S&AS:FND:Viewer-Centric Spatial Reasoning and Learning for Safe Autonomous Navigation

S

• 批准号: 1849333
• 负责人: Patricio Vela
• 金额: $ 47万
• 依托单位: Georgia Tech Research Corporation
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-02-15 至 2023-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1849333&HistoricalAwards=false
• 关键词: S& FND; Viewer; Centric; Spatial

Autonomous navigation has emerged as one of contemporary society's most promising technological advances. Robust, self-improving strategy for robot navigation will benefit several industries such as commercial and non-commercial transportation, large-scale infrastructure inspection, industrial warehousing, disaster response, and assistive robotics. The main challenge to robust navigation lies in developing the ability to navigate unstructured, dynamic environments for which there may be insufficient data collected for training machine learning methods, and for which model-based reasoning is too complex. A purely learning-based strategy fails to have operational guarantees (i.e., collision avoidance is not guaranteed). The research proposes a mixed method solution whereby physics-based reasoning and machine learning work together to resolve the unstructured navigation problem. The combined approach will lead to a cognizant and reflective navigation pipeline whose performance improves with time. A central claim of this project is that the learning module will act as an efficient multi-hypothesis generator for potential navigation decisions, for which options can be processed, scored, and confirmed by the physics-based component. The learning system will subsequently use these scores for online improvement. The net result will be mobile robots that are cognizant of their operation and adaptable to new information gained during task execution. The research goal of this proposal is to derive a safe autonomous navigation framework for general settings through the use of a viewer-centric processing paradigm capable of leveraging learning and model driven methods to overcome the limitations of entirely object-centric approaches to navigation. Appealing to Marr's framework for visual processing, the project investigates a viewer-centric approach to navigation. By more tightly linking perceptual and planning representations through the viewer-centric approach, the new approach leverages measurements obtained during navigation to provide online assessment for improving performance and generating knowledge regarding navigation through unknown scenes. The project investigates the effect of a viewer-centric model representation for use in local planning, as well as the connection of such representations to reflective, experiential machine learning for improved performance that leverage the model-based planning subcomponent. The research involves meeting the following objectives: 1) Confirming the robustness of a viewer-centric navigation framework combining model-based and deep learning-based approaches for safe navigation with cognizant and adaptive operation; 2) Demonstrating enhanced reasoning through scene-selective strategies that improve through experience; and 3) Extending the framework to dynamic scenes through learned models for the relative physics of motion, whereby moving objects are modeled in the viewer's frame of reference to detect dangerous relative motion profiles.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.

自主导航已经成为当代社会最有前途的技术进步之一。强大的、自我改进的机器人导航策略将使几个行业受益，如商业和非商业运输、大规模基础设施检查、工业仓储、灾难响应和辅助机器人。鲁棒导航的主要挑战在于开发导航非结构化、动态环境的能力，这些环境可能没有足够的数据用于训练机器学习方法，并且基于模型的推理过于复杂。纯粹的基于学习的策略没有操作保证（即不能保证避免碰撞）。该研究提出了一种混合方法解决方案，即基于物理的推理和机器学习共同解决非结构化导航问题。这两种方法的结合将产生一种认知和反射的导航管道，其性能随着时间的推移而提高。这个项目的核心主张是，学习模块将作为一个有效的多假设生成器，用于潜在的导航决策，其中的选项可以被基于物理的组件处理、评分和确认。学习系统随后将使用这些分数进行在线改进。最终的结果将是移动机器人能够识别自己的操作，并适应任务执行过程中获得的新信息。本提案的研究目标是通过使用以观众为中心的处理范式，利用学习和模型驱动的方法来克服完全以对象为中心的导航方法的局限性，为一般设置导出一个安全的自主导航框架。该项目借鉴Marr的视觉处理框架，研究了一种以观众为中心的导航方法。通过以观众为中心的方法更紧密地连接感知和规划表示，新方法利用导航过程中获得的测量数据提供在线评估，以提高性能并生成关于未知场景导航的知识。该项目研究了以查看器为中心的模型表示用于局部规划的效果，以及将这种表示与反思性、体验性机器学习联系起来，以利用基于模型的规划子组件提高性能。该研究包括以下目标：1)验证以观众为中心的导航框架的鲁棒性，该框架结合了基于模型和基于深度学习的安全导航方法，具有认知和自适应操作；2)通过场景选择策略展示通过经验改进的增强推理能力；3)通过学习到的运动相对物理模型，将框架扩展到动态场景中，在观看者的参照系中对运动物体进行建模，以检测危险的相对运动轮廓。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。

项目成果

AeriaLPiPS: A Local Planner for Aerial Vehicles with Geometric Collision Checking

AeriaLPiPS：具有几何碰撞检查功能的飞行器本地规划器

• DOI: 10.1109/icra48891.2023.10160852
• 发表时间: 2023
• 期刊: International Conference on Robotics and Automation
• 作者: Smith, Justin S.;Vela, Patricio
• 通讯作者: Vela, Patricio

Geometry of Radial Basis Neural Networks for Safety Biased Approximation of Unsafe Regions

• DOI: 10.23919/acc55779.2023.10156278
• 发表时间: 2022-10
• 期刊: 2023 American Control Conference (ACC)
• 作者: Ahmad Abuaish;Mohit Srinivasan;P. Vela

GPF-BG: A Hierarchical Vision-Based Planning Framework for Safe Quadrupedal Navigation

• DOI: 10.1109/icra48891.2023.10160804
• 发表时间: 2023-05
• 期刊: 2023 IEEE International Conference on Robotics and Automation (ICRA)
• 作者: Shiyu Feng;Ziyi Zhou;Justin S. Smith;M. Asselmeier;Ye Zhao;P. Vela

Safe Hierarchical Navigation in Crowded Dynamic Uncertain Environments

• DOI: 10.1109/cdc51059.2022.9992674
• 发表时间: 2022-12
• 期刊: 2022 IEEE 61st Conference on Decision and Control (CDC)
• 作者: Hongyi Chen;Shiyu Feng;Ye Zhao;Changliu Liu;P. Vela

egoTEB: Egocentric, Perception Space Navigation Using Timed-Elastic-Bands

egoTEB：使用定时弹性带的以自我为中心的感知空间导航

• DOI: 10.1109/icra40945.2020.9196721
• 发表时间: 2020
• 期刊: IEEE International Conference on Robotics and Automation
• 作者: Smith, Justin S.;Xu, Ruoyang;Vela, Patricio
• 通讯作者: Vela, Patricio