Vandi Verma is a visionary researcher at NASA's Jet Propulsion Laboratory, specializing in AI for space exploration. In a captivating discussion, she reveals how AI transforms Mars missions, particularly the autonomous capabilities of the Perseverance Rover. Verma shares insights into the innovative techniques used for navigating the Martian landscape and the crucial role of human-robot interaction. She also reflects on her journey in robotics and dispels common misconceptions about AI, highlighting its potential in advancing exploration.
AI enables the Perseverance Rover to achieve 88% autonomy in navigating Mars, ensuring efficient exploration of uncharted terrain.
Human-defined criteria guide the rover's discovery process, while advanced AI algorithms enhance its ability to detect and prioritize novel features.
Deep dives
Generative AI in Space Exploration
Generative AI plays a crucial role in the functioning of robotic missions, particularly in space exploration efforts like those conducted by NASA's Jet Propulsion Laboratory. The Perseverance Rover utilizes AI to achieve an impressive 88% of its autonomy in driving, enabling it to navigate uncharted Martian terrain. This autonomous capability allows the rover to assess hazards and make driving decisions based on its own camera images, which is particularly vital since no human has seen the terrain prior to the rover's exploration. Such innovative use of AI facilitates efficient operation and increases the likelihood of discovering significant geological features during the mission.
Defining Interesting Discoveries
Determining what constitutes an 'interesting' discovery on Mars is a complex process governed by human input and data parameters. Scientists specify various criteria such as rock composition, size, and color, which are programmed into the rover to guide its exploration and sampling activities. Advanced AI algorithms help in 'novelty detection', allowing the rover to identify and prioritize areas of interest that have not been sampled yet. This interplay between human-defined criteria and machine learning enhances the quality of data collected, ultimately supporting the investigation of the possibility of ancient life on Mars.
Simulation and Risk Management
To prepare for the unique challenges of operating robots on Mars, NASA employs detailed simulation practices combined with a structured approach to risk management. Engineers create simulations that mimic Martian conditions to predict how rovers will behave in an environment that cannot be perfectly replicated on Earth. The careful design of these simulations, along with incremental testing of autonomous capabilities, allows for safe, efficient exploration while minimizing the risk of mission failure. This method parallels how organizations implement AI in other sectors, where gradual trust is built with technology through experience and measured risk-taking.
Today, we’re bringing you a special episode from our friends over at Me, Myself and AI hosted by Sam Ransbotham, who was our guest on the podcast earlier this year. Sam is talking to Vandi Verma from NASA's Jet Propulsion Laboratory about how AI is revolutionizing space exploration on Mars. Be sure to check out Me, Myself and AI on Apple podcasts, Spotify, or wherever you get your podcasts.
Get the Snipd podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered podcast player
Listen to all your favourite podcasts with AI-powered features
Discover highlights
Listen to the best highlights from the podcasts you love and dive into the full episode
Save any moment
Hear something you like? Tap your headphones to save it with AI-generated key takeaways
Share & Export
Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more
AI-powered podcast player
Listen to all your favourite podcasts with AI-powered features
Discover highlights
Listen to the best highlights from the podcasts you love and dive into the full episode