Enhanced Autonomous Navigation on the Perseverance Mars Rover
Olivier Toupet, Masahiro Ono, Tyler Del Sesto, Mark Maimone, Michael McHenry
AI summary
Problem
Previous Mars rovers relied heavily on human-directed driving because their autonomous navigation was too slow and overly conservative to safely navigate high rock density and complex terrain within strict single-core CPU limits.
Approach
ENav replaces conservative disk-based hazard avoidance with a precise wheel-based collision checker and a two-stage path-selection algorithm, optimized alongside FPGA-accelerated vision processing to enable fast, safe thinking-while-driving on limited hardware.
Key results
- Increased average daily driving distance by an order of magnitude over predecessors
- Enabled ~90% of Perseverance’s 32.1 km traverse to be driven autonomously
- Achieved ~92 m/h average autonomous driving speed in complex terrain
- Set new autonomous driving distance records on Mars (e.g., 347.7 m on sol 753)
Why it matters
Demonstrates how algorithmic efficiency and targeted hardware acceleration can overcome extreme computational constraints for safe, high-speed autonomous exploration in harsh extraterrestrial environments.
Abstract
This article presents Enhanced Autonomous Navigation (ENav), the autonomous driving algorithm of NASA’s Mars rover Perseverance. A unique challenge for the autonomous driving of Perse- verance is to meet strict safety and performance requirements in a highly uncertain environment with only a single-core CPU with extremely limited computing resources. ENav overcame this challenge with a novel two-stage path-selection approach that balances the path optimality and computational efficiency, combined with a unique collision checking algorithm that conservatively approximates computationally expensive kinematic settling. In addition, ENav provides robustness against slip by expanding the bounding boxes for wheels used by the collision check. These new features, together with field programmable gate array (FPGA)-accelerated vision processing, enabled Perseverance to autonomously drive on substantially more rock-dense terrains and increased the average daily driving distance by an order of magnitude compared to its predecessors, the Curiosity, Spirit, and Opportunity rovers. Perseverance has set several new records for autonomous driving on Mars, breaking those previously held by the Opportunity rover. As of the 1312th Martian day since landing, or October 28, 2024 on the Earth calendar, ∼90% of the 32.1 km of driving has used ENav to evaluate the terrain. This article provides detailed documentation of the ENav algorithm, as well as its implementation, testing, deployment, and driving results on Mars.