NASA’s Perseverance rover completed the first Mars drives planned autonomously by generative AI on Dec. 8 and Dec. 10, 2025, executed by JPL in collaboration with Anthropic using Claude models. The vision-language models analyzed HiRISE imagery and digital elevation maps to generate waypoints, and JPL’s digital twin verified over 500,000 telemetry variables before commands were sent. Perseverance drove 689 feet and 807 feet on those sols, demonstrating potential for kilometer-scale autonomous planning and reduced operator workload.
Key Points
- 1Generated waypoints planned Perseverance’s Dec. 8 and 10 drives using vision-language AI models.
- 2Enabled analysis of HiRISE imagery and elevation data to identify hazards and continuous paths.
- 3Allows meter-to-kilometer autonomous planning, reducing operator workload and increasing science return.
Scoring Rationale
High novelty and official NASA validation, with strong relevance to planetary robotics but limited immediate applicability to broader AI operations.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
