Joint torques prediction of a robotic arm using neural networks

TL;DR

Experiments reveal that the best accuracy and performance are obtained by a cascade NN, in which the prior physical knowledge about the dependencies between joints is encoded, complemented by an appropriate optimisation of the hyperparameters.

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.

Figures (4)

• Figure 1: Example of feedforward neural network architecture
• Figure 3: Comau Racer-5-0.80 robot WinNT
• Figure 4: Actual and predicted torque values using a single NN after scaling
• Figure 5: Train and test average MSE using a single NN after scaling