Autonomous Gardening Vehicle Using SLAM for Wire-Free Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous gardening vehicles inefficiently cover terrain, requiring multiple passes over the same sections and lacking precise terrain information and navigation, especially in varying conditions, and rely on buried wires for movement control, which is time-consuming and invasive.
Innovation Solution
An unmanned autonomous gardening vehicle equipped with a camera and SLAM algorithm that captures image series to generate scaled terrain information, allowing for simultaneous localization and mapping, and uses absolute scale information to derive precise position and orientation data, enabling efficient navigation and treatment of terrain without buried wires.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If an autonomous lawnmower moves according to a random path to mow the terrain, then the mower can cover the terrain area, but the time period required is comparatively lengthy as the mower moves several times over identical terrain sections
Solution Approach 1:
The system performs preliminary mapping of the terrain using a camera and SLAM algorithm to create a digital map with identifiable features. This preliminary action enables the mower to plan an optimized path that avoids revisiting already-mowed sections, thereby reducing the total time required to cover the entire terrain area.
Solution Approach 2:
The system continuously captures images of the terrain and uses SLAM to update the mower's position and the terrain map in real-time. This feedback mechanism allows the mower to adjust its path dynamically, ensuring it moves to new, unmowed sections rather than revisiting identical terrain sections, thus improving productivity and reducing time loss.
2Ease of operation
If buried wires are used to define working areas and control movement of the mower, then the mower can be directed to move away from wires, but preparation of the terrain is quite time consuming and related to environmental intrusions
Solution Approach 1:
The system replaces the mechanical buried wire system with a vision-based navigation system. A camera captures images of the terrain, and SLAM algorithms process these images to create a map and determine the mower's position. This substitution eliminates the need for time-consuming wire installation while providing accurate movement control and working area definition through software-based terrain mapping.
Solution Approach 2:
The system introduces an intermediary layer of image processing and SLAM algorithms between the camera and the control system. These algorithms process the captured images to extract terrain features, build a map, and generate navigation commands, thereby enabling wire-free movement control without direct mechanical intervention in the terrain.
3Productivity
If the gardening vehicle treats terrain sections independently without considering terrain conditions, then the vehicle can perform gardening operations, but the terrain conditions are maintained in a degraded state with no improvement for plant growth
Solution Approach 1:
The system applies different gardening operations to different terrain sections based on their specific conditions. By analyzing terrain features and conditions captured in images, the system determines the appropriate treatment for each local area, such as mowing, aeration, or fertilization, thereby improving plant growth conditions while maintaining operational efficiency.
Solution Approach 2:
The system dynamically adapts its gardening operations based on real-time terrain condition assessment. Using SLAM and image analysis, the system continuously evaluates terrain state and adjusts the type and intensity of gardening operations accordingly, ensuring that each terrain section receives appropriate treatment to improve plant growth conditions while maintaining overall productivity.
Data Source
Figure 1~3
Figure 2
Figure 4
AI summary
Method for generating scaled terrain information with an unmanned autonomous gardening vehicle (1), the gardening vehicle (1) comprising a driving unit comprising a set of at least one drive wheel (5) and a motor connected to the at least one drive wheel for providing movability of the gardening vehicle (1), a gardening-tool (7) and a camera (10a-b) for capturing images of a terrain, the camera (10a-b) being positioned and aligned in known manner relative to the gardening vehicle (1). In context of the method the gardening vehicle (1) is moved in the terrain whilst concurrently generating a set of image data by capturing an image series of terrain sections so that at least two (successive) images of the image series cover an amount of identical points in the terrain, wherein the terrain sections are defined by a viewing area of the camera (10a-b) at respective positions of the camera while moving. Furthermore, a simultaneous localisation and mapping (SLAM) algorithm is applied to the set of image data and thereby terrain data is derived, the terrain data comprising a point cloud representing the captured terrain and position data relating to a relative position of the gardening vehicle (1) in the terrain. Additionally, the point cloud is scaled by applying absolute scale information to the terrain data, particularly wherein the position data is scaled.