EAGER: Refinement and Evaluation of a Robotic Wheelchair System

ALS、四肢瘫痪和类似情况的全职轮椅使用者使用的界面是典型的单任务直接控制界面。例如，PI帮助的一位ALS患者通过头部和肩部激活的开关组合来驾驶轮椅，并通过头部运动控制计算机的帮助来说话。他不能一边开车一边交流，而正常人认为这是理所当然的。对我们大多数人来说，走路是一种无意识的活动；我们决定在房间里去哪里，然后忘记它。给电动轮椅增加自主性，可以让许多轮椅使用者恢复一些这种能力，从本质上讲，就是把轮椅变成一个机器人，可以利用现有的大量软件和技术来导航世界。这种轮椅的使用者可以在他/她的电脑上显示的地图上选择一个位置，然后忘记它，因为轮椅会自己开到那个位置，减少对照顾者的依赖，增加独立性。在这个探索性项目中，PI的目标是开发一个低成本、开源的电子包，它将以500美元的总硬件成本（有些武断）提供这种功能，因为医疗保险不会支付这样一个系统，所以潜在的用户必须自掏腰包，PI急于确保项目成果能够进入真正的轮椅使用者的生活。以这种方式对轮椅进行检测将有额外的好处（例如，知道轮椅在家里的位置可以让一个更简单、更快速的界面来控制家庭自动化）。由于该系统将有一个开放的软件API，它将为研究人员和开发人员提供一个共同的平台，为全职轮椅使用者提供辅助系统。为此，PI设计并实现了Permobil动力轮椅的原型电子包，并在从俄勒冈州和西南华盛顿ALS协会借来的Permobil M300动力轮椅上进行了测试。电子组件安装在椅子前部座位下方的定制金属板上，包括两个Hokuyo激光测距仪（每侧一个），一个小型计算机安装在椅体前面的脚踏板后面，以及定制的电子设备，从轮椅电池供电。连接到计算机的Arduino微控制器允许通过Permobil I/O模块将运动命令发送到轮椅。与ROS的集成允许系统构建环境地图，使用这些地图来定位轮椅，并利用广泛的自主导航能力。一旦轮椅定位在地图上，用户可以通过屏幕上基于地图的界面或谷歌眼镜为它提供一个目标点；然后，椅子可以使用标准的ROS导航系统，自动导航到那个点，避开障碍物。在杂乱的办公室环境中进行的初步试验令人鼓舞，虽然需要进一步改进URDF和系统的运动模型，并且需要通过在电子设备包中增加一个IMU来改进本地化。当前工作的智力价值在于三个方面：理解设想的电子封装背后的设计压力，如果它要部署在现实世界中的一系列电动轮椅上；重新设计和实现地图、定位和路径规划算法的设置；设计一个容错的系统，能够在没有训练有素的机器人专家干预的情况下，一次运行数月或数年。具体任务将包括：改进和推广硬件和电子设计；改进定位算法；提高轮椅运动质量；研究现有激光测距仪的替代方案；记录如何将所有东西整合到椅子上；并建立一些额外的工具包。

The interfaces used by full-time wheelchair users with ALS, quadriplegia, and similar conditions are typically single-tasking, direct control interfaces. For example, a person with ALS with whom the PI works drives his wheelchair through a combination of head- and shoulder-activated switches, and speaks with the assistance of a computer he controls with head movements. He cannot drive the chair and communicate at the same time, in the way that normally-abled people take for granted. For most of us, walking is an unconscious activity; we decide where to go in the room, and then forget about it. Adding autonomy to a powered wheelchair would allow many wheelchair users to recover some of this ability, by essentially turning the wheelchair into a robot that can take advantage of the vast body of existing software and techniques for navigating about the world. The user of such a wheelchair would select a location on a map displayed on his/her computer, and then forget about it as the wheelchair drives itself to that location, reducing the dependence on caregivers and increasing independence. The PI's goal in this exploratory project is to develop a low-cost, open-source electronics package that will provide this capability for a (somewhat arbitrary) total hardware cost of $500 since medical insurance will not pay for such a system so potential users must pay for it out-of-pocket and the PI is anxious to ensure that project outcomes will find their way into the lives of real wheelchair users. Instrumenting a wheelchair in this way will have additional benefits (e.g., knowing where the wheelchair is in the home could allow a simpler and faster interface to control home automation). And because the system will have an open software API, it will provide a common platform for researchers and developers working on assistive systems for full-time wheelchair users.To these ends, the PI has designed and implemented a prototype electronics package for Permobil powered wheelchairs, and has tested this on a Permobil M300 powered wheelchair on loan from the ALS Association of Oregon and Southwest Washington. The electronics package is mounted underneath the seat at the front of the chair on a custom-fabricated metal plate, and includes two Hokuyo laser range-finders (one on each side), a small computer mounted on the front of the chair body behind the footrest, and custom electronics to supply power from the wheelchair batteries. An Arduino microcontroller connected to the computer allows movement commands to be sent to the wheelchair through a Permobil I/O Module. Integration with ROS allows the system to build maps of the environment, to use these to localize the wheelchair, and to take advantage of extensive autonomous navigation abilities. Once the wheelchair is localized within a map, the user can provide it with a goal point either via an on-screen map-based interface or by means of a Google Glass; the chair can then autonomously navigate to that point avoiding obstacles as it goes, using the standard ROS navigation system. Preliminary trials in a cluttered office environment have been encouraging, although additional refinement of the URDF and kinematic models of the system are needed, and the localization needs to be improved by adding an IMU to the electronics package. The intellectual merit of the current work lies in three areas: understanding the design pressures behind the envisaged electronics package, if it is to be deployed on a range of powered wheelchairs in the real world; the redesign and implementation of mapping, localization, and path-planning algorithms for this setting; and designing a system that is fault-tolerant and capable of running for months and years at a time, without intervention by trained roboticists. Specific tasks will include: to improve and generalize the hardware and electronic design; to improve the localization algorithm; to improve the quality of wheelchair movement; to investigate replacements for the current laser range-finders; to document how to integrate everything onto a chair; and to build a number of additional kits.