Trajectory tracking of SSMR using backstepping control with neural estimation for logistics applications

The control of Skid Steering mobile robots (SSMRs) in logistics applications is challenging due to their nonlinear dynamics, nonholonomic constraints, payload variations, and sensitivity to disturbances and wheel slip. These factors make accurate, fast, and robust trajectory tracking essential for ensuring safe and efficient operation in dynamic logistics environments. Additionally, this class of robots is known to be underactuated in nature which may limit the ability of classical controllers to ensure sufficient performance. To address the above-cited challenges, this work presents the development of a nested control system for trajectory tracking of an SSMR. The proposed architecture consists of an outer loop for kinematic posture control and an inner loop for robust control based on backstepping and a neural estimator. The central challenge addressed is the underactuated nature of the robot, which has three states but only two physical control inputs, preventing direct control of the lateral error. To address the unmodeled uncertainties in lateral friction, longitudinal resistive force, and opposition torque, which vary significantly depending on the terrain, a neural estimator based on radial basis function neural networks (RBF-NN) is integrated. This estimator is combined with a robust backstepping technique that uses a virtual control law to indirectly stabilize the lateral error through kinematic coupling with angular velocity. The practical stability of the nested system is rigorously demonstrated using Lyapunov theory, ensuring that the longitudinal, lateral, and angular tracking errors are Uniformly Ultimately Bounded (UUB). Simulation results demonstrate that the proposed adaptive neural robust controller achieves improved tracking accuracy and reduced error residuals compared to conventional feedback linearization and pure backstepping controllers within the evaluated operating scenarios. The robustness of the scheme is confirmed numerically under simulated external disturbances and parameter uncertainties.

Authors

Institutions

Publication Details

Journal
Scientific Reports
Published
2026-11-13
DOI
https://doi.org/10.1038/s41598-026-78031-1
Primary Topic
Control and Dynamics of Mobile Robots
Type
article
Field-Weighted Citation Impact
0.00

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Trajectory tracking of SSMR using backstepping control with neural estimation for logistics applications

Sahbi Boubaker, Khalid A. Alattas, Francisco Rossomando
3 links
Scientific Reports
Control and Dynamics of Mobile Robots
article

Trajectory tracking of SSMR using backstepping control with neural estimation for logistics applications

Sahbi Boubaker, Khalid A. Alattas, Francisco Rossomando
article en

Abstract

The control of Skid Steering mobile robots (SSMRs) in logistics applications is challenging due to their nonlinear dynamics, nonholonomic constraints, payload variations, and sensitivity to disturbances and wheel slip. These factors make accurate, fast, and robust trajectory tracking essential for ensuring safe and efficient operation in dynamic logistics environments. Additionally, this class of robots is known to be underactuated in nature which may limit the ability of classical controllers to ensure sufficient performance. To address the above-cited challenges, this work presents the development of a nested control system for trajectory tracking of an SSMR. The proposed architecture consists of an outer loop for kinematic posture control and an inner loop for robust control based on backstepping and a neural estimator. The central challenge addressed is the underactuated nature of the robot, which has three states but only two physical control inputs, preventing direct control of the lateral error. To address the unmodeled uncertainties in lateral friction, longitudinal resistive force, and opposition torque, which vary significantly depending on the terrain, a neural estimator based on radial basis function neural networks (RBF-NN) is integrated. This estimator is combined with a robust backstepping technique that uses a virtual control law to indirectly stabilize the lateral error through kinematic coupling with angular velocity. The practical stability of the nested system is rigorously demonstrated using Lyapunov theory, ensuring that the longitudinal, lateral, and angular tracking errors are Uniformly Ultimately Bounded (UUB). Simulation results demonstrate that the proposed adaptive neural robust controller achieves improved tracking accuracy and reduced error residuals compared to conventional feedback linearization and pure backstepping controllers within the evaluated operating scenarios. The robustness of the scheme is confirmed numerically under simulated external disturbances and parameter uncertainties.

Scientific Reports
Consejo Nacional de Investigaciones Científicas y Técnicas (AR), National University of San Juan (AR), University of Jeddah (SA)
University of Jeddah
Industry, innovation and infrastructure
Control and Dynamics of Mobile Robots
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon