Current research on Brain-Computer Interface (BCI) controllers has expanded the opportunities of robotic applications within the biomechanical field. With the implementation of a real-time BCI controller, researchers have developed smart prosthetics, semi-autonomous wheelchairs, and collaborative robots for human interactions, allowing patients with neuromuscular disabilities the freedom to interact with the world. These advances have been made possible through the ease of non-invasive procedures for recording and processing electroencephalography (EEG) signals from the human scalp. However, EEG based BCI controllers are limited in their ability to accurately process real-time signals and convert them into input for a system. This research focuses on the development of a hybrid-BCI controller for a semi-autonomous three-wheeled omnidirectional robot capable of processing accurate real-time commands. EEG scans are recorded utilizing a fourteen-electrode channel cap provided by Easycap utilizing modified Emotiv Epoc hardware. Signals are recorded and processed by a program called OpenViBE in which users respond to different stimulus events. A MATLAB plugin, called BCILAB, is used to clean and process the data. This data is used to train the hybrid-BCI controller to be capable of differentiating between hand and foot motor imagery (MI) as well as jaw electromyography (EMG) signals. Once identified, the controller converts the signal into input commands of {forward, backward, left, right, rotate, stop}, which are published over LabStreamingLayer (LSL) to the robot. To date, omnidirectional mobile robots are popularly employed for their holonomic abilities, meaning they have three degrees of freedom (DoF) and are capable of traversing through its environment in any orientation. As such, a holonomic robot is proposed. The system is equipped with the Intel RealSense Depth Camera D435, as well as Lidar sensors to build a full map of the robot's surroundings. Robot operations are completed on the NVIDIA Jetson Xavier which runs the Robot Operating System (ROS). ROS manages all aspects of robot operations, called nodes. This includes receiving and translating BCI inputs, reading all sensor data, computing a trajectory and navigating the robot along the trajectory. Prototyping and developmental work was performed by creating a model of the robot in the Unified Robot Description Format (URDF) which can be run in Gazebo, a simulation software with a realistic physics model. The design of the system controller was tested in this simulated environment for both path planning and obstacle avoidance as well as receiving inputs from the BCI controller. The robot was able complete testing tasks and achieve goals with less than 10% error on average, often experiencing no more than 2% error when considering built in tolerance thresholds

The recent advent of consumer grade Brain-Computer Interfaces (BCI) provides a new revolutionary and accessible way to control computers. BCI translate cognitive electroencephalography (EEG) signals into computer or robotic commands using specially built headsets. Capable of enhancing traditional interfaces that require interaction with a keyboard, mouse or touchscreen, BCI systems present tremendous opportunities to benefit various fields. Movement restricted users can especially benefit from these interfaces. In this thesis, we present a new way to interface a consumer-grade BCI solution to a mobile robot. A Red-Green-Blue-Depth (RGBD) camera is used to enhance the navigation of the robot with cognitive thoughts as commands. We introduce an interface presenting 3 different methods of robot-control: 1) a fully manual mode, where a cognitive signal is interpreted as a command, 2) a control-flow manual mode, reducing the likelihood of false-positive commands and 3) an automatic mode assisted by a remote RGBD camera. We study the application of this work by navigating the mobile robot on a planar surface using the different control methods while measuring the accuracy and usability of the system. Finally, we assess the newly designed interface's role in the design of future generation of BCI solutions.

This book discusses the basic requirements and constraints in building a brain–computer interaction system. These include the technical requirements for building the signal processing module and the acquisition module. The major aspects to be considered when designing a signal acquisition module for a brain–computer interaction system are the human brain, types and applications of brain–computer systems, and the basics of EEG (electroencephalogram) recording. The book also compares the algorithms that have been and that can be used to design the signal processing module of brain–computer interfaces, and describes the various EEG-acquisition devices available and compares their features and inadequacies. Further, it examines in detail the use of Emotiv EPOC (an EEG acquisition module developed by Emotiv) to build a complete brain–computer interaction system for driving robots using a neural network classification module.

This Research Topic presents bio-inspired and neurological insights for the development of intelligent robotic control algorithms. This aims to bridge the inter-disciplinary gaps between neuroscience and robotics to accelerate the pace of research and development.

The ability to direct a robot using only human thoughts could provide a powerful mechanism for human-robot interaction with a wide range of potential applications including medical robotics, search-and-rescue operations, and industrial manufacturing. Brain-computer interfaces (BCIs) are systems that allow the user to control a computer with only their thoughts, providing a promising research area for new methods of robotic control. They could be used to control the navigation of a robotic wheelchair, an assistive or telepresence robot that performs errands, or even the movement of a prosthetic limb. In this work I present the design and evaluation of the first BCI to use four imagined movements recorded via functional near-infrared spectroscopy (fNIRS) to control both a virtual and a physical robot. The BCI is used to navigate the robot to a goal location in a room, a prototype and initial step towards remote control of a telepresence or assistive robot. Four imagined movement tasks (tapping of the left hand, right hand, left foot, and right foot) are mapped to high-level commands (turn left, turn right, walk forwards, walk backwards) to direct the robot. The ability to reliably distinguish multiple mental tasks is essential for use in a practical BCI. In an offline analysis I compare the activation patterns generated during both motor imagery and motor execution (actual movement). This is the first analysis of the activation patterns recorded via fNIRS separately for left and right foot motor imagery tasks. Signal processing, feature extraction, and machine learning methods are integral parts of BCI design. In an additional offline analysis I compare classification results using eight methods of signal preprocessing that have been suggested for use in fNIRS BCIs. I also provide comparisons of two commonly-used classifiers in BCIs as well as feed-forward and convolutional neural networks. Additionally I present the results of a five-class classification task, adding a resting state to the four motor imagery tasks, which could potentially increase the number of inputs available to the BCI.

Neuro-robotics is one of the most multidisciplinary fields of the last decades, fusing information and knowledge from neuroscience, engineering and computer science. This book focuses on the results from the strategic alliance between Neuroscience and Robotics that help the scientific community to better understand the brain as well as design robotic devices and algorithms for interfacing humans and robots. The first part of the book introduces the idea of neuro-robotics, by presenting state-of-the-art bio-inspired devices. The second part of the book focuses on human-machine interfaces for performance augmentation, which can seen as augmentation of abilities of healthy subjects or assistance in case of the mobility impaired. The third part of the book focuses on the inverse problem, i.e. how we can use robotic devices that physically interact with the human body, in order (a) to understand human motor control and (b) to provide therapy to neurologically impaired people or people with disabilities.