Body-Swarm Interface (BoSI) : Controlling robotic swarms using human bio-signals

摘要

Traditionally robots are controlled using devices like joysticks, keyboards, mice and other
\nsimilar human computer interface (HCI) devices. Although this approach is effective and
\npractical for some cases, it is restrictive only to healthy individuals without disabilities,
\nand it also requires the user to master the device before its usage. It becomes complicated and non-intuitive when multiple robots need to be controlled simultaneously with these traditional devices, as in the case of Human Swarm Interfaces (HSI).
\n
\nThis work presents a novel concept of using human bio-signals to control swarms of
\nrobots. With this concept there are two major advantages: Firstly, it gives amputees and
\npeople with certain disabilities the ability to control robotic swarms, which has previously
\nnot been possible. Secondly, it also gives the user a more intuitive interface to control
\nswarms of robots by using gestures, thoughts, and eye movement.
\n
\nWe measure different bio-signals from the human body including Electroencephalography
\n(EEG), Electromyography (EMG), Electrooculography (EOG), using off the shelf
\nproducts. After minimal signal processing, we then decode the intended control action
\nusing machine learning techniques like Hidden Markov Models (HMM) and K-Nearest
\nNeighbors (K-NN). We employ formation controllers based on distance and displacement
\nto control the shape and motion of the robotic swarm. Comparison for ground truth for
\nthoughts and gesture classifications are done, and the resulting pipelines are evaluated with both simulations and hardware experiments with swarms of ground robots and aerial vehicles.