← Multimodal Sources 🕐 2 min read
Multimodal Sources

AI on Mars: NASA’s Vandi Verma

> 88% of the driving that we've done is autonomous. It's detecting the terrain and figuring out what's hazardous and navigating around obstacles.

Show: Me, Myself, and AI · Publisher: MIT Sloan Management Review + BCG · Host: Sam Ransbotham, Shervin Khodabandeh

Episode URL: https://sloanreview.mit.edu/audio/ai-on-mars-nasas-vandi-verma

Publish date: 2023-12-19
Duration: NAs
Default source credibility: HIGH — MIT SMR + BCG joint production. Named F500 CxOs on-record about production AI deployments. Academic/consulting co-brand keeps claims disciplined. Host has light BCG framing; guest metrics stay HIGH.

  • 88% of Perseverance rover’s driving on Mars is autonomous, navigating unknown terrain to collect samples.
  • AI helps prioritize interesting features for analysis, using parameters defined by scientists to detect novelty and characterize findings.
  • Simulations and digital twins are crucial for testing Mars rover capabilities on Earth, balancing risk and innovation.

Extracted quotes

# Credibility Speaker Org Timestamp Topic Quote
1 HIGH Vandi Verma (Deputy Manager for the Mobility and Robotics System) NASA’s Jet Propulsion Laboratory 02:56 01-ai-native-landscape 88% of the driving that we’ve done is autonomous. It’s detecting the terrain and figuring out what’s hazardous and navigating around obstacles.
2 HIGH Vandi Verma (Deputy Manager for the Mobility and Robotics System) NASA’s Jet Propulsion Laboratory 08:00 02-corporate-tools We have over 64,000 explicit parameters. These are saved in non-volatile memory. This does not even take into account the arguments to commands you can set.
3 HIGH Vandi Verma (Deputy Manager for the Mobility and Robotics System) NASA’s Jet Propulsion Laboratory 12:14 07-adoption-challenges We do it in stages. So we might actually have the autonomous navigation tell us what it would do, but not actually do the navigation. We would actually have the human direct a drive, as we call it, but we’re actually letting it shatter and say, let’s see what you would have done.

Per-quote detail

1. Vandi Verma — NASA’s Jet Propulsion Laboratory (02:56)

88% of the driving that we’ve done is autonomous. It’s detecting the terrain and figuring out what’s hazardous and navigating around obstacles.

  • Stat: 88% of driving is autonomous
  • Credibility: HIGH — Specific metric with denominator from named executive in unscripted interview.
  • Topic tag: 01-ai-native-landscape

2. Vandi Verma — NASA’s Jet Propulsion Laboratory (08:00)

We have over 64,000 explicit parameters. These are saved in non-volatile memory. This does not even take into account the arguments to commands you can set.

  • Stat: 64,000 explicit parameters
  • Credibility: HIGH — Specific metric with denominator from named executive in unscripted interview.
  • Topic tag: 02-corporate-tools

3. Vandi Verma — NASA’s Jet Propulsion Laboratory (12:14)

We do it in stages. So we might actually have the autonomous navigation tell us what it would do, but not actually do the navigation. We would actually have the human direct a drive, as we call it, but we’re actually letting it shatter and say, let’s see what you would have done.

  • Credibility: HIGH — Specific production deployment detail from named executive in unscripted interview.
  • Topic tag: 07-adoption-challenges

Extracted 2026-04-15T00:03:29 via scripts/podcast_mine.py (MLX mlx-community/Qwen2.5-32B-Instruct-4bit).