Mobile Robot Crosswalk Waiting Control for Traffic Light Occlusion

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous robotic vehicles face challenges in navigating through dynamic environments, particularly when objects occlude their sensors' view of traffic lights, hindering their ability to determine whether it is safe to cross a crosswalk.

Innovation Solution

The robotic vehicle uses LIDAR and camera sensors to generate a bounding box or shell structure of objects, determining a visual occlusion zone and a reduced waiting area to position itself for unobstructed view of traffic lights, employing a processor to control its movement to maintain visibility of traffic indicators.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the mobile robot uses camera sensors to monitor traffic lights, then it can detect traffic light states, but objects may occlude the field of view and prevent tracking

Engineering Contradiction:
Improvetraffic light state tracking reliabilityVSAvoidsensor occlusion by objects
Core Design Contradiction:
ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The system transitions from 2D image plane analysis to 3D spatial reasoning by projecting occlusion zones into the three-dimensional waiting area. The processor calculates visual occlusion zones based on object positions, bounding boxes, and camera parameters, then maps these zones into 3D space to determine safe waiting positions that maintain traffic light visibility.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Solution Approach 2:

The system performs preliminary calculation of visual occlusion zones and reduced waiting areas before the robot actually waits. By pre-computing which positions in the waiting area will maintain traffic light visibility and which will be occluded by objects, the robot can proactively select optimal positions rather than reactively adjusting after occlusion occurs.

Inventive Principle:
Principle #10Preliminary action

2Reliability

If the mobile robot moves to maintain unobstructed view of traffic lights, then it can continue tracking, but it may delay crossing the crosswalk

Engineering Contradiction:
Improvetraffic light state tracking reliabilityVSAvoidcrossing delay
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system calculates optimal waiting positions in advance, identifying areas where the traffic light remains visible without requiring continuous robot movement. By pre-determining these positions based on object locations and occlusion zones, the robot can wait efficiently without unnecessary repositioning delays.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system uses its own camera parameters, field of view characteristics, and positioning data to autonomously calculate occlusion zones and determine optimal waiting positions. The robot serves itself by independently assessing which positions will maintain visibility without external assistance or complex coordination.

Inventive Principle:
Principle #25Self-service

3Measurement precision

If the mobile robot generates a reduced waiting area by subtracting visual occlusion zones, then it can identify safe positions, but the available waiting area may be limited

Engineering Contradiction:
Improvesafe position identification accuracyVSAvoidavailable waiting area
Core Design Contradiction:
Measurement precisionVSArea of stationary object

Solution Approach 1:

The system applies different quality requirements to different spatial regions. Rather than requiring uniform visibility throughout the entire waiting area, the system identifies specific local zones (reduced waiting areas) where visibility is maintained. This allows the robot to utilize non-uniform spatial distribution of safe positions, maximizing the use of available space while maintaining tracking reliability.

Inventive Principle:
Principle #3Local quality

Data Source

PatentEP4174611B1Mobile robot and a method for controlling the mobile robot
Publication Date: 2024.08.28 DIRECT CURSUS TECH LLC
  • EP4174611B1 patent drawingFigure 1
  • EP4174611B1 patent drawingFigure 2
  • EP4174611B1 patent drawingFigure 3

AI summary

A mobile robot (306) and a method (700) for controlling a mobile robot are provided. The method includes: accessing a 3D map representation of an environment (200) including a respective indication of a crosswalk (302), a waiting area, and a visual traffic indicator; detecting an object located in the waiting area for generating a bounding box of the object; mapping a position of the bounding box to the 3D map representation; determining a visual occlusion zone of the object in the waiting area; determining a reduced waiting area as a difference between the waiting area and the visual occlusion area, and triggering control of the propulsion system for moving the mobile robot to the reduced waiting area.