Artificial Intelligence for Future Rover Missions

by Paul Gilster on August 16, 2004

NASA’s Spirit and Opportunity rovers have given us remarkable views of Mars, but the next generation of such vehicles will need greater onboard intelligence. And as we move ever farther away from the Earth, our systems will eventually need to become capable of a great degree of autonomy. Imagine an Alpha Centauri probe 4.3 light years away as it experiences a malfunction, or discovers a new target in Centauri space that needs investigation. There will be no way to wait 8.6 years for a round-trip signal to Earth, so autonomy and AI are crucial for robotic exploration. A recent story in SpaceDaily talks about NASA’s work at its Ames Research Center that focuses on improving what our rovers can currently do. An interesting quote from NASA’s Kanna Rajan: “Part of the problem is we are not closing the loop on board the rover. Signals from the rover have to go to Earth for a human with his/her cognitive capacity to deliberate on the information in the signal and make a decision. Based on that decision, a signal goes back to Mars to instruct the rover to take pictures or do other work.” NASA hopes to remedy this time-consuming situation with a new AI-based agent software architecture called Intelligent Deployable Execution Agents, or IDEA.