Artificial Intelligence May Have Been The Key Differentiator Between The First Two And The Third Chandrayaan Mission

What sets apart the successful 23 August soft landing on the moon of  Chandrayaan-3’s Vikram lander and the subsequent investigations of the  Pragyan robotic rover, from Chandrayan-1 and 2, in 2009 and 2019? 

There is general agreement that what played a part in the precisely executed manoeuvres was the heightened use of artificial intelligence (AI) in key operations like guidance and control.

Yes, AI was around in 2019 too — but there is no denying that the technology has matured spectacularly in the last 3-4 years, in areas that could be directly deployed into the Chandrayaan programme.

These include areas like:

Computer Vision: Where AI enhances computers as they analyse digital images and classify objects, individuals, and actions.

Recent advancements have empowered robots like Pragyan to achieve near-human-level performance in tasks like object detection and collision avoidance. Such roving robotic vehicles can interpret large volumes of visual data in real time.

AI-Optimised Hardware:  Means specialised hardware architectures or components built and optimised to accelerate AI and machine learning applications. 

When AI is harnessed to enhance graphical processing units or central processing units, it can substantially improve the quality of the outcomes.

Once the Vikram lander went into its descent phase during the final  quarter-hour on 23 August, its ability to make a soft landing depended on navigation and control: a combination of its instantaneous location, speed, orientation.

The instruments that achieved this were velocimeters judging the speed, and altimeters monitoring the height.

Computers — enhanced by AI — made the vital micro corrections which ensured a smooth touch down.

Cameras on both orbiter and lander — the lander position detection camera and the lander hazard detection and avoidance camera — harnessed AI-enhanced computer vision to subtly change the lander’s orientation from horizontal to vertical, as it found the perfect landing spot. 

Indian Space Research Organisation (ISRO) chairman S Somnath, was quoted saying this was one of the most complicated manoeuvres of the descent.

Pragyan Deployed Critical Made-In-India Instruments

Once the Pragyan Rover started its autonomous journey on the moon’s surface, AI would have kicked in again to ensure that it could navigate safely, along the optimal path, mapping the lunar features it encountered, even as it logged a mass of critical data.

It deploys indigenously developed instruments, including a laser-induced breakdown spectroscope or LIBS and an alpha-particle induced x-ray spectroscope, the APIXS, to assess the composition of the elements on the lunar surface.

It goes without saying that AI was harnessed in the pre-flight stages when multiple simulations helped scientists iron out any kinks — and post flight, when terabytes of data need to be analysed and processed.

Some of the above insights came during the post-landing briefings by ISRO — and if they were fairly intuitive and somewhat general, that is because no space-tech player is about to share anything more than a broad acknowledgement of its proprietary processes and software.

But as the corny saying goes, the proof is in the pudding, and India’s demonstration of its abilities, only underlines the robustness and cutting-edge quality of its indigenous space technology, during a time when AI is increasingly proving to be an agni astra.