Trusted AI on Mars -- Steve Chien
In October 2023, the Onboard Planner (OBP) took control of the Perseverance rover on Mars, over 200 million miles from Earth. As of 29th January 2025, OBP has operated for 429 Martian days (sols) and has: executed over 7800 activities requested by scientists and engineers, driven over 12 kilometers, acquired over 70,000 images, and collected 4 rock core samples. In contrast to the traditional form of operations, where operators provide a rigid set of instructions for the rover, with OBP Perseverance has replanned over 7000 times (an average of 16 times each sol) to stay responsive in a dynamic Martian environment where things don't always go as expected. This flexibility allows the mission to manage resources such as energy more efficiently and therefore accomplish more science.
We first describe the challenges in designing a planner to operate onboard the Perseverance Rover on Mars: (a) Perseverance has a 133 MHz Rad750 processor, about 50x less computation than a modern cell phone, and must share this computer with scores of other critical software processes; (b) the Onboard Planner must manage complex thermal and energy constraints; (c) the planner behavior must be understandable by rover operations experts, not AI trained staff.
We then discuss the approach to ensuring that an AI system, specifically the Onboard Planner, would (1) achieve mission objectives; and critically (2) protect the rover, a multi-billion dollar one of a kind asset. We describe the "whole lifecycle" approach to developing trusted autonomy software for M2020, spanning: conception, design, analysis, prototyping, and testing. We then describe the incremental rollout and training to smooth the transition to operations with increased onboard autonomy. Next we discuss how the OBP software has performed. Finally, we describe the even greater challenges of autonomy in future missions to hunt for life beyond Earth.
For further information on the M2020 Onboard Planner see: https://ai.jpl.nasa.gov/public/projects/m2020-scheduler/
Bio (https://ai.jpl.nasa.gov/public/people/chien/)
Steve Chien is a Technical Fellow in Artificial Intelligence and Co-head of the Artificial Intelligence Group (https://ai.jpl.nasa.gov/) at the Jet Propulsion Laboratory, California Institute of Technology. He has spent decades deploying AI/Autonomy to numerous space missions including: Earth Observing One, Sensorweb, ESA's Rosetta Orbiter, and M2020. He has been awarded four NASA Medals in 1997, 2000, 2007, and 2015 for development and deployment of AI technologies for space missions. He has supported numerous US government bodies including the Defense Science Board and the Air Force Scientific Advisory Board. He was appointed by Congress to the National Security Commission on Artificial Intelligence (2018-2021). He currently serves on the Army Science Board and as an Advisor to the Senate Defense Modernization Caucus.
The Balman Project: Steering Into the Wind -- Marta Lostao and François Vacher
After 50 years of operating stratospheric balloons, CNES is taking on the exciting challenge of achieving precise altitude control for these vehicles. The BALMAN project has been introduced to significantly broaden the potential applications of stratospheric balloons, which have traditionally been used for scientific research. Thanks to advancements in digital technologies and AI, these control algorithms can now be executed quickly, making them fully compatible with real-time operations. Following the remarkable success of its first flight in 2024, BALMAN invites you to join us in October 2025 in French Guiana, where the project will showcase its altitude maneuvering capabilities.
For more details about the Balman Project see :
https://cnes.fr/en/projects/ballons
https://cnes.fr/actualites/succes-premier-vol-dessai-ballon-manoeuvrant-balman
https://www.hemeria-group.com/en/product/balman-maneuvering-stratospheric-balloon/
Francois Vacher holds a PhD in Physics (2007). Since then, he has held various positions at the French Space Agency (CNES), including quality manager, standardization specialist, and electrical architect, primarily working on low Earth orbit satellites. For the past four years, he has been working as the project leader for the BALMAN project.
Marta Lostao is an aerospace engineer since 2013, with a master's degree in control and programming. Since 2020, she has been working as a flight physics expert at CNES, for the stratospheric balloon department. For BALMAN, she is the flight manager, being responsible for software development and flight physics during operations.