Fabian JustChalmers University of Technology · Center for Bionics and Pain Research
Fabian Just
Ph.D. ETH Zurich
Prosthetic control, machine learning, deep learning, clinical studies
About
11
Publications
4,591
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
95
Citations
Citations since 2017
Introduction
Fabian Just is a postdoctoral research scientist in machine learning and control at the Institute of Bionics at Chalmers (Prof. Ortiz Catalan). At ETH Zurich, he developed as a Postdoc and Ph.D. student the fifth version of the arm rehabilitation robot 'ARMin' (hardware, sensors, modeling, controls). His focus is controls, robotics, EMG, deep learning, and reinforcement learning. He was awarded the 1st place best paper award at the AUTOMED (VDI/VDE) conference and won several other prizes.
Additional affiliations
May 2020 - October 2020
Position
- PostDoc Position
Description
- Leading the ARMin - arm robotics group at Balgrist Campus and ETH Zurich. Testing our therapist imitating robot (BridgeTherapy, see video) in clinical settings with healthy participants, therapists, and stroke patients. Writing grants applications and publishing our clinical and robotic results.
May 2015 - April 2020
Position
- PhD Student
Description
- I developed the fifth version of the upper limb rehabilitation robot ARMin with focus on exoskeleton controls, imitation learning, and physical human-robot interaction. At ETH Zurich, I am a lecturer for several courses in the area of rehabilitation engineering. We hold a patent for therapist imitating robot (BridgeTherapy, see video). 1st place best paper award at the AUTOMED conference 2018, at the Jiao Tong University Academic Forum, and at the neurorehabilitation symposium in Hertenstein.
September 2013 - April 2015
Position
- Lecture Assistant
Description
- Lecture Assistent for "Nonlinear Controls"
Education
May 2015 - December 2019
October 2013 - December 2014
August 2012 - October 2013
Publications
Publications (11)
Background: Arm weight compensation with rehabilitation robots for stroke patients has been successfully used to increase the active range of motion and reduce the effects of pathological muscle synergies. However, the differences in structure, performance, and control algorithms among the existing robotic platforms make it hard to effectively asse...
Undesired forces during human-robot interaction limit training effectiveness with rehabilitation robots. Thus, avoiding such undesired forces by improved mechanics, sensorics, kinematics, and controllers are the way to increase exoskeleton transparency.
In this paper, the arm therapy exoskeleton ARMin IV+ was used to compare the differences in tran...
The impact of arm rehabilitation robots increases with their usability. Hereby, usability can refer to many aspects of the robot’s functionalities in relation to interaction with the patient and/or the therapist. In the current case, the usability of robotic hand modules are in the focus. Especially for patients with spastic hand function, the desi...
Highly impaired stroke patients at early stages of recovery are unable to generate enough muscle force to lift the weight of their own arm. Accordingly, task-related training is strongly limited or even impossible. However, as soon as partial or full arm weight support is provided, patients are enabled to perform arm rehabilitation training again t...
Robot-assisted arm therapy is increasingly applied in neurorehabilitation. The reason for this development over the last decades was that robots relieve the therapist from hard physical work while the training intensity can be increased. Importantly, an increase in training intensity is closely linked to functional improvements of the patient. Howe...
Therapists have been conducting training sessions with
patients in rehabilitation for decades, but robot developers
have not set focus on usability and acceptance of rehabilitation
devices by the therapy staff [1], [2]. One important
factor for robot usability is robot transparency, i.e. the robot
does neither disturb the patient nor the therapist...
This paper considers a model predictive control (MPC) strategy for mitigating the effects of Parkinson tremors on a movement-sensing, joystick controlled battery powered wheelchair with regenerative braking to extend its range between charges. Regenerative braking transforms the wheelchair model into a (switched) hybrid system. The wheelchair is re...
Projects
Project (1)
ARMin 5.0, an arm rehabilitation robot specifically designed with intelligent control strategies to enhance the capabilities of therapists.
