Robotic Lawn Mower Control Unit With AI Obstacle Recognition

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Robotic lawn mowers face challenges in efficiently handling different types of obstacles under varying lighting and weather conditions, and require improved energy efficiency to extend operating time between charging and navigate diverse terrains without hindrance.

Innovation Solution

Incorporating a separate auxiliary processing unit with a neural network for object recognition and classification, utilizing artificial intelligence to offload processing tasks from the main unit, thereby reducing power consumption and enhancing obstacle handling capabilities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a separate auxiliary processing unit with neural network is added for object recognition and classification, then the capability for recognition and classification of objects is vastly increased, but the device complexity increases

Engineering Contradiction:

Improveobject recognition and classification capabilityVSAvoidcontrol unit structure

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The control unit is segmented into two distinct processing units: a main processing unit for general control functions and a separate auxiliary processing unit specifically dedicated to object recognition and classification using neural networks. This segmentation allows each unit to be optimized for its specific function, reducing the complexity burden on the main unit while maintaining high recognition capability.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The auxiliary processing unit acts as an intermediary between the environment detection devices (sensors) and the main processing unit. It pre-processes sensor data through neural network-based recognition and classification before presenting processed information to the main control unit, thereby simplifying the main unit's decision-making process.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Duration of action of moving object

If all processing is performed by the main processing unit, then device complexity is lower, but power consumption increases reducing operating time between charging

Engineering Contradiction:

Improveoperating time between chargingVSAvoidpower consumption

Core Design Contradiction:

Duration of action of moving objectVSUse of energy by moving object

Solution Approach 1:

Processing tasks are segmented and distributed between the main processing unit and the auxiliary processing unit. The auxiliary unit, being specialized for neural network operations, performs recognition and classification more energy-efficiently than a general-purpose main unit could, thereby reducing overall power consumption and extending operating time.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent replaces traditional geometric-based detection methods with artificial intelligence (neural network-based) object recognition. This substitution enables more accurate discrimination of objects and terrains, allowing the mower to navigate more efficiently and consume less energy during operation.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If traditional geometric based detection is used, then device complexity is lower, but the ability to handle different types of obstacles under varying lighting and weather conditions deteriorates

Engineering Contradiction:

Improveobstacle handling capability under varying conditionsVSAvoiddetection system

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

Traditional geometric-based detection systems are replaced with artificial intelligence-based neural network recognition systems. This substitution enables the system to adapt to varying lighting and weather conditions by learning from training data, significantly improving obstacle handling capability under diverse environmental conditions.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The detection system transitions from fixed geometric parameters to adaptive neural network parameters that can be continuously trained and adjusted. This allows the system to maintain high adaptability across different obstacles and environmental conditions by modifying its recognition parameters based on learned patterns rather than relying on static geometric rules.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentEP4000367B1An energy efficient robotic lawn mower

Publication Date: 2025.10.15 HUSQVARNA AB

Figure 1A~1B
Figure 2
Figure 3~4

AI summary

The present disclosure relates to a robotic lawn mower control unit (110) adapted for use in a robotic lawn mower (100) and comprising a main processing unit (115) adapted to cause the control unit (110) to control the operation of the robotic lawn mower (100). This includes, but is not limited to, controlling at least one environment detection device (170, 171) and the propulsion of the robotic lawn mower (100). The control unit (110) further comprises a separate auxiliary processing unit (111) that is dedicated to perform recognition and classification of objects (182) by means of data acquired by means of at least one environment detection device (170, 171).