Working Machine Camera Alerting for 360° Collision Avoidance

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Off-highway vehicles face challenges in avoiding collisions with workers or animals due to limited visibility, particularly during reversing, slow-speed maneuvers, loading/unloading, and implement coupling/uncoupling, leading to frequent incidents.

Innovation Solution

A working machine equipped with a collision avoidance system featuring multiple cameras and a machine learning algorithm to detect animate objects, providing alerts and warnings to operators through a control system, and a 360° field of view using overlapping camera fields to ensure comprehensive monitoring.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If multiple cameras are installed to provide 360° field of view, then the coverage area is improved, but the device complexity increases

Engineering Contradiction:
Improvecoverage areaVSAvoiddevice complexity
Core Design Contradiction:
Area of stationary objectVSDevice complexity

Solution Approach 1:

Multiple camera fields of view are merged to provide comprehensive 360° coverage of the working environment. The camera system combines multiple viewing angles to create a complete surveillance area around the machine

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The camera system serves multiple functions: detecting animate objects, providing operator awareness, and enabling collision avoidance across all directions simultaneously

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

2Measurement precision

If machine learning algorithm is used to detect animate objects, then the detection accuracy is improved, but the processing time increases

Engineering Contradiction:
Improvedetection accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The machine learning algorithm is pre-trained with extensive data about animate objects before deployment. This preliminary training enables the system to quickly recognize and classify objects during actual operation without requiring complex real-time processing

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

Traditional mechanical or rule-based detection systems are replaced with machine learning-based computer vision algorithms that can process visual data more efficiently and accurately

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Reliability

If collision avoidance system with alerts is implemented, then the safety is improved, but the device complexity increases

Engineering Contradiction:
ImprovesafetyVSAvoiddevice complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system provides immediate feedback to the operator through alerts when animate objects are detected. This feedback loop enables real-time collision avoidance by notifying the operator of potential hazards in the working area

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The control system acts as an intermediary between the camera detection system and the operator. It processes detection data and translates it into actionable alert signals that communicate hazard information to the operator

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP4717833A2A working machine
Publication Date: 2026.04.01 J C BAMFORD EXCAVATORS LTD
  • EP4717833A2 patent drawingFigure 1
  • EP4717833A2 patent drawingFigure 2
  • EP4717833A2 patent drawingFigure 3

AI summary

A working machine includes a body, a ground engaging propulsion structure supporting the body, and a working arm mounted to the body. The machine also includes a control system and a collision avoidance system. The collision avoidance system has a camera mounted on the body of the working machine configured to monitor an area in its field of view and to generate an output signal to the control system in response to a detected animate object in said field of view. The control system includes a processor configured to execute a machine learning algorithm trained to determine whether the detected animate object is an animate object to determine whether an animate object is within the field of view of the at least one camera from the camera output signal. The system provides an output to alert an operator of the working machine if it is determined that an animate object has been detected in the field of view of the at least one camera.