Multi-Sensor Beacon Fusion for Logistics Vehicle Collision Avoidance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional collision avoidance systems suffer from false positives, inability to handle varying illumination, and difficulty in differentiating colors, leading to sub-optimal performance and unnecessary actions in logistics vehicles like cargo tractors and associated dollies.

Innovation Solution

A multi-sensor data fusion system using LiDAR and color cameras to detect reflective beacons, combined with a model predictive controller, determines optimal speed thresholds to avoid collisions with high-value assets by fusing sensor data and adjusting vehicle movement.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional single-sensor collision avoidance systems are used, then the system structure is simple, but false positive detection occurs and the system cannot differentiate between intended markers and non-intended reflective surfaces

Engineering Contradiction:
Improvedetection accuracyVSAvoidsystem structure
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The patent combines multiple sensor types (LiDAR, color cameras, and other detectors) into a unified collision avoidance system. The LiDAR sensor detects reflective beacons while color cameras capture visual information, and their data is fused to accurately identify markers versus false positives like worker safety vests. This multi-sensor integration resolves the contradiction by improving detection reliability through cross-validation while managing complexity through coordinated sensor fusion algorithms.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The patent introduces reflective beacons as intermediary objects that facilitate accurate detection. These beacons are specifically designed to be detectable by LiDAR while having distinct visual characteristics for camera identification. The beacons serve as intermediaries between the vehicle and the environment, providing unambiguous signals that resolve the ambiguity between intended markers and non-intended reflective surfaces, thereby improving detection accuracy without requiring overly complex sensor systems.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Reliability

If conventional collision avoidance systems react to all detections, then false positives are addressed, but system efficiency is reduced due to unnecessary actions

Engineering Contradiction:
Improvefalse positive reductionVSAvoidsystem efficiency
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent implements a feedback mechanism where sensor detections are continuously validated against multiple criteria before triggering collision avoidance actions. The system cross-references LiDAR detections with camera imagery, checks against the vehicle's path plan, and evaluates the object's velocity and trajectory. This multi-layered feedback process filters out false positives (such as stationary reflective surfaces or objects outside the vehicle's path) while maintaining rapid response to genuine threats, thereby reducing unnecessary actions and improving system efficiency.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent applies partial action by selectively responding only to detections that meet specific criteria for genuine threats. Rather than reacting to all detected objects, the system evaluates each detection against multiple parameters (location relative to no-entry areas, velocity, trajectory, confirmation from multiple sensors) and triggers avoidance actions only when necessary. This selective approach reduces false positive responses while maintaining adequate safety coverage, optimizing the balance between reliability and productivity.

Inventive Principle:
Principle #16Partial or excessive action

3Measurement precision

If LiDAR and camera sensors are used together, then detection precision is improved, but data processing complexity increases

Engineering Contradiction:
Improvelocation identification accuracyVSAvoiddata processing
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the data processing task into distinct functional modules: LiDAR data processing for range and reflective beacon detection, camera processing for visual identification and color analysis, sensor fusion for cross-validation, and decision-making for collision avoidance actions. Each module handles specific aspects of the detection task independently, then integrates results at appropriate stages. This segmentation reduces overall processing complexity by breaking down the complex multi-sensor fusion problem into manageable, specialized sub-tasks that can be optimized independently.

Inventive Principle:
Principle #1Segmentation

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

Enhances collision avoidance by reducing false positives and improving the ability to detect and avoid collisions with towed dollies, ensuring safe movement of logistics vehicles near high-value assets.

Implementation Method 1

a light detection and ranging (LiDAR) sensor and multiple color cameras to detect beacons as types of markers

Methodology Applied
Scientific EffectLight detection and ranging (LiDAR): LIDAR

Implementation Method 2

detecting objects/markers and not delineating intended markers and non-intended reflective surfaces

Methodology Applied
Scientific EffectReflection: Reflection

Implementation Method 3

multiple color cameras to detect beacons as types of markers

Methodology Applied
Scientific EffectPhotoelectric Effect: Photoelectric Effect

Data Source

PatentEP3758983B1Systems and methods for enhanced collision avoidance on logistics ground support equipment using multi-sensor detection fusion
Publication Date: 2025.07.02 FEDERAL EXPRESS CORP
  • EP3758983B1 patent drawingFigure 1
  • EP3758983B1 patent drawingFigure 2
  • EP3758983B1 patent drawingFigure 3

AI summary

Enhanced systems and methods for collision avoidance of a high value asset with reflective beacons around it using multi-sensor data fusion on a mobile industrial vehicle. The system has a sensing processing system with a LiDAR and camera sensors, and a multi¬ processor module responsive to the different sensors. The sensing processing system fuses the different sensor data to locate the reflective beacons. A model predictive controller on the vehicle determines possible control solutions where each defines a threshold allowable speed for the vehicle at discrete moments based upon an estimated path to a breaching point projected from the reflective beacons, and then identifies an optimal one of the control solutions based upon a performance cost function and associated with an optimal threshold allowable speed. The system has a vehicle actuator configured to respond and alter vehicle movement to avoid a collision when the vehicle exceeds the optimal threshold allowable speed.