Spatial Knowledge Reasoning and Robotic Assembly in the Presence of Uncertainties

这是一个为期三年的IRI-9210423项目的第一年资助。该项目旨在为能够基于不完善的感官数据对机器人环境进行推理的自动系统做出贡献，并恢复由内在和不可避免的系统不确定性引起的机器人运动错误。具体而言，该项目研究如何在存在传感和建模不确定性的情况下获得关于物体空间状态的足够准确的信息，并根据所涉及部件的空间状态制定实用的自动装配运动策略。该项目特别关注在存在不确定性的情况下，通过结合位置/方向传感、视觉传感和力/力矩传感，自动识别（机械手）握住的部件与环境之间的意外碰撞/接触，并根据获得的接触信息自动生成运动计划，作为补救计划。从无意的碰撞/接触中引导零件达到预期目标。该项目期望实现一个原型系统，该系统能够在存在不确定因素的情况下自动识别接触者并生成基于接触者的计划，以及适当执行这些计划。//

This is the first year funding of a three continuing award IRI-9210423. This project seeks to contribute to automatic systems capable of reasoning about a robotic environment based on imperfect sensory data and recovering errors of robot motions caused by intrinsic and inevitable system uncertainties. Specifically, the project studies how to acquire sufficiently accurate information about the spatial state of an object in the presence of sensing and modeling uncertainties and develops practical strategies for automatic assembly motions based on the spatial states of the parts involved. The project particularly focuses on, in the presence of uncertainties, the automatic recognition of unintended collision/contacts between a held part (by a manipulator) and the environment by combining position/orientation sensing, vision sensing, and force/moment sensing, and the automatic generation of motion plans based on the obtained contact information, as remedy plans, to lead the part to its intended goal from the unintended collision/contact. The project expects to result in the implementation of a prototype system capable of such automatic recognition of contacts and generation of contact-based plans, as well as proper execution of the plans, all in the presence of uncertainties. //