Mobile Robot Safety Control Using AI Hazard Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing mobile robot devices face challenges in ensuring user safety while providing services, as they may malfunction and cause accidents due to inadequate environmental sensing and control mechanisms.
Innovation Solution
A mobile robot device equipped with a training model trained using an artificial intelligence algorithm, which senses the surrounding environment and adjusts its safety operation level to prevent accidents by controlling its movement and arm device operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a mobile robot device provides services to users, then user service capability is improved, but safety risk increases due to potential malfunction and inadequate environmental sensing
Solution Approach 1:
The robot performs preliminary environmental sensing and hazard prediction before executing service tasks. The processor continuously analyzes surrounding environment data using trained models to predict potential dangerous situations in advance, allowing the robot to adjust its operation level proactively rather than reactively, thus preventing accidents before they occur.
Solution Approach 2:
The system implements continuous feedback loops where the robot senses the environment, processes data through trained models, predicts dangerous situations, and adjusts its operation level accordingly. This closed-loop control ensures that service provision continues safely by constantly monitoring environmental conditions and adapting behavior based on predicted risks.
2Reliability
If the mobile robot device increases environmental sensing and safety control mechanisms, then safety is improved, but device complexity increases
Solution Approach 1:
The processor serves multiple functions: it controls basic robot operations, processes environmental sensor data, runs trained prediction models, and adjusts safety parameters. By making the processor multi-functional rather than adding separate dedicated hardware for each function, the system achieves enhanced safety without proportionally increasing device complexity.
Solution Approach 2:
The robot uses its own sensing capabilities and processed environmental data to autonomously predict dangerous situations and adjust its operation level. The trained models enable the system to self-evaluate safety conditions and self-regulate its behavior without external intervention, reducing the need for additional complex external safety systems.
3Measurement precision
If the mobile robot device uses AI training models for real-time environmental prediction, then safety prediction accuracy is improved, but computational resource consumption increases
Solution Approach 1:
The system applies prediction models selectively based on environmental context and robot operation states. Rather than continuously running full computational models at maximum precision, the processor adjusts the level of prediction analysis to match the actual risk level and service requirements, consuming computational resources proportionally to the situation's complexity and urgency.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Provided are an artificial intelligence (Al) system utilizing a machine learning algorithm such as deep learning and an application thereof. A method of providing, by a mobile robot device including an arm device, a service to a user includes obtaining sensing information obtained by sensing a surrounding environment of the mobile robot device while the mobile robot device is traveling, changing, based on the sensing information which has been obtained by sensing, a safety operation level of the mobile robot device, and controlling, based on the changed safety operation level, an operation of the mobile robot device, wherein the safety operation level is a level for controlling an operation related to a movement of the mobile robot device and a motion of the arm device, and the mobile robot device changes the safety operation level by applying the obtained sensed information to a training model trained using an artificial intelligence algorithm.