EDAN: An EMG-controlled Daily Assistant to Help People With Physical Disabilities

Abstract

Injuries, accidents, strokes, and other diseases can significantly degrade the capabilities to perform even the most simple activities in daily life. A large share of these cases involves neuromuscular diseases, which lead to severely reduced muscle function. However, even though affected people are no longer able to move their limbs, residual muscle function can still be existent. Previous work has shown that this residual muscular activity can suffice to apply an EMG-based user interface. In this paper, we introduce DLR's robotic wheelchair EDAN (EMG-controlled Daily Assistant), which is equipped with a torque-controlled, eight degree-of-freedom light-weight arm and a dexterous, five-fingered robotic hand. Using electromyography, muscular activity of the user is measured, processed and utilized to control both the wheelchair and the robotic manipulator. This EMG-based interface is enhanced with shared control functionality to allow for efficient and safe physical interaction with the environment.

Toward Seamless Transitions Between Shared Control and Supervised Autonomy in Robotic Assistance

“…2. In SCTs, a human operator controls the movements of the robot using either a 3D joystick or an sEMG-based interface [20]. Exploiting knowledge of the task and the objects in the world, the robot assists the user by mapping input commands to task-relevant robot motions.…”

“…Both EDAN and Justin use a Cartesian impedance controller for the LWR arms. EDAN also includes a whole-body controller that coordinates the motion of the wheelchair (2DoF) and the modified [20] arm (8DoF) to follow the target pose H t . More details on this approach are given in Iskandar et.…”

“…In the case of EDAN, it is either because the user explicitly introduced it on the tablet GUI, or because the robot inferred it. EDAN has an inference pipeline that uses a robot vision system and position heuristics [20]. An example of an inferred task is: if there is a mug on the table and the user is driving a filled bottle towards it, perhaps the user wants to start pouring some liquid.…”

“…All runs of the automaton start in Shared Control and switch to Supervised Autonomy after a button press at the start of the trial. The experiments on EDAN were conducted with an RGB-D-based perception pipeline for detecting and estimating the pose [20] of the bottle, the mug, and the drawer.…”

Detachable Robotic Grippers for Human-Robot Collaboration

“…Collaborative robots can also be used in assistive applications to help people with reduced mobility (Vogel et al, 2020). In this context, having a platform that allows the easy exchange of tools at the robot end-effector can be useful for people who lost an arm (e.g., amputees) or have reduced mobility in it (e.g., post-stroke patients), and thus should be able to attach/detach tools with a single hand.…”