We're sunsetting PodQuest on 2025-07-28. Thank you for your support!
Export Podcast Subscriptions
cover of episode AI on Mars: NASA’s Vandi Verma

AI on Mars: NASA’s Vandi Verma

2023/12/19
logo of podcast Me, Myself, and AI

Me, Myself, and AI

AI Deep Dive AI Chapters Transcript
People
V
Vandi Verma
Topics
Vandi Verma: 我是NASA喷气推进实验室(JPL)移动和机器人系统副经理,也是火星2020任务的首席工程师。我们的任务是利用机器人技术探索火星,这其中AI扮演着至关重要的角色。Perseverance火星探测器88%的驾驶都是自主完成的,AI系统负责图像处理、地形识别和障碍物规避。此外,AI还用于识别最值得研究的地点,例如选择SuperCam激光器照射的目标。在任务规划方面,AI也考虑了能源、温度等因素。定义‘有趣’的目标依赖于人类的输入,科学家会设置参数来指定感兴趣的目标特征。超级计算机被用来将科学家的粗略描述转化为探测器可以理解的参数。火星探测器有超过64000个参数需要调整,AI可以帮助找到最佳参数组合。火星探测任务容错率极低,任何操作都必须谨慎小心。在AI应用中,风险评估和容忍度至关重要。为了在火星探测中使用AI,JPL创建了模拟环境,包括软件模拟和硬件模拟,以测试和训练自主导航系统和人类操作员。在火星探测中,AI能力的部署是分阶段进行的,先进行模拟测试,再逐步增加自主性。人类操作员也需要经过训练才能操作火星探测器,JPL采用课堂培训和影子操作等方式进行培训。人类能够很好地从不同机器人和任务中提取经验,并应用于新的任务。改进用户界面有助于提高人类操作员的效率,但AI仍然受到技术和想象力的限制。在火星探测中,AI的应用会不断带来意想不到的结果,这需要人类保持开放的心态。模拟环境不可能完全复制现实,因此在设计AI系统时,需要留有足够的余地,避免过度约束。我对机器人和太空探索的兴趣始于研究生时期,我博士期间的研究方向与NASA的任务密切相关。 Sam Ransbotham & Sherwin Khodabandeh: 两位主持人与Vandi Verma就AI在火星探测中的应用、挑战以及风险管理等方面进行了深入探讨,并就AI的机遇、误解和未来发展方向提出了问题。

Deep Dive

Chapters
Vandi Verma introduces her role as the deputy manager for the mobility and robotics system at NASA's Jet Propulsion Laboratory and chief engineer for the Mars 2020 mission.

Shownotes Transcript

When Vandi Verma saw the Spirit and Opportunity rovers land on Mars while she was working toward a Ph.D. in robotics, it set her on a path toward working at NASA in space exploration., Perhaps unsurprisingly, today, as chief engineer for robotic operations at Nasa’s Jet Propulsion Laboratory (JPL), Vandi sees the biggest opportunities for artificial intelligence in robotics and automation.

She describes the ways in which the Mars rovers rely on AI, including the technology’s use in digital twin simulations that enable JPL scientists at to practice their driving skills before actually controlling the rovers on Mars. She also discusses how NASA’s use of AI — and its approach to risk — offer lessons for organizations that are looking to simulate real-world scenarios here on Earth. Read the episode transcript here).

Me, Myself, and AI is a collaborative podcast from MIT Sloan Management Review and Boston Consulting Group and is hosted by Sam Ransbotham and Shervin Khodabandeh. Our engineer is David Lishansky, and the coordinating producers are Allison Ryder and Sophie Rüdinger.

Stay in touch with us by joining our LinkedIn group, AI for Leaders at mitsmr.com/AIforLeaders) or by following Me, Myself, and AI on LinkedIn).

Guest bio:

Vandi Verma is a principal engineer and the deputy section manager for the Mobility & Robotics section at the NASA Jet Propulsion Laboratory. She also serves as chief engineer of robotic operations for the Mars 2020 Perseverance rover. She was previously the assistant section manager of the Mobility & Robotics section, the supervisor of the section staff group, and the supervisor of the Operable Robotics Group.

Verma works on new robotics capabilities, including R&D; mission design; prototyping; flight development, testing, and launch; and landing and surface operations. She has been engaged in robotic operations on Mars since 2008 with the Mars Exploration Rover mission's Spirit and Opportunity, Curiosity rover, Perseverance rover, and Ingenuity helicopter.

Before joining JPL, she led the NASA Ames Research Center team that developed PLEXIL (Plan Execution Interchange Language) for operating autonomous systems, as well as the development of technology that has been deployed on rovers and human spaceflight projects.

Verma earned a Ph.D. in robotics from Carnegie Mellon University in 2005.

We encourage you to rate and review our show. Your comments may be used in *Me, Myself, and AI *materials.