Joint torques prediction of a robotic arm using neural networks

TL;DR

This paper explores neural network architectures for predicting joint torques in a robotic arm, demonstrating that a cascade neural network leveraging physical knowledge and hyperparameter optimization yields the best accuracy.

Contribution

It introduces a cascade neural network approach that incorporates physical knowledge and hyperparameter tuning for improved torque prediction in robotic arms.

Findings

Cascade NN outperforms other architectures in accuracy

Encoding physical knowledge improves model performance

Hyperparameter optimization enhances neural network effectiveness

Abstract

Accurate dynamic models are crucial for many robotic applications. Traditional approaches to deriving these models are based on the application of Lagrangian or Newtonian mechanics. Although these methods provide a good insight into the physical behaviour of the system, they rely on the exact knowledge of parameters such as inertia, friction and joint flexibility. In addition, the system is often affected by uncertain and nonlinear effects, such as saturation and dead zones, which can be difficult to model. A popular alternative is the application of Machine Learning (ML) techniques - e.g., Neural Networks (NNs) - in the context of a "black-box" methodology. This paper reports on our experience with this approach for a real-life 6 degrees of freedom (DoF) manipulator. Specifically, we considered several NN architectures: single NN, multiple NNs, and cascade NN. We compared the performance of the system by using different policies for selecting the NN hyperparameters. Our experiments reveal that the best accuracy and performance are obtained by a cascade NN, in which we encode our prior physical knowledge about the dependencies between joints, complemented by an appropriate optimisation of the hyperparameters.