Autonomous driving system for single hydrostatic transmission crawler tractor based on multi-modal steering control

Area of Science:

• Agricultural Engineering
• Robotics
• Control Systems

Background:

• Autonomous navigation is crucial for precision agriculture, but current systems struggle with accuracy and stability in challenging terrains.
• Existing autonomous crawler tractor systems often present a trade-off between precise path-tracking and stable steering, limiting their effectiveness.

Purpose of the Study:

• To develop an advanced autonomous driving system for single-Hydrostatic Transmission (HST) crawler tractors.
• To enhance both control resolution and operational reliability for autonomous crawler tractors in precision agriculture.

Main Methods:

• Established a kinematic model for a single-HST crawler chassis.
• Developed a state-feedback path-tracking controller and a pulse-width modulation (PWM)-based multi-modal steering control strategy for intelligent switching between steering modes.
• Implemented a three-layer hardware/software architecture and an embedded vehicle controller for path planning and real-time control.

Main Results:

• Achieved an average lateral deviation of 4.25 cm with a standard deviation below 5.0 cm during curve path tracking, a 34.4% improvement over unilateral braking.
• Recorded an average inter-row spacing error of 6.04 cm in reciprocating operations, meeting precision requirements on both soil and cement surfaces.

Conclusions:

• The developed system effectively balances path-tracking accuracy and steering stability in autonomous crawler tractor navigation.
• The multi-modal steering strategy provides a viable solution for agricultural machinery on diverse terrains, with significant potential for precision farming applications.