity of the lower limb during …

de (code pays fourni par la source)

Time-Efficient Reinforcement Learning with Stochastic Stateful Policies

Firas Al-Hafez, Guoping Zhao, Jan Peters, Davide Tateo

Stateful policies play an important role in reinforcement learning, such as handling partially observable environments, enhancing robustness, or imposing an inductive bias directly into the policy structure. The conventional method for training stateful policies is Backpropagation Through Time (BPTT), which comes with …

LocoMuJoCo: A Comprehensive Imitation Learning Benchmark for Locomotion

Firas Al-Hafez, Guoping Zhao, Jan Peters, Davide Tateo

Imitation Learning (IL) holds great promise for enabling agile locomotion in embodied agents. However, many existing locomotion benchmarks primarily focus on simplified toy tasks, often failing to capture the complexity of real-world scenarios and steering research toward unrealistic domains. To advance research …

Exoskeleton developments at the Technical University of Darmstadt

Martin Grimmer, Maximilian Stasica, Guoping Zhao

The International Symposium on Technikpsychologie celebrates 100 years of interdisciplinary research of human-technology interaction at TU Darmstadt that dates back to the foundation of the institute for "Psychotechnik" in 1922. Since the introduction of the first functional computers in the 1940s, human-technology …

Improving Sample Efficiency of Example-Guided Deep Reinforcement Learning for Bipedal Walking

Rustam Galljamov, Guoping Zhao, Boris Belousov, André Seyfarth et autres

Reinforcement learning holds a great promise of enabling bipedal walking in humanoid robots. However, despite encouraging recent results, training still requires significant amounts of time and resources, precluding fast iteration cycles of the control development. Therefore, faster training methods are needed. In …

de (code pays fourni par la source)

Exploring surface electromyography (EMG) as a feedback variable for the human-in-the-loop optimization of lower limb wearable robotics

Martin Grimmer, Julian Zeiss, Florian Weigand, Guoping Zhao

Human-in-the-loop (HITL) optimization with metabolic cost feedback has been proposed to reduce walking effort with wearable robotics. This study investigates if lower limb surface electromyography (EMG) could be an alternative feedback variable to overcome time-intensive metabolic cost based exploration. For application, it …

de (code pays fourni par la source)