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

对于近100万有身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重大的挑战。安装在轮椅上的机器人手臂-以及其他身体辅助设备-有望提高用户的自主性，减少对护理人员的依赖，并提高生活质量。不幸的是，使这些机器人助手有用的灵巧性也使人类难以控制它们。今天的用户必须在整个任务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吃饭时，他们需要仔细协调末端执行器的位置和方向，将叉子移动到盘子上，叉一口食物，然后将食物引导回他们的嘴里。这些挑战通常是令人望而却步的：残疾用户报告说，由于相关的困难，他们选择在吃饭时不使用辅助机器人。本项目的主要观点是，通过学习和利用约定，可以使控制高维机器人变得更容易，从而使用户能够使用简单的低维输入向机器人传达他们的意图、目标和计划。本项目的目标是研究人机交互的约定形成。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。该项目将从算法的角度推进最先进的机器人技术：i）开发新的算法，使得能够通过重复的交互来学习人类和机器人之间开发的约定，ii）利用这些约定来开发用于具有高自由度的遥控机器人的更直观、一致和可控的接口，iii）共享自治算法，其基于所学习的约定混合自治动作，以及iv）扩展最先进的共享自治技术以随着时间的推移积极地影响约定。此外，拟议的共享自主权和遥操作算法将通过人类受试者研究进行广泛评估。该奖项反映了NSF的法定使命，并通过使用基金会的智力价值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.