Adjustable Robot Vision for Predicted-Path Blind Spot Capture

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Robots face challenges in navigating environments with unknown or uncertain environmental objects and attributes due to blind spots and limitations in vision systems, leading to reduced operational efficiency and increased collision risks.

Innovation Solution

The implementation of multiple vision components, including a fixed and an adjustable vision component, dynamically adjusted to mitigate unknown environmental objects and attributes, utilizing factors like planned paths, blind spots, and dynamic object locations to enhance data accuracy and coverage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If a fixed vision component is used to capture vision data, then the device complexity is reduced, but the measurement precision and coverage of environmental objects are insufficient due to blind spots

Engineering Contradiction:
Improvevision system complexityVSAvoidenvironmental object detection accuracy
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent applies the dynamics principle by implementing an adjustable vision component that can dynamically change its pose relative to the robot frame. The adjustable vision component transitions between different poses to capture vision data from multiple angles, eliminating blind spots and improving environmental object detection accuracy without requiring a completely fixed vision system.

Inventive Principle:
Principle #15Dynamics

2Measurement precision

If the adjustable vision component is dynamically adjusted to multiple poses, then the measurement precision and coverage are improved, but the device complexity and operational complexity increase

Engineering Contradiction:
Improveenvironmental object detection accuracyVSAvoidvision system complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The adjustable vision component serves multiple functions: it acts as both a fixed vision component when in a stable pose and as an adjustable vision component when transitioning between poses. This multi-functionality reduces the need for separate fixed and adjustable vision components, thereby managing device complexity while maintaining improved measurement precision.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Reliability

If the adjustable vision component is dynamically adjusted during navigation, then the reliability of navigation is improved by reducing blind spots, but the productivity and navigation speed are reduced

Engineering Contradiction:
Improvenavigation safetyVSAvoidnavigation speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The system performs preliminary action by capturing vision data at multiple poses before the robot completes its navigation task. The adjustable vision component anticipates potential blind spots along the navigation path and proactively captures data from multiple angles in advance, ensuring reliable navigation without requiring real-time adjustments that would slow down the robot.

Inventive Principle:
Principle #10Preliminary action

4Measurement precision

If multiple vision components are used to cover blind spots, then the measurement precision is improved, but the device complexity and cost increase

Engineering Contradiction:
Improveenvironmental object detection accuracyVSAvoidnumber of vision components
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

Instead of using multiple fixed vision components simultaneously, the patent uses a single adjustable vision component that dynamically changes its pose to cover different areas. This approach achieves the same blind spot coverage as multiple fixed components but with fewer physical components, thereby reducing device complexity and cost while maintaining measurement precision.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP4386504A1Using adjustable vision component for on-demand vision data capture of areas along a predicted trajectory of a robot
Publication Date: 2024.06.19 GOOGLE LLC
  • EP4386504A1 patent drawingFigure 1
  • EP4386504A1 patent drawingFigure 2A
  • EP4386504A1 patent drawingFigure 2B

AI summary

Implementations set forth herein relate to a robot that employs a stereo camera and LIDAR for generating point cloud data while the robot is traversing an area. The point cloud data can characterize spaces within the area as occupied, unoccupied, or uncategorized. For instance, an uncategorized space can refer to a point in three-dimensional (3D) space where occupancy of the space is unknown and/or where no observation has been made by the robot-such as in circumstances where a blind spot is located at or near a base of the robot. In order to efficiently traverse certain areas, the robot can estimate resource costs of either sweeping the stereo camera indiscriminately between spaces and/or specifically focusing the stereo camera on uncategorized space(s) during the route. Based on such resource cost estimations, the robot can adaptively maneuver the stereo camera during routes while also minimizing resource consumption by the robot.