NRI-Small: Contextually Grounded Collaborative Discourse for Mediating Shared Basis in Situated Human Robot Dialogue

在人机对话中，虽然人类伙伴和机器人共同存在于共享的环境中，但他们在感知和推理环境方面的能力完全不匹配。他们对共享世界的知识和表征截然不同。此外，共享环境充满了不确定性和突发事件。人类和机器人在处理和应对这些不确定性方面可能具有不同的能力。所有这些都导致人类和机器人之间的感知基础失调，从而危及他们的协作活动和任务性能。为了使位于人类机器人对话，一个关键组成部分是开发技术，将支持调解有效的对话和任务完成的共享感知基础。这个国家机器人计划项目的目标是开发一个新的框架，将高级语言和对话处理与低级传感和控制系统紧密集成，并根据上下文建立协作话语，以调解共享的感知基础。通过捕获接地的符号表示以及机器人系统的内部配置的连续表示和从不断变化的环境中感测到的连续信息，该框架允许机器人在不中断正在进行的任务的情况下迅速修改其执行。它进一步使人类和机器人之间的协作，以调解共享的感知基础，并支持在一个高度动态的环境中进行有效的交互。这个项目将提供洞察力，人类和机器人之间的错位感知基础应如何通过协作过程进行调解，以及如何将这样的过程整合，以产生智能和协作的机器人行为。预期的结果将有利于许多应用，如制造，服务，辅助技术，搜索和救援。

In human robot dialogue, although human partners and robots are co-present in a shared environment, they have completely mismatched capabilities in perceiving and reasoning about the environment. Their knowledge and representations of the shared world are drastically different. In addition, the shared environment is full of uncertainties and unexpected events. Humans and robots may have different capabilities in attending and responding to these uncertainties. All of these contribute to a misaligned perceptual basis between a human and a robot, which jeopardizes their collaborative activities and task performance. To enable situated human robot dialogue, a critical component is to develop techniques that will support mediating the shared perceptual basis for effective conversation and task completion. The objective of this National Robotics Initiative project is to develop a novel framework that tightly integrates high level language and dialogue processing with low level sensing and control systems and contextually grounds the collaborative discourse to mediate shared perceptual basis. By capturing grounded symbolic representations as well as continuous representations of the internal configuration of a robotic system and continuous information sensed from the changing environment, the framework allows the robot to promptly modify its execution without interrupting the on-going tasks. It further enables collaborations between humans and robots to mediate a shared perceptual basis and support efficient interaction in a highly dynamic environment.This project will provide insight as to how the misaligned perceptual basis between a human and a robot should be mediated through a collaborative process and how such a process should be integrated to produce intelligent and collaborative robot behaviors. The expected results will benefit many applications such as manufacturing, service, assistive technology, and search and rescue.