Task level hierarchical system for BCI-enabled shared autonomy

  title={Task level hierarchical system for BCI-enabled shared autonomy},
  author={Iretiayo Akinola and Boyuan Chen and Jonathan Koss and Aalhad Patankar and Jacob Varley and Peter K. Allen},
  journal={2017 IEEE-RAS 17th International Conference on Humanoid Robotics (Humanoids)},
This paper describes a novel hierarchical system for shared control of a humanoid robot. Our framework uses a low-bandwidth Brain Computer Interface (BCI) to interpret electroencephalography (EEG) signals via Steady-State Visual Evoked Potentials (SSVEP). This BCI allows a user to reliably interact with the humanoid. Our system clearly delineates between autonomous robot operation and human-guided intervention and control. Our shared-control system leverages the ability of the robot to… 

Figures and Tables from this paper

Brain-robot Shared Control Based on Motor Imagery and Improved Bayes Filter*

To achieve better control effect at the interval between two instructions, the relationship with two steps of Bayes filter is redesigned, and the number of instructions used in single trial is reduced by 50%.

A dual-arm mobile robot system performing assistive tasks operated via P300-based brain computer interface

This paper presents the development of a robotic system aimed at assisting people with this kind of severe motion disabilities by providing a certain level of autonomy by integrating control and perception software modules developed in the robots and systems environment with the BCI2000 framework.

NAO Robot Walking Control System Based on Motor Imagery

A brain-computer interface system based on motor imagery, and uses it to control the movement of NAO robot to communicate with the computer or control external equipment.

Plug-and-play supervisory control using muscle and brain signals for real-time gesture and error detection

This paper presents continuous classification of left and right hand-gestures using muscle signals, time-locked classification of error-related potentials using brain signals, and a framework that combines these pipelines to detect and correct robot mistakes during multiple-choice tasks.

Error-related potential-based shared autonomy via deep recurrent reinforcement learning

The evaluation results confirmed that the shared autonomy via deep recurrent reinforcement learning is an effective way to deal with uncertain human feedback in a complex human–robot interaction task.

Review of Closed-Loop Brain–Machine Interface Systems From a Control Perspective

In recent years, brain–machine interface (BMI) technology has made great progress in controlling external devices and restoring motor function for people with disabilities. To better optimize BMI

Accelerated Robot Learning via Human Brain Signals

This work proposes a method that uses evaluative feedback obtained from human brain signals measured via scalp EEG to accelerate RL for robotic agents in sparse reward settings, and achieves a stable obstacle-avoidance policy with high success rate.

An Effective Model for Human Cognitive Performance within a Human-Robot Collaboration Framework

A novel time-variant human cognitive performance modeling approach for human-robot collaborative actions that can relate human cognitive workload and the task complexity to a utilization factor which is functionally correlated with the robot’s mistake probability.

Noninvasive Electroencephalography Equipment for Assistive, Adaptive, and Rehabilitative Brain–Computer Interfaces: A Systematic Literature Review

The findings of this review indicate that the implications of using BCIs for assistive, adaptive, and rehabilitative technologies are encouraging for people with severe motor disabilities and healthy people.

Control strategies for cleaning robots in domestic applications: A comprehensive review

This article aims to provide a general overview of robotic cleaning tasks based on different types of control methods using manipulator and suggest a description of the future directions of cleaning tasksbased on the evaluation of the control approaches.



An adaptive brain-computer interface for humanoid robot control

This paper explores the application of hierarchical BCIs to the task of controlling a PR2 humanoid robot and teaching it new skills, and presents the first demonstration of training a hierarchical BCI for a non-navigational task.

A Low-Cost EEG System-Based Hybrid Brain-Computer Interface for Humanoid Robot Navigation and Recognition

An approach that combines the P300 potential, the steady state visually evoked potential (SSVEP), and event related de-synchronization (ERD) to solve a complicated multi-task problem consisting of humanoid robot navigation and control along with object recognition using a low-cost BCI system is described.

Control of a humanoid robot by a noninvasive brain–computer interface in humans

It is shown that by leveraging advances in robotics, an interface based on EEG can be used to command a partially autonomous humanoid robot to perform complex tasks such as walking to specific locations and picking up desired objects.

Correcting robot mistakes in real time using EEG signals

The application of EEG-measured error-related potentials (ErrPs) to closed-loop robotic control and the potential for EEG-based feedback methods to facilitate seamless robotic control are explored, and the goal of real-time intuitive interaction is moved closer.

Control of a Wheelchair in an Indoor Environment Based on a Brain–Computer Interface and Automated Navigation

  • Rui ZhangYuanqing Li Z. Gu
  • Computer Science
    IEEE Transactions on Neural Systems and Rehabilitation Engineering
  • 2016
A brain-controlled intelligent wheelchair with the capability of automatic navigation and the mental burden of the user can be substantially alleviated.

EEG-Based Brain-Controlled Mobile Robots: A Survey

A comprehensive review of the complete systems, key techniques, and evaluation issues of brain-controlled mobile robots along with some insights into related future research and development issues is provided.

A policy-blending formalism for shared control

This work proposes an intuitive formalism that captures assistance as policy blending, illustrates how some of the existing techniques for shared control instantiate it, and provides a principled analysis of its main components: prediction of user intent and its arbitration with the user input.

An online hybrid brain-computer interface combining multiple physiological signals for webpage browse

  • Long ChenZhongpeng Wang Dong Ming
  • Computer Science
    2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
  • 2015
A serial hybrid BCI system which combined more than one brain-computer or human-machine interact paradigms to achieve the functions of typing letters, moving and clicking cursor, and switching among them for the purpose of browsing webpages was constructed.

High-speed spelling with a noninvasive brain–computer interface

This study presents an electroencephalogram-based BCI speller that can achieve information transfer rates (ITRs) up to 5.32 bits per second, the highest ITRs reported inBCI spellers using either noninvasive or invasive methods, and demonstrates that BCIs can provide a truly naturalistic high-speed communication channel using noninvasively recorded brain activities.

A neuro-based method for detecting context-dependent erroneous robot action

  • S. EhrlichG. Cheng
  • Computer Science, Psychology
    2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids)
  • 2016
This paper proposes and validate a neuro-based method to detect from the electronencephalo-gram (EEG) of a human interaction partner, the perception of inappropriate / unexpected / erroneous robot behavior and suggests that EEG-based ErrP detection can be used for quantitative evaluation and thus improvement of robot behavior.