Skip to main content
To KTH's start page

EXHILO: Real-time exoskeleton control for human-in-the-loop optimization

The project goal is to develop a modular lower-limb exoskeleton prototype equipped with off-board actuation and a flexible digital control interface. The system enables Human-in-the-Loop (HILO) optimization, where assistance strategies are automatically tuned in real time to each user. This approach supports adaptive, personalized exoskeleton control and accelerates research into wearable robotics.

Background

Musculoskeletal disorders are a major cause of long-term disability, and exoskeleton technologies have the potential to improve mobility and reduce strain. However, adoption beyond research labs has been limited, in part due to difficulties in adapting devices to the needs of diverse users.

Human-in-the-Loop optimization (HILO) is a method in which control parameters of an exoskeleton are continuously adjusted based on real-time measurements of user performance (e.g., energy cost, kinematics, or subjective comfort). This makes it possible to personalize assistance dynamically, improving both user acceptance and functional outcomes. The mission of EXHILO is to demonstrate how HILO methods, combined with modular hardware, can make exoskeleton testing more flexible, reliable, and user-centered.

This project brings together expertise from the Promobilia MoveAbility Lab (biomechanics) and the Robot Design Lab (mechatronics). The collaboration bridges these two fields, enabling an integrated approach to both human-centered testing and robotic system development.

Our Contribution

The Robot Design Lab contributes with the design and integration of the modular system architecture, enabling off-board actuation and real-time control. In parallel, we investigate and implement Human-in-the-Loop algorithms, such as CMA-ES, to dynamically adapt torque profiles based on user performance. We also develop and demonstrate prototypes to validate the feasibility of personalized assistance strategies during walking experiments.

Sustainability Goals

With this project we aim to improve health and well-being in all genders, reduce inequalities and participation of marginalized populations (UN sustainable development goals 3, 5, 10).

Funded by

Digital Futures

Project Duration

2022-2024

Contact

Georgios Andrikopoulos
Georgios Andrikopoulos assistant professor
REMA: Redefining Mobility for Aging Adults
HARU: On the compliance, reliability and motion control of a tabletop robot
EXHILO 2: Advancing Real-time Exoskeleton Control for Human-in-the-Loop Optimization
AKI: A Child-Centered Social Robot Platform for Safe Interactions
EXHILO: Real-time exoskeleton control for human-in-the-loop optimization
IRIS: Novel Mechatronic Systems and Soft Robotics enabled by 4D Printing and Machine Learning
SocketSense
Excellence in production research (XPRES)
WILDCAT
FIRE - the Future of mItigating Rural firEs
PICTORIAL - Predictive Intelligent Control for Resistance Welding
SALIENCE4CAV
CAVeaT: Connected Automated Vehicles trialling and Trustworthiness
TADDO2: Trustworthy Automated Driving DevOps, continued
AD-EYE
TADDO: Trustworthy Automated Driving DevOps
Entice - Enablers for trustworthy, infrastructure supported, autonomous vehicles
StorAIge: Embedded storage elements on next MCU generation ready for AI on the edge
BOAUT - Boundaries Of AUTonomy
Susan's Ride on Campus 2030
WASP: AD-EYE – an Open Modular Testbed
HUBCAP
TRUSST-E
ADinSOS
CAMPUS 2030 – Enabling systemic solutions for smart roads
ATRIUM: ArchiTectural RefInement using Uncertainty Management
FED4SAE
HI2OT
InSecTT – Intelligent Secure Trustable Things
PRYSTINE
Rigorous Systems Engineering
SMP Tool