Service Robot Relocalization After False Obstacle Detection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Mobile service robots face challenges in efficiently recovering from path blockages due to delocalization, where they rely on uncertain or erroneous location information, leading to incorrect perception of obstacles.

Innovation Solution

The service robot employs a delocalization recovery system that includes a travel impediment detector, robot delocalization detection module, and relocalization module to identify and correct its location using multiple sensors and localization models, enabling it to reorient and resume travel.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Extent of automation

If the service robot uses localization models to determine its position, then it can navigate autonomously, but it may become delocalized and perceive false obstacles

Engineering Contradiction:
Improveautonomous navigationVSAvoidlocation accuracy
Core Design Contradiction:
Extent of automationVSReliability

Solution Approach 1:

The system implements feedback by continuously comparing the robot's current position estimate from localization models with expected position based on travel path and detected features. When discrepancies are detected (delocalization), the system triggers relocalization operations to correct the position estimate, ensuring reliable autonomous navigation.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system performs preliminary delocalization detection before the robot becomes completely lost. By continuously monitoring position consistency and detecting early signs of delocalization, the system can trigger relocalization operations proactively, preventing complete navigation failure and maintaining reliable operation.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If the service robot performs relocalization operations to correct delocalization, then location accuracy improves, but navigation time increases

Engineering Contradiction:
Improveposition estimation accuracyVSAvoidnavigation time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The system applies partial relocalization by using selective feature matching and comparison rather than complete re-mapping. Instead of performing full relocalization operations, the system uses targeted comparisons between current sensor data and stored map features to correct position estimates, reducing computation time while maintaining accuracy.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The system skips unnecessary relocalization steps by first checking for delocalization conditions and only performing full relocalization when needed. The system rushes through the correction process by using efficient feature matching algorithms that quickly identify and correct position errors without exhaustive search, minimizing navigation time loss.

Inventive Principle:
Principle #21Skipping (Rushing through)

3Reliability

If the service robot detects travel impediments continuously, then navigation safety improves, but computational load increases

Engineering Contradiction:
Improveobstacle detection reliabilityVSAvoidcomputational energy
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system segments obstacle detection into multiple stages: initial travel path monitoring, delocalization detection, and detailed impediment analysis. By dividing the detection process into segments triggered only when needed (e.g., when delocalization is detected), the system maintains reliable obstacle detection while reducing overall computational energy consumption compared to continuous full-scale analysis.

Inventive Principle:
Principle #1Segmentation

Data Source

PatentUS20260093260A1Image-based delocalization recovery
Publication Date: 2026.04.02 BEAR ROBOTICS INC
  • US20260093260A1 patent drawing
  • US20260093260A1 patent drawing
  • US20260093260A1 patent drawing

AI summary

A computer-implemented method and apparatus to recover travel of a service robot, the method comprising: detecting a travel impediment relating to a first travel path to a destination for the service robot; responsive to detecting the travel impediment relating to the first travel path to the destination, determining that the service robot is delocalized by performing a comparison between a first pose estimate for the service robot and a second pose estimate for the service robot; responsive to determining that the service robot is delocalized, performing a relocalization operation of the service robot; and responsive to performing the relocalization operation of the service robot, initiating a second travel path to the destination.