Virtual Safety Bubble Control for Autonomous Farming Machines
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Farming machines face challenges in navigating confined or dense environments due to their large size, which makes it difficult to gauge proximity to objects, and this issue is exacerbated in automated systems where obstacles can be obscured, leading to safety concerns.
Innovation Solution
The implementation of a virtual safety bubble around autonomous farming machines, which uses detection mechanisms and a control system to generate and dynamically adjust a safety zone, allowing the machine to detect and respond to obstacles within this zone by adjusting operations or rerouting.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If farming machines operate autonomously in confined or dense environments, then productivity is improved, but safety and collision avoidance deteriorate due to obscured obstacles and difficulty gauging proximity
Solution Approach 1:
The system performs preliminary detection and classification of objects in the environment before the farming machine reaches them. The detection system continuously scans and identifies objects ahead of time, allowing the control system to plan safe navigation paths in advance, thus maintaining both autonomous operation and collision avoidance.
Solution Approach 2:
The patent introduces a virtual safety bubble as an intermediary concept between the farming machine and physical obstacles. This virtual boundary, maintained at a safe distance from the machine, acts as a mediator that allows autonomous operation while ensuring collision avoidance by triggering warnings or stop conditions when objects breach this virtual barrier.
2Reliability
If the virtual safety bubble size is increased to improve safety margin, then collision avoidance is improved, but the area available for farming operations is reduced
Solution Approach 1:
The virtual safety bubble is implemented as a dynamic rather than static concept. The control system continuously adjusts the bubble's parameters (size, shape, position) based on real-time detection of objects in the environment. When no objects are present, the bubble can be minimized to maximize farming area; when objects are detected, the bubble expands or shifts to maintain safe distances, thus balancing safety margin with farming operation area.
Solution Approach 2:
The system applies different safety bubble characteristics in different local areas around the farming machine. Rather than using a uniform safety zone in all directions, the virtual bubble can be expanded in directions where objects are detected and minimized in clear directions, allowing the farming machine to operate closer to obstacles when safe and maintain larger margins where needed.
3Measurement precision
If detection mechanisms are added to improve obstacle detection, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The detection system is segmented into multiple independent detection mechanisms positioned at different locations on the farming machine, each with a specific field of view. This segmentation allows the system to achieve comprehensive coverage and high measurement precision through multiple viewpoints while keeping each individual sensor relatively simple. The control system processes data from each segment separately and integrates the results.
Solution Approach 2:
The detection mechanisms are designed with multi-functionality, serving both as obstacle detection sensors and as sources of spatial information for navigation and mapping. This universal use of detection components improves measurement precision for obstacle detection without requiring additional dedicated sensors, thus avoiding increased device complexity.
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
An autonomous farming machine navigable in an environment for performing farming action(s) is disclosed. The farming machine receives a notification from a manager that there are no obstacles in the blind spots of the detection system. The farming machine applies an obstacle detection model to the captured images to verify that there are no obstacles in unobstructed views. The farming machine determines a configuration of the farming machine. The farming machine determines a virtual safety bubble for the farming machine to autonomously perform the farming action(s) based on the determined configuration. The farming machine detects an obstacle in the environment by applying the obstacle detection model to the captured images. The farming machine determines that the obstacle is entering the virtual safety bubble. In response to determining that the obstacle is entering the virtual safety bubble, the farming machine terminates operation of the farming machine and/or enacts preventive measures.