Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Anti-Slip AI-Driven Model-Free Control with Global Exponential Stability in Skid-Steering Robots

Mehdi Heydari Shahna, Pauli Mustalahti, Jouni Mattila

TL;DR

This work tackles the challenge of wheel slippage in skid-steering heavy-duty robots by introducing a model-free neural network based tracking framework (NN-RMFC). The core idea is to approximate unknown wheel dynamics with radial basis function neural networks and to adapt their weights online through a novel adaptive law, enabling robust tracking of commanded velocities despite slip disturbances. A rigorous stability proof establishes global exponential stability with convergence rate $\rho$, ensuring uniform exponential convergence from arbitrary initial conditions (Theorem 1). The approach is validated both in simulation and on a real 4,836 kg SSHDR operating on slippery snowy terrain, where NN-RMFC outperforms competing model-free methods in steady-state error and settling time, demonstrating practical potential for reliable autonomous navigation in rough off-road environments.

Abstract

Undesired lateral and longitudinal wheel slippage can disrupt a mobile robot's heading angle, traction, and, eventually, desired motion. This issue makes the robotization and accurate modeling of heavy-duty machinery very challenging because the application primarily involves off-road terrains, which are susceptible to uneven motion and severe slippage. As a step toward robotization in skid-steering heavy-duty robot (SSHDR), this paper aims to design an innovative robust model-free control system developed by neural networks to strongly stabilize the robot dynamics in the presence of a broad range of potential wheel slippages. Before the control design, the dynamics of the SSHDR are first investigated by mathematically incorporating slippage effects, assuming that all functional modeling terms of the system are unknown to the control system. Then, a novel tracking control framework to guarantee global exponential stability of the SSHDR is designed as follows: 1) the unknown modeling of wheel dynamics is approximated using radial basis function neural networks (RBFNNs); and 2) a new adaptive law is proposed to compensate for slippage effects and tune the weights of the RBFNNs online during execution. Simulation and experimental results verify the proposed tracking control performance of a 4,836 kg SSHDR operating on slippery terrain.

Anti-Slip AI-Driven Model-Free Control with Global Exponential Stability in Skid-Steering Robots

TL;DR

This work tackles the challenge of wheel slippage in skid-steering heavy-duty robots by introducing a model-free neural network based tracking framework (NN-RMFC). The core idea is to approximate unknown wheel dynamics with radial basis function neural networks and to adapt their weights online through a novel adaptive law, enabling robust tracking of commanded velocities despite slip disturbances. A rigorous stability proof establishes global exponential stability with convergence rate , ensuring uniform exponential convergence from arbitrary initial conditions (Theorem 1). The approach is validated both in simulation and on a real 4,836 kg SSHDR operating on slippery snowy terrain, where NN-RMFC outperforms competing model-free methods in steady-state error and settling time, demonstrating practical potential for reliable autonomous navigation in rough off-road environments.

Abstract

Undesired lateral and longitudinal wheel slippage can disrupt a mobile robot's heading angle, traction, and, eventually, desired motion. This issue makes the robotization and accurate modeling of heavy-duty machinery very challenging because the application primarily involves off-road terrains, which are susceptible to uneven motion and severe slippage. As a step toward robotization in skid-steering heavy-duty robot (SSHDR), this paper aims to design an innovative robust model-free control system developed by neural networks to strongly stabilize the robot dynamics in the presence of a broad range of potential wheel slippages. Before the control design, the dynamics of the SSHDR are first investigated by mathematically incorporating slippage effects, assuming that all functional modeling terms of the system are unknown to the control system. Then, a novel tracking control framework to guarantee global exponential stability of the SSHDR is designed as follows: 1) the unknown modeling of wheel dynamics is approximated using radial basis function neural networks (RBFNNs); and 2) a new adaptive law is proposed to compensate for slippage effects and tune the weights of the RBFNNs online during execution. Simulation and experimental results verify the proposed tracking control performance of a 4,836 kg SSHDR operating on slippery terrain.

Paper Structure

This paper contains 9 sections, 25 equations, 13 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Differential Drive System Dynamics
  3. Rbfnn-Based NN-RMFC
  4. Stability Proof
  5. A Guide to Tune Control Parameters
  6. Performance Validation and Results
  7. Simulation Results in Slippery Terrains
  8. Experimental Results in Extremely Slippery and Snowy Terrains
  9. Conclusion

Figures (13)

  • Figure 1: A four-wheel SSHDR prototype operating on rough terrain.
  • Figure 2: The whole framework of a four-wheel SSHDR.
  • Figure 3: Human-in-loop SSHDRs for the remote control verification.
  • Figure 4: Verification of the remote control system in practice; the video is available at: https://youtu.be/AQycbEVt_M8.
  • Figure 5: The right side of the control-implemented SSHDR as a representative sample. The left side follows the same structure.
  • ...and 8 more figures