Robot Motion Sensing for Human-Aware Navigation Around Moving Bodies

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current robots lack the ability to differentiate between people, animals, and objects, leading to inefficient navigation and potential harm, and existing recognition systems are often expensive and ineffective in dynamic environments.

Innovation Solution

A robot equipped with multiple sensor units, including LIDAR, that detect motion and characteristics to differentiate between people, animals, and objects, allowing it to adjust its behavior accordingly, such as slowing down or navigating around them.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Object-affected harmful factors

If the robot always slows down when interacting with moving bodies, then safety around people and animals is improved, but navigation efficiency and speed are worsened

Engineering Contradiction:
Improveharm to people and animalsVSAvoidnavigation efficiency
Core Design Contradiction:
Object-affected harmful factorsVSProductivity

Solution Approach 1:

The robot applies different behavior characteristics to different types of moving bodies. It identifies people and animals through sensor data analysis and applies cautious navigation (slowing down) specifically to them, while maintaining normal speed for inanimate objects. This localized differentiation resolves the contradiction by making safety measures selective rather than universal.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The robot dynamically adjusts its navigation behavior based on real-time identification of moving bodies. When people or animals are detected, the robot transitions to cautious mode with reduced speed; when only inanimate objects are present, it maintains efficient navigation speed. This dynamic adaptation allows the system to optimize both safety and efficiency based on current environmental conditions.

Inventive Principle:
Principle #15Dynamics

2Productivity

If the robot tries to navigate around moving bodies that are also moving, then path efficiency is improved, but path deviation and complexity are worsened

Engineering Contradiction:
Improvenavigation efficiencyVSAvoidpath variation
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The robot applies different navigation strategies based on the type of moving body detected. For people and animals, it uses cautious navigation with potential path adjustments. For inanimate objects, it employs simple avoidance maneuvers. This differentiated approach reduces unnecessary path complexity while maintaining efficiency.

Inventive Principle:
Principle #3Local quality

3Measurement precision

If the robot uses advanced recognition algorithms to identify people, then detection accuracy is improved, but computational cost and processing time are worsened

Engineering Contradiction:
Improvedetection accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The robot uses a two-stage detection approach: first applying simpler, faster sensor-based motion detection to identify potential targets, then applying more sophisticated algorithms only when needed to differentiate between people, animals, and objects. This partial application of complex algorithms reduces computational overhead while maintaining sufficient accuracy for navigation decisions.

Inventive Principle:
Principle #16Partial or excessive action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

Enables safer and more efficient interactions with moving bodies, improving confidence in autonomous robot operation and reducing injuries by accurately recognizing and responding to people and animals.

Implementation Method 1

A robot equipped with multiple sensor units, including LIDAR, that detect motion and characteristics

Methodology Applied
Scientific EffectLIDAR: LIDAR

Implementation Method 2

Each sensor unit can be configured to generate sensor data indicative of a portion of a moving body at a plurality of times

Methodology Applied
Scientific EffectTime of flight: Time of Flight

Data Source

PatentEP3479568B1Systems and methods for robotic behavior around moving bodies
Publication Date: 2023.08.16 BRAIN CORP
  • EP3479568B1 patent drawingFigure 1
  • EP3479568B1 patent drawingFigure 2
  • EP3479568B1 patent drawingFigure 3A~3B

AI summary

Systems and methods for detection of people are disclosed. In some exemplary implementations, a robot can have a plurality of sensor units. Each sensor unit can be configured to generate sensor data indicative of a portion of a moving body at a plurality of times. Based on at least the sensor data, the robot can determine that the moving body is a person by at least detecting the motion of the moving body and determining that the moving body has characteristics of a person. The robot can then perform an action based at least in part on the determination that the moving body is a person.