Autonomous Steering System Using Camera Boundary Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing steering systems for commercial vehicles with implements cannot efficiently guide them along laterally extending work areas without manual operator intervention, relying on external position determination signals and dividing the operator's attention between steering and monitoring the environment.
Innovation Solution
A steering system with a control unit, camera arrangement, and user interface that evaluates image data to generate steering signals, allowing the vehicle to autonomously follow a boundary between the driving and working areas, independent of external signals, and enabling the operator to focus on the implement and surroundings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a steering system uses external position determination signals (RTK GPS) to guide the vehicle, then positioning accuracy is improved, but the system becomes dependent on external signals that are not available everywhere and require additional fees
Solution Approach 1:
The patent introduces an optical intermediary (camera system) that captures visual features of the environment to determine vehicle position and orientation. Instead of relying on external satellite signals, the system uses intermediate visual markers and environmental features as mediators for position determination, enabling operation anywhere with sufficient visual contrast.
Solution Approach 2:
The patent replaces the satellite-based electromagnetic signal system (RTK GPS) with an optical vision-based system. The camera arrangement captures images, and image processing algorithms substitute for the external signal processing, eliminating dependency on external infrastructure and enabling global operation.
2Adaptability or versatility
If the operator manually steers the vehicle while monitoring the environment and implement operation, then flexibility and obstacle detection are improved, but operator fatigue increases and continuous monitoring becomes difficult
Solution Approach 1:
The steering system performs self-steering based on pre-planned routes and real-time image processing. The control unit autonomously calculates steering commands from camera data, maintaining the vehicle's position relative to the working area boundary without continuous operator intervention, thereby reducing fatigue while preserving safety through automated monitoring.
Solution Approach 2:
The system implements continuous feedback loops where camera images are processed in real-time to detect the boundary between drivable and work areas. This feedback is fed back to the control unit, which adjusts steering commands accordingly, enabling autonomous operation with reduced operator burden while maintaining adaptability to environmental changes.
3Measurement precision
If the camera arrangement is oriented exclusively in the direction of travel, then forward path detection is improved, but lateral boundary detection for work areas becomes difficult
Solution Approach 1:
The patent transitions from a one-dimensional forward-facing camera view to a two-dimensional lateral viewing direction. The camera is oriented perpendicular to the direction of travel, enabling simultaneous detection of both the forward path and the lateral boundary between drivable and work areas, thus capturing complete spatial information in a single view.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present invention relates to a steering system (17) for a commercial vehicle (1, 2), in particular an agricultural or municipal vehicle, with a work implement (3), wherein the steering system (17) comprises a control unit (8) for generating steering signals for autonomously guiding the commercial vehicle (1, 2), a camera arrangement (4) for capturing images, and a user interface (14) connected to the control unit (8), wherein the control unit (8) is configured to evaluate the image data generated by the camera arrangement (4) in order to generate the steering signals depending on the image data, wherein the at least one camera arrangement (4) is positioned on the commercial vehicle (1, 2) and oriented with its viewing direction (7c) such that a ground area (18) to be driven on and a laterally adjacent ground area (19) to be worked on can be detected simultaneously, and wherein the control unit (8) is configured to determine a boundary (20, ) based on the captured image data.25) to determine the path along which the steering system (17) guides the commercial vehicle (1, 2) and/or the work equipment (3) at a distance (A) to be maintained.