Ground Robot Object Distance Estimation for Adaptive Obstacle Avoidance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing ground robots face challenges in accurately determining the distance to objects in their environment, leading to inefficient navigation and obstacle avoidance, especially when multiple objects are present, which reduces their operational benefit.

Innovation Solution

A method using a scanning device attached to the ground robot to create an image of the environment, determine the object's representation, and calculate its distance based on geometric relationships, employing an artificial neural network for recognition and trigonometric considerations, allowing for precise distance measurement.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the floor robot maintains a predetermined safety distance around the object to avoid damaging it, then the reliability of object protection is improved, but the productivity of the floor robot is reduced due to substantial untreated area remaining

Engineering Contradiction:
Improveobject protectionVSAvoidfloor cleaning coverage
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The robot dynamically adjusts its distance to objects based on real-time classification. For safe objects, it moves closer to maximize cleaning coverage; for hazardous objects, it maintains larger safety distances. This dynamic adaptation resolves the contradiction by making the safety distance variable rather than fixed, improving productivity while maintaining reliability when needed.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system changes the parameter of safety distance based on object classification results. By analyzing object features and determining hazard levels, the robot modifies its operational parameters (distance, speed, cleaning intensity) to optimize both protection and cleaning efficiency, thereby resolving the trade-off between reliability and productivity.

Inventive Principle:
Principle #35Parameter changes

2Productivity

If the floor robot reduces its speed and moves toward the object to clean the floor surface as close as possible, then the productivity is improved, but the reliability of avoiding damage to the object or robot is reduced

Engineering Contradiction:
Improvefloor cleaning coverageVSAvoiddamage avoidance
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system dynamically changes operational parameters (speed, distance, cleaning intensity) based on object classification. For safe objects, it increases speed and reduces distance to maximize productivity; for hazardous objects, it maintains conservative parameters to ensure reliability, thus resolving the contradiction through parameter adaptation.

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The robot transitions from static safety protocols to dynamic behavior adjustment. By continuously classifying objects and adjusting its movement and cleaning parameters in real-time, the system optimizes the balance between productivity and reliability based on actual environmental conditions.

Inventive Principle:
Principle #15Dynamics

3Reliability

If the floor robot avoids the object at a greater distance, then the reliability of avoiding entanglement or damage is improved, but the productivity is reduced due to large untreated areas remaining

Engineering Contradiction:
Improveentanglement avoidanceVSAvoidfloor cleaning efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system adjusts the avoidance distance parameter based on object hazard classification. For objects posing entanglement risks like loose cables or carpet fringes, it maintains larger distances; for safe objects, it reduces the avoidance distance to maximize cleaning efficiency, thereby resolving the contradiction through adaptive parameter changes.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP4439221A1Controlling a ground robot in relation to an object
Publication Date: 2024.10.02 BSH HAUSGERATE GMBH
  • EP4439221A1 patent drawingFigure 1
  • EP4439221A1 patent drawingFigure 2
  • EP4439221A1 patent drawingFigure 3

AI summary

A method (200) for controlling a ground robot (105) in an environment in which an object (110) is located comprises steps of creating an image of the environment by means of a scanning device (135) attached to the ground robot (105); determining a representation (315) of the object (110) on the image; determining a boundary (320) of the representation (315) on the image; and determining a distance (d2) of the object (110) from the ground robot (105) based on a position of the boundary (320) on the image and a position of the scanning device (135) on the ground robot (105).