Autonomous Robot Obstacle Recognition for Entanglement Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous robots often encounter objects such as cords, wires, clothing, and toys that can cause malfunctions or prevent task completion due to entanglement with moving parts.
Innovation Solution
Equipping robots with image sensors and processors that utilize deep learning to capture and analyze images, identify object types from an object dictionary, and adjust navigation paths to avoid these objects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If autonomous robots operate in workspaces with objects present, then task completion capability is improved, but risk of entanglement with moving parts increases causing malfunction
Solution Approach 1:
The robot performs preliminary identification of objects in the workspace before operation begins. The image sensor captures images and the processor identifies object types (clothing, cords, pet waste, shoes) in advance, allowing the robot to plan a safe path that avoids potential entanglement hazards before they become problems during operation.
Solution Approach 2:
An image sensor and image processing system serve as an intermediary between the robot and the workspace objects. This intermediary system captures visual information, processes it to identify object types, and provides this information to the navigation system, enabling the robot to indirectly perceive and respond to objects without direct physical interaction that could cause entanglement.
2Reliability
If robot navigation is adjusted to avoid identified objects, then entanglement risk is reduced, but navigation complexity increases
Solution Approach 1:
The navigation system changes operational parameters (path planning parameters) based on identified object types. When objects are detected, the system adjusts navigation parameters to route around these objects, transforming the navigation approach from fixed to adaptive based on real-time object identification results.
3Measurement precision
If deep learning is used to identify object types from images, then object recognition accuracy is improved, but processing time and computational requirements increase
Solution Approach 1:
The system applies deep learning processing selectively rather than to all images continuously. The image sensor captures images and the processor applies object type identification using deep learning only when needed for navigation decisions, balancing recognition accuracy with processing time requirements for real-time operation.
Data Source
AI summary
Provided is a robot, including: a plurality of sensors; a processor; a tangible, non-transitory, machine readable medium storing instructions that when executed by the processor effectuates operations including: capturing, with an image sensor, images of a workspace as the robot moves within the workspace; identifying, with the processor, at least one characteristic of at least one object captured in the images of the workspace; determining, with the processor, an object type of the at least one object based on characteristics of different types of objects stored in an object dictionary, wherein possible object types comprise a type of clothing, a cord, a type of pet bodily waste, and a shoe; and instructing, with the processor, the robot to execute at least one action based on the object type of the at least one object.