Robot System Identification Research Articles

Risk Identification of Robotic Systems through the Application of System-Theoretic Process Analysis

Autonomous multi-mobile robots are becoming increasingly prevalent in various applications, ranging from industrial automation to healthcare and logistics. While these robots offer enhanced efficiency and productivity, their operation introduces many safety challenges. In this paper, the application of System-Theoretic Process Analysis (STPA) is proposed as a systematic approach to identify and mitigate risks associated with the main features of autonomous multi-mobile robots. This approach is illustrated using a case study concerning a transportation task of hazardous products within a robotic analysis laboratory. Through a structured analysis process, STPA enables the identification of unsafe control actions, the establishment of safety constraints also the generation of safety requirements. The ultimate goal is to improve the autonomous attribute of mobile robots, so on ensuring their operational safety in high-risk environments.

Identification of robotic systems with hysteresis using Nonlinear AutoRegressive eXogenous input models

Identification of robotic systems with hysteresis is the main focus of this article. Nonlinear AutoRegressive eXogenous input models are proposed to describe the systems with hysteresis, with no limitation on the nonlinear characteristics. The article introduces an efficient approach to select model terms. This selection process is achieved using an orthogonal forward regression based on the leave-one-out cross-validation. A sampling rate reduction procedure is proposed to be incorporated into the term selection process. Two simulation examples corresponding to two typical hysteresis phenomena and one experimental example are finally presented to illustrate the applicability and effectiveness of the proposed approach.

Bayesian robot system identification with input and output noise

For complex robots such as humanoids, model-based control is highly beneficial for accurate tracking while keeping negative feedback gains low for compliance. However, in such multi degree-of-freedom lightweight systems, conventional identification of rigid body dynamics models using CAD data and actuator models is inaccurate due to unknown nonlinear robot dynamic effects. An alternative method is data-driven parameter estimation, but significant noise in measured and inferred variables affects it adversely. Moreover, standard estimation procedures may give physically inconsistent results due to unmodeled nonlinearities or insufficiently rich data. This paper addresses these problems, proposing a Bayesian system identification technique for linear or piecewise linear systems. Inspired by Factor Analysis regression, we develop a computationally efficient variational Bayesian regression algorithm that is robust to ill-conditioned data, automatically detects relevant features, and identifies input and output noise. We evaluate our approach on rigid body parameter estimation for various robotic systems, achieving an error of up to three times lower than other state-of-the-art machine learning methods.

Parameter identification of robotic systems with series elastic actuators

This paper presents a framework for identification of parameters of a robotic system with series elastic actuation. A model of the series elastic actuation is presented and a method for identification of the model parameters is proposed based on a regressor form of the system model. An algorithm is contributed for automatic derivation of the regressor form from the system equations of motion. The suggested framework is validated in experiments on a humanoid robot equipped with series elastic actuated joints.

Experimental Local Model Predictive Control: Trajectory Tracking and Cost Function Tuning for WMR Reactive Navigation

This paper presents local model predictive control techniques for WMR (wheeled mobile robot) reactive navigation. The use of dynamic models and experimental cost function factor adjustments are important issues of the above work. In the methodology presented dynamic experimental models are used. In order to do this, a set of dynamic models obtained from experimental robot system identification are used to predict the horizon of available coordinates. Local trajectory planning is a relevant idea of this work. Hence, when dynamic environments or obstacle avoidance policies are considered, the navigation path planning should be constrained to the robot neighbourhood. The testing and analysis of the experimental results of trajectory tracking are reported. In this context, the different parameter weight performances of the cost function are studied. In this way, different kinds of trajectories are tested by using factor tuning.

Parametric identification of robotic systems with stable time-varying Hopfield networks

In this work, a novel method for on-line identification of non-linear systems is proposed based upon the optimisation methodology with Hopfield neural networks. The original Hopfield model is adapted so that the weights of the resulting network are time-varying. A rigorous analytical study proves that, under mild assumptions, the estimations provided by the method converge to the actual parameter values in the case of constant parameters, or to a bounded neighbourhood of the parameters when these are time-varying. Time-varying parameters, often appearing in mechanical systems, are dealt with by the neural estimator in a more natural way than by least squares techniques. Both sudden and slow continuous variations are considered. Besides, in contrast to the gradient method, the neural estimator does not critically depend on the adjustment of the gain. The proposed method is applied to the identification of a robotic system with a flexible link. A reduced output prediction error and an accurate estimation of parameters are observed in simulation results.