A self-orchestrating physics-discovering neural architecture for adaptive and fault-resilient robotic motion control via RPA and digital twins

Daksh Singla, G Logeswari, K Tamilarasi, J Deepika Roselind · 2026

Read A self-orchestrating physics-discovering neural architecture for adaptive and fault-resilient robotic motion control via RPA and digital twins by Daksh Singla, G Logeswari, K Tamilarasi, J Deepika Roselind (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/PMC13572557.txt.

Description

Daksh Singla, with three colleagues, presents a 2026 robot control system that learns the physics of its own motion while it works. Fixed models age fast when loads shift or parts wear, and hand tuning takes experts. The system aims to keep learning, check itself, and recover from faults with no human in the loop.

A physics-informed network carries the robot's known constraints and hunts unknown ones, such as changing friction, by symbolic regression. A digital twin, a full software copy, lets the system test ideas safely first. Process automation handles data intake, fault spotting, retraining, and rollout. On a robot arm that tracked paths and dodged obstacles under shifting loads, accuracy hit 98.4 percent. Energy use fell by 22.7 percent, and fault recovery ran 41.3 percent faster than standard methods.

Catalog record

CREATORDaksh Singla, G Logeswari, K Tamilarasi, J Deepika Roselind
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE77927
LICENSEhttps://creativecommons.org/licenses/by/4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/article/MED/PMC13572557

Browse the full library · About the Tower of Babel