CAREER: Active Bayesian Inference for Collaborative Robot Mapping

人工感知技术使机器人系统能够利用感官数据了解自己的位置和周围环境，有助于在精心控制的制造环境之外实现机器人自动化。然而，目前的机器人系统对世界的感知仍然是被动的。与生物系统不同，机器人缺乏探索和缓解不确定性的好奇心机制，这对智能决策至关重要。这种能力在灾难响应、安全和监视以及环境监测中非常重要，在这些领域，快速获得环境中地形、建筑物和人类的态势感知是必要的。本项目开发的方法将影响自主机器人团队的测绘和主动传感算法的设计及其在上述应用中的使用。该学院早期职业发展（Career）项目研究开发了基本的机器人自主能力，这也将影响依赖自主机器人的其他领域。此外，该项目将开发一套开源教育材料，包括理论问题、项目、讲座和核心机器人算法的示范实现，统一在一个易于访问的模拟环境中。该平台将支持研究生的课程开发，以及本科生和K-12学生的外展和研究启动活动。研究议程将通过两项关键技术创新来实现。首先，该项目将正式定义一个主动贝叶斯推理问题，寻求传感系统的最优控制以实现最小的不确定性估计。利用问题结构的分布式近似动态规划方法，由建模概率、质量演化和估计性能的函数引起，将开发有效地表示和优化多机器人感知控制策略。其次，该项目将展示地面和空中机器人团队，使用主动贝叶斯推理技术，可以实现对未知环境的自主探索和主动高保真映射。这一目标将通过分布式和概率技术对在线密集隐式表面映射的新贡献得到支持，该技术允许多个机器人协同估计环境几何和语义，同时量化这些估计的不确定性，以允许规划信息行动。该项目由跨部门机器人基础研究项目支持，由工程（ENG）和计算机与信息科学与工程（CISE）联合管理和资助。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

Artificial perception techniques, allowing robot systems to know their location and surroundings using sensory data, have been instrumental for enabling robot automation outside of carefully controlled manufacturing settings. Current robot systems, however, remain passive in their perception of the world. Unlike biological systems, robots lack curiosity mechanisms for exploration and uncertainty mitigation, which are critical for intelligent decision making. Such capabilities are very important in disaster response, security and surveillance, and environmental monitoring, where it is necessary to quickly gain situational awareness of the terrain, buildings, and humans in the environment. The methods developed in this project will impact the design of mapping and active sensing algorithms for autonomous robot teams and their use in the aforementioned applications. This Faculty Early Career Development (CAREER) Program research develops fundamental robot autonomy capabilities that will also impact other domains relying on autonomous robots. In addition, the project will develop a suite of open-source education materials, including theoretical problems, projects, lectures, and exemplary implementations of core robotics algorithms, unified in an easily accessible simulation environment. This platform will support curriculum development for graduate students, as well as outreach and research-initiation activities for undergraduate and K-12 students.The research agenda will be achieved through two key technical innovations. First, the project will formally define an Active Bayesian Inference problem, seeking optimal control of sensing systems for minimum uncertainty estimation. Methods for distributed approximate dynamic programming that utilize the structure of the problem, induced by the functions modeling probability mass evolution and estimation performance, will be developed to efficiently represent and optimize multi-robot sensing control policies. Second, the project will demonstrate that a team of ground and aerial robots, using Active Bayesian Inference techniques, can achieve autonomous exploration and active high-fidelity mapping of an unknown environment. This objective will be supported by novel contributions to online dense implicit surface mapping in terms of distributed and probabilistic techniques that allow multiple robots to collaboratively estimate the environment geometry and semantics, while quantifying the uncertainty of these estimates to allow planning informative actions.This project is supported by the cross-directorate Foundational Research in Robotics program, jointly managed and funded by the Directorates for Engineering (ENG) and Computer and Information Science and Engineering (CISE).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.