Brain-machine interfacing control of whole-body humanoid motion

Abstract

We propose to tackle in this paper the problem of controlling whole-body humanoid robot behavior through non-invasive brain-machine interfacing (BMI), motivated by the perspective of mapping human motor control strategies to human-like mechanical avatar. Our solution is based on the adequate reduction of the controllable dimensionality of a high-DOF humanoid motion in line with the state-of-the-art possibilities of non-invasive BMI technologies, leaving the complement subspace part of the motion to be planned and executed by an autonomous humanoid whole-body motion planning and control framework. The results are shown in full physics-based simulation of a 36-degree-of-freedom humanoid motion controlled by a user through EEG-extracted brain signals generated with motor imagery task.

Behavior-Based SSVEP Hierarchical Architecture for Telepresence Control of Humanoid Robot to Achieve Full-Body Movement

“…developed a P300-based adaptive model for controlling a humanoid robot, including an off-line training and an on-line execution [14]. Bouyarmane et al (2014) used motor imagery potentials to control the walking gait of a simulated humanoid 2379-8920 © 2016 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.…”

“…robot through waypoints in [15]. navigated a humanoid robot in an office environment with an obstacle and picked an object up via motion-onset visual evoked potentials [16].…”

Trial-and-error learning of repulsors for humanoid QP-based whole-body control

“…[30]). Modugno et al [31] exploited a black-box optimizer (CMA-ES [32]) to learn the temporal profiles of the task weights of a QP-based controller, using a simulated robot.…”

Adaptive whole-body manipulation in human-to-humanoid multi-contact motion retargeting

“…Examining the contact wrench set is also a good way to measure feasibility, and there has been some recent work in constructing a feasible region of CoM positions and accelerations based on this notion [27]. In the longer term, we envision the combination of a fully versatile human-tohumanoid loco-manipulation retargeting system with wholebody motor-imagery BCI control [28] to enhance the retargeting system with a feed-forward predictive "intention of motion" component.…”