Mobile Robot Road Crossing With Adaptive Detection Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile robots traveling outdoors face challenges in optimizing their autonomous operation while ensuring safety, particularly in crossing roads, due to false detections of hazardous objects, which can lead to unnecessary delays and reduced autonomy.
Innovation Solution
A method for setting detection thresholds based on various parameters such as weather, location, visibility, and historical safety data to transform probabilistic findings into discrete findings, allowing the robot to determine whether to cross a road autonomously or request human assistance, thereby balancing safety and autonomy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the robot uses strict detection thresholds to ensure safety, then safety is improved, but false detections increase causing unnecessary delays
Solution Approach 1:
The detection threshold is made dynamic rather than static. The system adjusts the threshold based on contextual factors including weather conditions, location characteristics, visibility levels, and historical safety data. This allows the threshold to be higher (more autonomous) in safe conditions and lower (more cautious) in hazardous conditions, resolving the contradiction between safety and speed
Solution Approach 2:
The system changes the detection threshold parameter adaptively based on multiple input parameters. By transforming probabilistic findings into discrete decisions using context-dependent thresholds, the system optimizes the balance between safety and autonomous operation percentage, reducing false detections while maintaining reliability
2Productivity
If the robot increases autonomous operation percentage, then productivity is improved, but safety may be compromised due to reduced human oversight
Solution Approach 1:
The system incorporates historical safety data as feedback to continuously refine detection thresholds. By analyzing past safety outcomes and adjusting thresholds accordingly, the system can operate more autonomously while maintaining safety standards, as the feedback loop ensures that autonomy increases only when safety conditions permit
Solution Approach 2:
The system performs preliminary assessment of safety conditions using historical data and environmental parameters before determining the appropriate detection threshold. This preliminary action allows the robot to establish safe autonomous operation boundaries in advance, enabling higher productivity without compromising safety
3Measurement precision
If the robot uses multiple sensors and strict detection, then measurement precision is improved, but false detections increase leading to reduced autonomy
Solution Approach 1:
The system applies different detection thresholds to different contextual situations rather than using a uniform threshold. By tailoring the threshold to local conditions (weather, location, visibility), the system maintains high measurement precision where needed while allowing higher autonomy in conditions where precision requirements are lower
Data Source
AI summary
A method for operating a robot traveling in an environment includes the robot sensing the environment and thereby creating sensor data; generating at least one probabilistic finding based on the sensor data, wherein the probabilistic finding is expressed as an object score and wherein the object score indicates a probability of detection of an object; setting at least one detection threshold; and, based on the at least one detection threshold, transforming the at least one probabilistic finding based on the sensor data to at least one discrete finding. The method is for operating a robot crossing a road. The robot is configured to be controlled by at least one human operator when crossing the road. Setting the at least one detection threshold is based on a level of supervision by the at least one human operator when crossing the road.