Abstract
An autonomous payload agent architecture enables a physical shipment container to act as an independent routing agent. The cyber-physical transshipment container (CPTC) independently orchestrates its journey by negotiating with and transferring between different autonomous carriers using local mesh networks. The container operates in a low-power state until an onboard inertial measurement unit (IMU) detects a carrier anomaly, triggering a hardware interrupt that activates an edge-compute processor. Upon activation, the CPTC uses a graph attention network to select a nearby carrier from a dynamic graph of available transport options. The container then verifies the target carrier’s authorization using a zero-knowledge proof and computes a collision-free rendezvous trajectory using a control barrier function. Sensor-fused actuation, using ultra-wideband (UWB) ranging and load-cell sensors, confirms physical alignment before an electromechanical latch releases the container. This decentralized approach enables resilient and power-efficient multi-modal transshipment without reliance on a central cloud dispatcher.
Keywords: autonomous payload agent architecture, Cyber-Physical Transshipment Container, multi-agent reinforcement learning, local mesh network, inertial measurement unit, Graph Attention Network, Zero-Knowledge Proof, Control Barrier Function, electromechanical latch, vehicle-to-everything (V2X)
Creative Commons License
This work is licensed under a Creative Commons Attribution 4.0 License.
Recommended Citation
S R, Mithun Kumar, "Autonomous Payload Agent Architecture for Decentralized Multi-Modal Transshipment", Technical Disclosure Commons, ()
https://www.tdcommons.org/dpubs_series/12552