Autonomous Dock Pose Tracking for Moved Mobile Robot Docks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous mobile devices (AMDs) face challenges in navigating back to their dock when it has been moved, especially with passive docks that do not emit signals, as they struggle to maintain a consistent reference pose, leading to potential battery depletion and operational failure.
Innovation Solution
The AMD determines transform data to relate the new dock pose to the previous pose using sensor data and SLAM algorithms, allowing it to update its map and maintain a consistent reference pose even after the dock has been moved, without relying on active signal emission from the dock.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Use of energy by stationary object
If the dock uses passive design without signal emission, then power consumption is reduced and energy standards are met, but the AMD cannot reliably locate and return to the dock when it has been moved
Solution Approach 1:
The AMD creates a digital copy of the dock's physical appearance by capturing images and generating a synthetic template representation. This digital copy is stored in its map data, allowing the AMD to identify and locate the dock by comparing current sensor data against this stored template, eliminating the need for active signal emission while maintaining reliable dock location tracking
Solution Approach 2:
The AMD performs preliminary actions by capturing images of the dock and generating a synthetic template before the dock is moved. This pre-established digital representation is stored in the map data, enabling the AMD to later identify the dock's new location through template matching without requiring the dock to emit signals at the time of location tracking
2Reliability
If the AMD uses traditional beacon-based navigation, then it can reliably return to the dock, but the dock requires active signal emission which increases power consumption and hardware complexity
Solution Approach 1:
Instead of using physical beacons or active signal emission hardware in the dock, the AMD creates and stores a digital copy (synthetic template) of the dock's visual appearance. This eliminates the need for complex active hardware in the dock while maintaining reliable navigation through image-based identification and template matching algorithms
Solution Approach 2:
The patent replaces the mechanical/electronic signal emission system with an optical/image-based system. The dock passively reflects environmental light which is captured by the AMD's sensors, and the navigation is achieved through computational image processing and template matching rather than active electromagnetic signal transmission
3Ease of manufacture
If the dock is moved without active signaling, then the AMD cannot detect the move and may fail to return correctly, but adding active signaling increases power consumption and cost
Solution Approach 1:
The AMD creates a digital copy of the dock's visual characteristics and stores it as a synthetic template in its map data. When the dock is moved, the AMD captures new images and compares them against the stored template to detect the move and update its map, preserving dock position information without requiring active signaling hardware
Solution Approach 2:
The AMD performs self-updating of its map data by autonomously capturing images of the dock, comparing them against stored templates, detecting position changes, and updating its internal representation. This self-service mechanism allows the AMD to track dock position without external signaling from the dock itself
Data Source
AI summary
An autonomous mobile device (AMD) moves in a physical space and uses a dock located at a first pose. Sometimes a user may move the dock. To determine whether the dock has moved, the AMD compares first pose data that was previously obtained while at the dock in the first pose to second pose data, such as after a restart or after leaving the dock. If a difference between the first pose and the second pose is greater than a threshold, the dock has moved. The pose data may be determined using a simultaneous localization and mapping (SLAM) algorithm to process images from cameras on the AMD. Transform data that relates coordinates of the second pose to coordinates of the first pose may be determined. If the dock is used as an origin for a map of the physical space, the transform data may be used to update the map.