Thermal Imaging Obstacle Detection for AGVs in Obscured Environments
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous guided vehicles (AGVs) struggle to effectively detect obstacles, particularly in non-industrial environments, such as retail stores, where traditional navigation systems like LiDAR, badge sensors, and camera-based systems fail to accurately identify humans obscured by objects or lack infrastructure support, leading to potential collisions.
Innovation Solution
Implementing a thermal imaging sensor system with an automation processing system that uses machine learning to detect and analyze heat-emitting obstacles, combined with auxiliary sensors, to provide real-time obstacle detection and control actions for AGVs, enabling 360-degree field of view and obstacle motion tracking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional navigation systems like LiDAR, badge sensors, and camera-based systems are used, then the AGV can navigate in industrial environments with infrastructure support, but the system fails to accurately identify humans obscured by objects or detect obstacles in non-industrial environments without additional infrastructure
Solution Approach 1:
The thermal imaging sensor system provides universal obstacle detection capability that functions across both industrial and non-industrial environments without requiring environment-specific infrastructure. The system detects heat-emitting obstacles including humans, animals, and hot objects regardless of whether the environment has badges, LiDAR infrastructure, or camera coverage, making the AGV adaptable to diverse settings from warehouses to retail stores and homes.
Solution Approach 2:
The thermal imaging sensor acts as an intermediary detection mechanism that bridges the gap between active sensing systems (LiDAR, cameras) and passive obstacle detection. By detecting thermal radiation emitted or reflected from obstacles, the system provides reliable detection of obscured objects and humans without requiring line-of-sight or infrastructure support, complementing traditional navigation systems.
2Reliability
If badge sensors are used to track people and vehicles, then the system can identify obstacles in industrial environments, but it requires every person to be fitted with a badge which is not feasible in non-industrial environments
Solution Approach 1:
The thermal imaging sensor system enables obstacles to be detected through their own thermal radiation properties rather than requiring external tagging infrastructure. Humans, animals, and hot objects naturally emit or reflect thermal energy that the sensor can detect without any modification to the obstacles themselves, eliminating the need for badges or tags and enabling deployment in environments where infusing obstacles with sensors is not feasible.
3Measurement precision
If camera-based line-of-sight imaging is used to predict human presence, then the system can detect visible obstacles, but it cannot determine whether a detected obstacle is a human when the person is carrying a large box, obscured by infrastructure, or in a wheelchair
Solution Approach 1:
The thermal imaging sensor focuses on detecting the local thermal signature of obstacles, particularly the heat-emitting characteristics of human bodies and warm objects. This local thermal detection capability allows the system to identify humans and obstacles even when their overall shape or form is obscured by boxes, infrastructure, or unusual positions, as the thermal radiation from the obstacle itself provides identifying characteristics independent of visual appearance.
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 obstacle detection capabilities in diverse environments by identifying heat-emitting objects regardless of obstruction, reducing collision risks, and allowing proactive control decisions without additional infrastructure, suitable for both industrial and non-industrial settings.
Implementation Method 1
receive sensor data based on an output of a thermal imaging sensor; process the sensor data to determine at least one of a presence or a motion of a heat-emitting obstacle
Data Source
Figure 1
Figure 2A~2B
Figure 3
AI summary
Systems and methods of obstacle detection and AGV control comprise and/or utilize a thermal imaging sensor; and an automation processing system (APS) (110) having a processor and a memory, the APS (110) coupled with the thermal imaging sensor (202) and being configured to: receive sensor data based on an output of the thermal imaging sensor (202), process the sensor data to determine at least one of a presence or a motion of a heat-emitting obstacle (504, 506, 508) in a vicinity of the AGV (130), generate, based on the processed sensor data, an output comprising an indication of a control action for the AGV (130), and send the generated output to the VCS (210).