What is the optimal interface between a human and a machine?
In the Zero Pressure 播客, Helen Sharman与海军准将Michael Brasseur和Sameer Alam教授一起探索“人机合作”的概念。, how we manage the relationship between the human, 这台机器, and the interactions and interdependencies between them.
机器学习的概念在社会上变得越来越明显和有价值, 但了解如何优化人机界面以及它们如何协同工作是这项技术成功的关键.
So say Commodore Michael Brasseur and Professor Sameer Alam, 两名人工智能专家分别在无人海上应用和空中交通管制领域工作, in the latest episode of Imperial College London and Saab’s Zero Pressure podcast.
Available at your favourite channel:
Spotify - Google 播客s - 苹果播客
The role of maritime robotics
Zero Pressure’s host, UK astronaut Helen Sharman, 首先听迈克尔·布拉瑟讲述他作为美国海军新特遣部队59指挥官的角色. 该团队的目标是将无人系统和人工智能快速整合到海军第五舰队在阿拉伯湾的行动中. 这项技术最终有望用于反海盗和海上拦截行动.
布拉瑟尔准将告诉海伦，自主能力在减少人类操作员的负担方面具有很大的价值, 特别是在处理大量数据或在压力下进行多任务操作时. 然而, if humans are to trust machine algorithms, we need to be sure 这台机器 will do what we expect it to do.
“例如, 我们不希望我们的无人驾驶任务用机器侵犯别人的领海. 当潜在的对手试图破坏我们的通信或GPS时，我们需要了解机器的行为,他说.
“It’s a really difficult problem. 建立信任的唯一途径是在一个有争议的沟通环境中运作, by going through the paces, 在机器被设计用来做的地方做一些练习.”
最终, 布拉瑟尔准将认为，海上机器人的巨大价值之一是能够利用它们比载人解决方案更便宜的事实, such as more destroyers or cruisers, and therefore have more available for use.
他说:“在水上部署更多的传感器是有价值的，可以提高我们的海事意识。.
他在上图中描绘了一个人控制12或13个海上机器人的画面, on and below the water, with a supply of comprehensive data that builds up a pattern of life, so a machine can learn to determine when something is abnormal, highlighting it for the operator to take a closer look. 然而, 他补充说，他对未来的理想设想是人类始终参与其中, particularly for high-risk operations.
Machine learning for air traffic control
空中交通管理在接受机器学习研究方面比海上交通管理走得更远, 部分原因是不那么恶劣的物理环境和根深蒂固的自动化文化.
Professor Sameer Alam, 新加坡空中交通管理研究所副所长、南洋理工大学联合实验室联合主任, 有20年研究空中交通管理机器学习的经验吗, 在新加坡实验室领导着一个由20名研究科学家和7名博士生组成的团队.
For Professor Alam, the main focus areas include solving problems such as how 这台机器, 或人工智能代理, perceives its environment, 采取行动, whilst also evaluating what the repercussions of that action down the line. 和, 如何让机器收集到足够的人类行为数据，从而识别出既定的行为模式, upon which it can start basing its own decision-making.
“这使得算法非常强大，因为现在它们是随着时间的推移而进化的人类集体知识,他说.
Other research areas include Explainable AI, when 这台机器 not only advises you of a decision, but also advises you of the logic behind a decision. 和 does so in an understandable and thus trustworthy way.
The importance of the user interface
有趣的是, Brasseur准将和Alam教授都强调了界面技术在人类用户和人工智能代理之间建立信任的重要性.
In the air traffic control scenario, Alam points to augmented reality and virtual reality equipment, including trials with the Microsoft Hololens, where the controller can work from home, with no need to come to the control centre.
In the maritime case, 布拉瑟尔说，一艘无人水面舰艇的试航是由X-Box控制器控制的. 他说:“这是操作人员熟悉的界面，使过渡操作变得容易。.
改进界面技术和利用自主性的另一个重要好处是减少了决策者或操作员的认知负荷. “We’re in a period of sensor overload and the human brain can get overloaded, it gets fatigued, 而机器学习可以处理大量的信息并理解它们,” adds Commodore Brasseur.