Obstacle recognition method for autonomous robots

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous robots face challenges in efficiently navigating and cleaning environments due to the lack of effective object recognition and path planning, particularly in avoiding obstacles like cords, clothing, shoes, and pet waste, while also needing improved mapping and localization techniques.

Innovation Solution

The implementation of a robot equipped with sensors, a processor, and an image sensor that captures images of the workspace, identifies object types using an object dictionary, and adjusts its navigation path to avoid or clean around obstacles, while also utilizing a planar representation of the environment for efficient cleaning and user input integration.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the robot uses basic obstacle detection methods, then the device complexity is low, but the reliability of obstacle avoidance is insufficient

Engineering Contradiction:
Improveobstacle avoidance reliabilityVSAvoiddevice complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The robot divides the workspace into multiple zones using a planar representation system with dividers. This segmentation allows the robot to process and prioritize different areas independently, improving navigation reliability by systematically managing complex environments without requiring overly complex hardware

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a two-dimensional planar representation of the workspace, adding a spatial dimension to obstacle detection and navigation. This allows the robot to visualize and plan paths across the entire workspace rather than reacting to obstacles in isolation, enhancing avoidance reliability through top-down spatial awareness

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Adaptability or versatility

If the robot follows a fixed navigation path, then the ease of operation is high, but the adaptability to dynamic obstacles is poor

Engineering Contradiction:
Improvepath adaptation capabilityVSAvoidnavigation control simplicity
Core Design Contradiction:
Adaptability or versatilityVSEase of operation

Solution Approach 1:

The navigation path is designed as a dynamic system that can be altered in real-time based on detected objects. The processor modifies the planned path when obstacles are identified, allowing the robot to adapt to dynamic environments while maintaining relatively simple operational control through automated adjustments

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system continuously monitors the workspace using image sensors and compares detected objects against the planned navigation path. This feedback loop enables automatic path adjustments when obstacles are detected, providing adaptability while keeping the control system straightforward through sensor-driven decision-making

Inventive Principle:
Principle #23Feedback

3Productivity

If the robot cleans all areas uniformly, then the productivity is maximized, but the object-affected harmful factors increase due to disturbance of undetected objects

Engineering Contradiction:
Improvecleaning efficiencyVSAvoidobject disturbance harm
Core Design Contradiction:
ProductivityVSObject-affected harmful factors

Solution Approach 1:

The robot applies different cleaning behaviors to different zones based on object detection. When objects are detected in specific areas, the navigation path is altered to avoid or carefully navigate around those locations, allowing uniform cleaning in safe areas while providing localized protection for areas with detected objects

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The system performs preliminary object detection and path planning before executing cleaning operations. By identifying obstacles and adjusting the navigation path in advance, the robot can maintain high productivity in clear areas while pre-planning safe routes around detected objects, preventing harmful disturbances

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS11899463B1Obstacle recognition method for autonomous robots
Publication Date: 2024.02.13 AI INC
  • US11899463B1 patent drawing
  • US11899463B1 patent drawing
  • US11899463B1 patent drawing

AI summary

A robot including a medium storing instructions that when executed by a processor of the robot effectuates operations including: capturing images of a workspace as the robot moves within the workspace; identifying at least one characteristic of an object captured in the images of the workspace; determining an object type of the object based on an object dictionary of different types of objects, wherein the different object types comprise at least a cord, clothing garments, a shoe, earphones, and pet bodily waste; and instructing the robot to execute at least one action based on the object type of the object, wherein the at least one action comprises avoiding the object or cleaning around the object.