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

Engineering notes

Key topics: autonomous driving system, autonomous driving, path planning, perception, planning, control. See the paper for implementation details and experimental results.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。

Original abstract

Introduction Autonomous navigation of crawler tractors is essential for precision agriculture; however, existing systems often face a trade-off between path-tracking accuracy and steering stability, particularly under complex field conditions. To address this limitation, this study aimed to develop an autonomous driving system for single-HST (Hydrostatic Transmission) crawler tractors that enhances both control resolution and operational reliability. Methods A kinematic model of the single-HST crawler chassis was established, and a state-feedback path-tracking controller integrating lateral and heading deviations was proposed. A pulse-width modulation (PWM)-based multi-modal steering control strategy was designed to enable intelligent switching and smooth transition between differential steering and unilateral braking steering by dynamically adjusting the steering hydraulic cylinder stroke. A three-layer hardware and software architecture—comprising perception, decision-making, and execution layers—was constructed, and an embedded vehicle controller integrating path planning and real-time control was developed. Field tests were conducted at the China National Precision Agriculture Research Demonstration Base, including fixed-curvature path tracking and reciprocating autonomous operation trials. Results Under curve path-tracking conditions, the proposed multi-modal steering control achieved an average lateral deviation of 4.25 cm, with a standard deviation below 5.0 cm, representing a 34.4% reduction compared with unilateral braking steering. In reciprocating operations, the average inter-row spacing error was 6.04 cm, satisfying the precision requirements for agricultural machinery under both field soil and cement pavement conditions. Discussion The results demonstrate that the proposed system effectively balances tracking accuracy and steering stability in autonomous crawler tractor navigation. The multi-modal steering strategy offers a practical solution for agricultural machinery operating on varied surfaces and shows strong potential for broader application in precision farming systems with similar terrain conditions.

Links and sources

Comments