Methods and apparatus for multi-agent path finding within diagnostic laboratory systems
Patent Information
- Authority / Receiving Office
- EP · EP
- Patent Type
- Applications
- Current Assignee / Owner
- SIEMENS HEALTHCARE DIAGNOSTICS INC
- Filing Date
- 2024-08-07
- Publication Date
- 2026-06-17
AI Technical Summary
Determining the optimal paths and timing for transporting and processing multiple sample containers in diagnostic laboratory systems while avoiding collisions and unnecessary delays is challenging.
A method and apparatus that employ multi-agent path finding (MAPF) techniques using a trained neural network to determine actions for sample carriers, considering arrival, deadline, and precedence constraints, as well as non-instantaneous goal processing times.
The solution effectively optimizes the routing and processing of sample containers, reducing congestion and delays, and ensuring that samples are processed within their scheduled time windows.
Smart Images

Figure US2024041204_13022025_PF_FP_ABST