Autonomous Logistics Vehicle Vision for Dense Case Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automated logistics systems face challenges in navigation and object detection due to limited information from traditional sensors and impaired binocular vision systems, especially in densely packed and dynamically changing storage environments with deformities and irregularly placed cases.
Innovation Solution
The implementation of a vision system with pairs of inexpensive, unsynchronized two-dimensional rolling shutter cameras that generate stereo images, allowing for robust case/object detection and localization, combined with a controller that processes image data to create dense depth maps and keypoint data for accurate pose and location determination, even in super-constrained systems with closely packed and deformed cases.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If binocular cameras are used for vision guidance, then object detection capability is improved, but the system becomes impaired or unavailable due to blockage, view obstruction, or image degradation
Solution Approach 1:
The patent divides the vision system into multiple independent camera units distributed throughout the automated storage and retrieval system. Each camera captures images of cases from its local position, and the controller integrates these segmented views to form complete object detection and tracking capability, eliminating the single-point failure issue of binocular cameras
Solution Approach 2:
The patent employs cameras that serve multiple functions: they capture case images for identification, track case positions, detect case deformities, and provide navigation data. This multi-functional approach replaces the specialized binocular camera system while enhancing both detection capability and system reliability through functional redundancy
2Device complexity
If traditional sensors are used for navigation and object detection, then system simplicity is maintained, but information provided is limited for effective navigation and hazard identification
Solution Approach 1:
The patent replaces traditional mechanical sensors (proximity sensors, line following sensors, reflective beam sensors) with a vision-based system using cameras and image processing. This substitution provides richer information about case positions, orientations, and potential hazards while maintaining system simplicity through software-based processing rather than additional mechanical components
3Ease of manufacture
If stereo or binocular cameras are placed at conventional distances, then standard vision processing is enabled, but the system is unsuitable for warehousing logistics case storage and retrieval
Solution Approach 1:
The patent positions cameras at specific locations within the automated storage and retrieval system where they can optimally observe cases during storage and retrieval operations. Each camera is placed to capture specific views of cases at critical points, adapting the vision system to the unique requirements of warehousing logistics rather than using conventional stereo camera placements
Data Source
AI summary
An autonomous guided vehicle comprising a frame with a payload hold and a drive section coupled to the frame with drive wheels supporting the autonomous guided vehicle on a traverse surface, the drive wheels effect vehicle traverse on the traverse surface moving the autonomous guided vehicle over the traverse surface in a facility with a payload handler coupled to the frame configured to transfer a payload, with a flat undeterministic seating surface seated in the payload hold, to and from the payload hold of the autonomous guided vehicle and a storage location, of the payload. In a storage array with a vision system mounted to the frame, having more than one camera disposed to generate binocular images of a field of a logistic space including rack structure shelving on which more than one objects are stored and a controller, communicably connected to the vision system to register the binocular images.