CHS: Small: Learning and Leveraging Conventions in Human-Robot Interaction

对于近100万患有肢体残疾的美国成年人来说，拿起一口食物或倒一杯水是一个巨大的挑战。安装在轮椅上的机械臂--以及其他物理辅助设备--有望增加用户的自主性，减少对照顾者的依赖，并提高生活质量。不幸的是，让这些机器人助手变得有用的灵巧也让人类很难控制它们。今天的用户必须在整个任务过程中远程操作他们的辅助机器人。例如，当用户控制辅助机器人进食时，他们需要仔细协调末端执行器的位置和方向，以将叉子移动到盘子上，将一小块食物叉起来，然后将食物引导回他们的嘴边。这些挑战通常是令人望而却步的：残疾人用户报告说，他们选择在进食时不利用他们的辅助机器人，因为相关的困难。该项目的关键观点是，通过学习和利用约定，可以更容易地控制高维机器人，使用户能够使用简单和低维的输入向机器人传达他们的意图、目标和计划。惯例定义了日常行为和这些行为所体现的潜在意义之间的关系。这个项目将从算法的角度推动机器人学的最新发展：i)开发新的算法，使人类和机器人之间通过重复交互形成学习约定，ii)利用这些约定为远程操作机器人开发更直观、一致和可控的接口，iii)共享自主算法，基于学习的约定混合自主操作，以及iv)扩展最先进的共享自主技术，随着时间的推移对约定产生积极影响。此外，拟议的共享自主和遥操作算法将通过人类主题研究进行广泛评估。该奖项反映了NSF的法定使命，通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

For almost one million American adults living with physical disabilities, picking up a bite of food or pouring a glass of water presents a significant challenge. Wheelchair-mounted robotic arms -- and other physically assistive devices -- hold the promise of increasing user autonomy, reducing reliance on caregivers, and improving quality of life. Unfortunately, the very dexterity that makes these robotic assistants useful also makes them hard for humans to control. Today's users must teleoperate their assistive robots throughout entire tasks. For instance, when users control an assistive robot for eating, they would need to carefully orchestrate the position and orientation of the end-effector to move a fork to the plate, spear a morsel of food, and then guide the food back towards their mouth. These challenges are often prohibitive: users living with disabilities have reported that they choose not to leverage their assistive robot when eating because of the associated difficulty. The key insight of this project is that controlling high-dimensional robots can become easier by learning and leveraging conventions, which enable users to convey their intentions, goals, and plans to the robot using simple and low-dimensional inputs.The goal of this project is to study convention formation for human-robot interaction. Conventions define a relationship between the everyday actions and the latent meanings that these actions embody. This project will advance the state-of-the-art of robotics from an algorithmic perspective: i) developing new algorithms that enable learning conventions developed between humans and robots through repeated interactions, ii) leveraging these conventions to develop more intuitive, consistent, and controllable interfaces for teleoperating robots with high degrees of freedom, iii) shared autonomy algorithms that blend autonomous actions based on the learned conventions, and iv) extending state-of-the-art shared autonomy techniques to positively influence conventions over time. In addition, the proposed shared autonomy and teleoperation algorithms will be extensively evaluated through human subject studies. This can advance the state of teleoperation in domestic robotics; in tasks such as feeding or cooking.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.