A user interface for assistive grasping

Abstract

Abstract-There has been considerable interest in producing grasping platforms using non-invasive, low bandwidth brain computer interfaces(BCIs). Most of this work focuses on low level control of simple hands. Using complex hands improves the versatility of a grasping platform at the cost of increasing its complexity. In order to control more complex hands with these low bandwidth signals, we need to use higher level abstractions. Here, we present a user interface which allows the user to combine the speed and convenience of offline preplanned grasps with the versatility of an online planner. This system incorporates a database of pre-planned grasps with the ability to refine these grasps using an online planner designed for arbitrarily complex hands. Only four commands are necessary to control the entire grasping pipeline, allowing us to use a low cost, noninvasive commercial BCI device to produce robust grasps that reflect user intent. We demonstrate the efficacy of this system with results from five subjects and present results using this system to grasp unknown objects.

Assistive grasping with an augmented reality user interface

“…In Weisz et al (2013), we described a BCI-enabled grasping platform, through which we outlined a general strategy for an online assistive grasping system, based on an earlier system, which we described in Weisz et al (2012). The grasping task can be decomposed into four subtasks: Target object identification and localization, generation of grasp plans, picking an optimal plan, and executing the plan on the robot.…”

“…The Emotiv Epoc comes with three built-in signal processing modalities designed to detect emotional affect, facial movement, and EEG evoked responses. Combining these classifiers, we were able to derive a training paradigm for detection of four facial gestures robustly (Weisz et al, 2013).…”

“…This paper describes an sEMG-driven assistive grasping platform integrating human-in-the-loop planning through an augmented reality interface. We present the iterative development process we have used to arrive at our final system, comparing different user interface paradigms and grasp planners presented in our previous papers addressing this problem (Weisz et al, 2012, 2013, 2014). Then we present new results from our final user validation study of our sEMG paradigm, which addresses grasping in clutter with both known and unknown objects.…”

A Novel EMG Interface for Individuals With Tetraplegia to Pilot Robot Hand Grasping

“…A robot hand was preferred to conventional grippers since it allows manipulators or humanoids to handle complex shaped parts or objects that were originally designed for humans, at the cost of more sophisticated mechanical designs and control strategies [18], [19]. Recently, robot hand usage has been extended to the design of prostheses for amputees, under the control of brain-computer interfaces [20], or EMG signals [21], [22], [23], [24]. However, to our knowledge, surface EMG signals (in contrast to neural signals [25], [26]) have never been used by tetraplegic individuals to pilot robot hands.…”

An integrated framework for humanoid embodiment with a BCI

“…Many assistive applications have been developed using a BCI [8]. For example, a complex gripper can be controlled via BCI with a specifically designed user interface to realize a grasp [9]. Vehicles, such as a wheelchair [10], have also been controlled with a BCI.…”