S&AS: INT: Inference, Reasoning, and Learning for Robust Autonomous Driving

S

• 批准号: 1724282
• 负责人: Mark Campbell
• 金额: $ 139.86万
• 依托单位: Cornell University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-09-01 至 2023-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1724282&HistoricalAwards=false
• 关键词: S& INT; Inference; Reasoning; Learning

While research in autonomous driving has made great strides in recent years, fully autonomous cars are still a distant goal, primarily because of a lack of robustness. Current autonomous cars cannot drive on new roads, or roads that have changed substantially (such as after an earthquake), or when there is a GPS or data outage such as in parking garages, urban cities and tunnels. Importantly, humans are good at all of this: Humans can drive without detailed maps or high precision GPS/IMU sensors, and typically require only a small amount of sparse information for guidance, and their performance typically gets better over time through learning. Using the "intelligent" human driver as a guide, the planned research will develop algorithms that can perceive and make predictions about a scene in real time with measurable confidence, particularly as the scene is closer to the car. New robustness characteristics will be achieved through the ability to detect and overcome mistakes, both in the near term (real time) and long term (learning). The planned algorithms will be designed and validated in a way to enable an inherent robustness not currently available in autonomous driving, and fast adoption by the community. This project is aligned with NSF's Intelligent Physical Systems (IPS) because the algorithms will require cognizant and reflective capabilities in a knowledge-rich environment. Additionally, outputs of this project will impact robotics, machine learning and cyber-physical systems. Educationally, data logs will be disseminated to enable open ended student projects in the community, and undergrad and high school students will collaborate with the research team to integrate sensors, perform experiments and data collection, and disseminate data logs to the community. Led by researchers in Mechanical and Aerospace Engineering, and Computer Science at Cornell University, the goal of this research is to develop, integrate and validate theory and algorithms to enable robust and persistent autonomous driving. This project is aligned with NSF's Intelligent Physical Systems (IPS) because the algorithms will require cognizant and reflective capabilities in a knowledge-rich environment. The technical approach will develop a robust perceptual pipeline for detection, scene estimation, prediction, and anomaly/mistake detection and learning; integrate the algorithms into Cornell's autonomous car software framework and validate the components and system in a series of experimental scenarios to enable their faster adoption by the community. Key component level algorithms to be developed include anytime deep learning detectors with quantifiable performance; multiple hypothesis reasoning with memory attributes; generalized probabilistic anticipation algorithms to mimic a human's mental model of a dynamic scene; and anomaly/mistake detection coupled with online learning. Outcomes will include open source algorithms and data logs; publications, conferences, workshops; data logs for open ended projects in courses and across the community; and undergrad and high school education and diversity programs in the interdisciplinary area of autonomous driving.

虽然近年来自动驾驶的研究取得了长足的进步，但完全自动驾驶的汽车仍然是一个遥远的目标，主要是因为缺乏鲁棒性。目前的自动驾驶汽车无法在新建道路上行驶，或者在发生重大变化的道路上行驶（例如地震后），或者在停车场、城市和隧道等GPS或数据中断时行驶。重要的是，人类在这方面都很擅长：人类可以在没有详细地图或高精度GPS/IMU传感器的情况下驾驶，通常只需要少量稀疏的信息进行指导，并且他们的表现通常会随着时间的推移而变得更好。以“智能”人类驾驶员为指导，计划中的研究将开发算法，可以以可测量的信心在真实的时间内感知和预测场景，特别是当场景更接近汽车时。新的鲁棒性特征将通过在短期（真实的时间）和长期（学习）中检测和克服错误的能力来实现。计划中的算法将被设计和验证，以实现目前自动驾驶中不具备的固有鲁棒性，并被社区快速采用。该项目与NSF的智能物理系统（IPS）保持一致，因为算法将需要在知识丰富的环境中具有认知和反射能力。此外，该项目的产出将影响机器人、机器学习和网络物理系统。在教育方面，数据日志将被传播，以使开放式的学生项目在社区中，本科生和高中生将与研究团队合作，整合传感器，进行实验和数据收集，并向社区传播数据日志。由康奈尔大学机械和航空航天工程以及计算机科学的研究人员领导，这项研究的目标是开发，集成和验证理论和算法，以实现强大和持久的自动驾驶。该项目与NSF的智能物理系统（IPS）保持一致，因为算法将需要在知识丰富的环境中具有认知和反射能力。该技术方法将开发一个强大的感知管道，用于检测，场景估计，预测和异常/错误检测和学习;将算法集成到康奈尔大学的自动驾驶汽车软件框架中，并在一系列实验场景中验证组件和系统，以使其更快地被社区采用。待开发的关键组件级算法包括具有可量化性能的随时深度学习检测器;具有记忆属性的多假设推理;模仿人类对动态场景的心理模型的广义概率预测算法;以及与在线学习相结合的异常/错误检测。成果将包括开源算法和数据日志;出版物，会议，研讨会;课程和整个社区开放式项目的数据日志;以及自动驾驶跨学科领域的本科和高中教育和多样性计划。

项目成果

Priority Tracking of Pedestrians for Self-Driving Cars

自动驾驶汽车的行人优先追踪

• DOI: 10.1109/case49997.2022.9926614
• 发表时间: 2022
• 期刊: IEEE International Conference on Automation Science and Engineering (CASE
• 作者: Nino, Jose;Campbell, Mark
• 通讯作者: Campbell, Mark

Multi-Scale Dense Networks for Resource Efficient Image Classification

• 发表时间: 2017-03
• 作者: Gao Huang;Danlu Chen;Tianhong Li;Felix Wu;L. Maaten;Kilian Q. Weinberger

Hindsight is 20/20: Leveraging Past Traversals to Aid 3D Perception

• DOI: 10.48550/arxiv.2203.11405
• 发表时间: 2022-03
• 期刊: ArXiv
• 作者: Yurong You;Katie Luo;Xiangyu Chen;Junan Chen;Wei-Lun Chao;Wen Sun;Bharath Hariharan;Mark E. Campbell;Kilian Q. Weinberger

Unsupervised Domain Adaptation for Self-Driving from Past Traversal Features

根据过去的遍历特征进行自动驱动的无监督域适应

• DOI: 10.1109/iccvw60793.2023.00436
• 发表时间: 2023
• 期刊: IEEE/CVF International Conference on Computer Vision Workshops
• 作者: Zhang, Travis;Luo, Katie;Phoo, Cheng Perng;You, Yurong;Chao, Wei-Lun;Hariharan, Bharath;Campbell, Mark;Weinberger, Kilian Q.
• 通讯作者: Weinberger, Kilian Q.

Probabilistic Uncertainty Quantification of Prediction Models with Application to Visual Localization

• DOI: 10.1109/icra48891.2023.10160298
• 发表时间: 2023-05
• 期刊: 2023 IEEE International Conference on Robotics and Automation (ICRA)
• 作者: Junan Chen;Josephine Monica;Wei-Lun Chao;Mark E. Campbell